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>
16 ;;; Copyright © 2019 Brian Leung <bkleung89@gmail.com>
18 ;;; This file is part of GNU Guix.
20 ;;; GNU Guix is free software; you can redistribute it and/or modify it
21 ;;; under the terms of the GNU General Public License as published by
22 ;;; the Free Software Foundation; either version 3 of the License, or (at
23 ;;; your option) any later version.
25 ;;; GNU Guix is distributed in the hope that it will be useful, but
26 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
27 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
28 ;;; GNU General Public License for more details.
30 ;;; You should have received a copy of the GNU General Public License
31 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
33 (define-module (gnu packages bioinformatics)
34 #:use-module ((guix licenses) #:prefix license:)
35 #:use-module (guix packages)
36 #:use-module (guix utils)
37 #:use-module (guix download)
38 #:use-module (guix git-download)
39 #:use-module (guix hg-download)
40 #:use-module (guix build-system ant)
41 #:use-module (guix build-system gnu)
42 #:use-module (guix build-system cmake)
43 #:use-module (guix build-system haskell)
44 #:use-module (guix build-system meson)
45 #:use-module (guix build-system ocaml)
46 #:use-module (guix build-system perl)
47 #:use-module (guix build-system python)
48 #:use-module (guix build-system r)
49 #:use-module (guix build-system ruby)
50 #:use-module (guix build-system scons)
51 #:use-module (guix build-system trivial)
52 #:use-module (gnu packages)
53 #:use-module (gnu packages autotools)
54 #:use-module (gnu packages algebra)
55 #:use-module (gnu packages base)
56 #:use-module (gnu packages bash)
57 #:use-module (gnu packages bison)
58 #:use-module (gnu packages bioconductor)
59 #:use-module (gnu packages boost)
60 #:use-module (gnu packages check)
61 #:use-module (gnu packages code)
62 #:use-module (gnu packages compression)
63 #:use-module (gnu packages cpio)
64 #:use-module (gnu packages cran)
65 #:use-module (gnu packages curl)
66 #:use-module (gnu packages documentation)
67 #:use-module (gnu packages databases)
68 #:use-module (gnu packages datastructures)
69 #:use-module (gnu packages file)
70 #:use-module (gnu packages flex)
71 #:use-module (gnu packages gawk)
72 #:use-module (gnu packages gcc)
73 #:use-module (gnu packages gd)
74 #:use-module (gnu packages gtk)
75 #:use-module (gnu packages glib)
76 #:use-module (gnu packages graph)
77 #:use-module (gnu packages groff)
78 #:use-module (gnu packages guile)
79 #:use-module (gnu packages guile-xyz)
80 #:use-module (gnu packages haskell)
81 #:use-module (gnu packages haskell-check)
82 #:use-module (gnu packages haskell-web)
83 #:use-module (gnu packages image)
84 #:use-module (gnu packages imagemagick)
85 #:use-module (gnu packages java)
86 #:use-module (gnu packages java-compression)
87 #:use-module (gnu packages jemalloc)
88 #:use-module (gnu packages dlang)
89 #:use-module (gnu packages linux)
90 #:use-module (gnu packages lisp)
91 #:use-module (gnu packages logging)
92 #:use-module (gnu packages machine-learning)
93 #:use-module (gnu packages man)
94 #:use-module (gnu packages maths)
95 #:use-module (gnu packages mpi)
96 #:use-module (gnu packages ncurses)
97 #:use-module (gnu packages ocaml)
98 #:use-module (gnu packages pcre)
99 #:use-module (gnu packages parallel)
100 #:use-module (gnu packages pdf)
101 #:use-module (gnu packages perl)
102 #:use-module (gnu packages perl-check)
103 #:use-module (gnu packages pkg-config)
104 #:use-module (gnu packages popt)
105 #:use-module (gnu packages protobuf)
106 #:use-module (gnu packages python)
107 #:use-module (gnu packages python-compression)
108 #:use-module (gnu packages python-web)
109 #:use-module (gnu packages python-xyz)
110 #:use-module (gnu packages readline)
111 #:use-module (gnu packages ruby)
112 #:use-module (gnu packages serialization)
113 #:use-module (gnu packages shells)
114 #:use-module (gnu packages sphinx)
115 #:use-module (gnu packages statistics)
116 #:use-module (gnu packages swig)
117 #:use-module (gnu packages tbb)
118 #:use-module (gnu packages tex)
119 #:use-module (gnu packages texinfo)
120 #:use-module (gnu packages textutils)
121 #:use-module (gnu packages time)
122 #:use-module (gnu packages tls)
123 #:use-module (gnu packages vim)
124 #:use-module (gnu packages web)
125 #:use-module (gnu packages xml)
126 #:use-module (gnu packages xorg)
127 #:use-module (srfi srfi-1)
128 #:use-module (ice-9 match))
130 (define-public aragorn
137 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
141 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
142 (build-system gnu-build-system)
144 `(#:tests? #f ; there are no tests
146 (modify-phases %standard-phases
156 (string-append "aragorn" ,version ".c"))
159 (lambda* (#:key outputs #:allow-other-keys)
160 (let* ((out (assoc-ref outputs "out"))
161 (bin (string-append out "/bin"))
162 (man (string-append out "/share/man/man1")))
163 (install-file "aragorn" bin)
164 (install-file "aragorn.1" man))
166 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
167 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
169 "Aragorn identifies transfer RNA, mitochondrial RNA and
170 transfer-messenger RNA from nucleotide sequences, based on homology to known
171 tRNA consensus sequences and RNA structure. It also outputs the secondary
172 structure of the predicted RNA.")
173 (license license:gpl2)))
181 ;; BamM is not available on pypi.
183 (url "https://github.com/Ecogenomics/BamM.git")
186 (file-name (git-file-name name version))
189 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
190 (modules '((guix build utils)))
193 ;; Delete bundled htslib.
194 (delete-file-recursively "c/htslib-1.3.1")
196 (build-system python-build-system)
198 `(#:python ,python-2 ; BamM is Python 2 only.
199 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
200 ;; been modified from its original form.
202 (let ((htslib (assoc-ref %build-inputs "htslib")))
203 (list "--with-libhts-lib" (string-append htslib "/lib")
204 "--with-libhts-inc" (string-append htslib "/include/htslib")))
206 (modify-phases %standard-phases
207 (add-after 'unpack 'autogen
209 (with-directory-excursion "c"
210 (let ((sh (which "sh")))
211 (for-each make-file-writable (find-files "." ".*"))
212 ;; Use autogen so that 'configure' works.
213 (substitute* "autogen.sh" (("/bin/sh") sh))
214 (setenv "CONFIG_SHELL" sh)
215 (invoke "./autogen.sh")))
218 ;; Run tests after installation so compilation only happens once.
220 (add-after 'install 'wrap-executable
221 (lambda* (#:key outputs #:allow-other-keys)
222 (let* ((out (assoc-ref outputs "out"))
223 (path (getenv "PATH")))
224 (wrap-program (string-append out "/bin/bamm")
225 `("PATH" ":" prefix (,path))))
227 (add-after 'wrap-executable 'post-install-check
228 (lambda* (#:key inputs outputs #:allow-other-keys)
230 (string-append (assoc-ref outputs "out")
235 (assoc-ref outputs "out")
237 (string-take (string-take-right
238 (assoc-ref inputs "python") 5) 3)
240 (getenv "PYTHONPATH")))
241 ;; There are 2 errors printed, but they are safe to ignore:
242 ;; 1) [E::hts_open_format] fail to open file ...
243 ;; 2) samtools view: failed to open ...
247 `(("autoconf" ,autoconf)
248 ("automake" ,automake)
251 ("python-nose" ,python2-nose)
252 ("python-pysam" ,python2-pysam)))
254 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
255 ("samtools" ,samtools)
259 ("coreutils" ,coreutils)))
261 `(("python-numpy" ,python2-numpy)))
262 (home-page "http://ecogenomics.github.io/BamM/")
263 (synopsis "Metagenomics-focused BAM file manipulator")
265 "BamM is a C library, wrapped in python, to efficiently generate and
266 parse BAM files, specifically for the analysis of metagenomic data. For
267 instance, it implements several methods to assess contig-wise read coverage.")
268 (license license:lgpl3+)))
270 (define-public bamtools
277 (url "https://github.com/pezmaster31/bamtools.git")
278 (commit (string-append "v" version))))
279 (file-name (git-file-name name version))
282 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
283 (build-system cmake-build-system)
285 `(#:tests? #f ;no "check" target
287 (modify-phases %standard-phases
289 'configure 'set-ldflags
290 (lambda* (#:key outputs #:allow-other-keys)
294 (assoc-ref outputs "out") "/lib/bamtools"))
296 (inputs `(("zlib" ,zlib)))
297 (home-page "https://github.com/pezmaster31/bamtools")
298 (synopsis "C++ API and command-line toolkit for working with BAM data")
300 "BamTools provides both a C++ API and a command-line toolkit for handling
302 (license license:expat)))
304 (define-public bcftools
310 (uri (string-append "https://github.com/samtools/bcftools/"
312 version "/bcftools-" version ".tar.bz2"))
315 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
316 (modules '((guix build utils)))
318 ;; Delete bundled htslib.
319 (delete-file-recursively "htslib-1.9")
321 (build-system gnu-build-system)
324 (list "--enable-libgsl")
327 (modify-phases %standard-phases
328 (add-before 'check 'patch-tests
330 (substitute* "test/test.pl"
331 (("/bin/bash") (which "bash")))
339 (home-page "https://samtools.github.io/bcftools/")
340 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
342 "BCFtools is a set of utilities that manipulate variant calls in the
343 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
344 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
345 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
346 (license (list license:gpl3+ license:expat))))
348 (define-public bedops
355 (url "https://github.com/bedops/bedops.git")
356 (commit (string-append "v" version))))
357 (file-name (git-file-name name version))
360 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
361 (build-system gnu-build-system)
364 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
366 (modify-phases %standard-phases
367 (add-after 'unpack 'unpack-tarballs
369 ;; FIXME: Bedops includes tarballs of minimally patched upstream
370 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
371 ;; libraries because at least one of the libraries (zlib) is
372 ;; patched to add a C++ function definition (deflateInit2cpp).
373 ;; Until the Bedops developers offer a way to link against system
374 ;; libraries we have to build the in-tree copies of these three
377 ;; See upstream discussion:
378 ;; https://github.com/bedops/bedops/issues/124
380 ;; Unpack the tarballs to benefit from shebang patching.
381 (with-directory-excursion "third-party"
382 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
383 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
384 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
385 ;; Disable unpacking of tarballs in Makefile.
386 (substitute* "system.mk/Makefile.linux"
387 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
388 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
389 (substitute* "third-party/zlib-1.2.7/Makefile.in"
390 (("^SHELL=.*$") "SHELL=bash\n"))
392 (delete 'configure))))
393 (home-page "https://github.com/bedops/bedops")
394 (synopsis "Tools for high-performance genomic feature operations")
396 "BEDOPS is a suite of tools to address common questions raised in genomic
397 studies---mostly with regard to overlap and proximity relationships between
398 data sets. It aims to be scalable and flexible, facilitating the efficient
399 and accurate analysis and management of large-scale genomic data.
401 BEDOPS provides tools that perform highly efficient and scalable Boolean and
402 other set operations, statistical calculations, archiving, conversion and
403 other management of genomic data of arbitrary scale. Tasks can be easily
404 split by chromosome for distributing whole-genome analyses across a
405 computational cluster.")
406 (license license:gpl2+)))
408 (define-public bedtools
414 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
415 "download/v" version "/"
416 "bedtools-" version ".tar.gz"))
419 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
420 (build-system gnu-build-system)
422 '(#:test-target "test"
424 (list (string-append "prefix=" (assoc-ref %outputs "out")))
426 (modify-phases %standard-phases
427 (delete 'configure))))
428 (native-inputs `(("python" ,python-2)))
430 `(("samtools" ,samtools)
432 (home-page "https://github.com/arq5x/bedtools2")
433 (synopsis "Tools for genome analysis and arithmetic")
435 "Collectively, the bedtools utilities are a swiss-army knife of tools for
436 a wide-range of genomics analysis tasks. The most widely-used tools enable
437 genome arithmetic: that is, set theory on the genome. For example, bedtools
438 allows one to intersect, merge, count, complement, and shuffle genomic
439 intervals from multiple files in widely-used genomic file formats such as BAM,
441 (license license:gpl2)))
443 ;; Later releases of bedtools produce files with more columns than
444 ;; what Ribotaper expects.
445 (define-public bedtools-2.18
446 (package (inherit bedtools)
451 (uri (string-append "https://github.com/arq5x/bedtools2/"
452 "releases/download/v" version
453 "/bedtools-" version ".tar.gz"))
456 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
458 '(#:test-target "test"
460 (modify-phases %standard-phases
463 (lambda* (#:key outputs #:allow-other-keys)
464 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
465 (for-each (lambda (file)
466 (install-file file bin))
467 (find-files "bin" ".*")))
470 ;; Needed for pybedtools.
471 (define-public bedtools-2.26
472 (package (inherit bedtools)
477 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
478 "download/v" version "/"
479 "bedtools-" version ".tar.gz"))
482 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
491 (url "https://github.com/PacificBiosciences/pbbam.git")
493 (file-name (git-file-name name version))
496 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
497 (build-system meson-build-system)
500 (modify-phases %standard-phases
501 (add-after 'unpack 'find-googletest
502 (lambda* (#:key inputs #:allow-other-keys)
503 ;; It doesn't find gtest_main because there's no pkg-config file
504 ;; for it. Find it another way.
505 (substitute* "tests/meson.build"
506 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
507 (format #f "cpp = meson.get_compiler('cpp')
508 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
509 (assoc-ref inputs "googletest"))))
511 ;; TODO: tests/pbbam_test cannot be linked
512 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
513 ;; undefined reference to symbol '_ZTIN7testing4TestE'
514 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
515 ;; error adding symbols: DSO missing from command line
517 #:configure-flags '("-Dtests=false")))
518 ;; These libraries are listed as "Required" in the pkg-config file.
524 ("samtools" ,samtools)))
526 `(("googletest" ,googletest)
527 ("pkg-config" ,pkg-config)
528 ("python" ,python-wrapper))) ; for tests
529 (home-page "https://github.com/PacificBiosciences/pbbam")
530 (synopsis "Work with PacBio BAM files")
532 "The pbbam software package provides components to create, query, and
533 edit PacBio BAM files and associated indices. These components include a core
534 C++ library, bindings for additional languages, and command-line utilities.
535 This library is not intended to be used as a general-purpose BAM utility - all
536 input and output BAMs must adhere to the PacBio BAM format specification.
537 Non-PacBio BAMs will cause exceptions to be thrown.")
538 (license license:bsd-3)))
540 (define-public blasr-libcpp
542 (name "blasr-libcpp")
547 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
549 (file-name (git-file-name name version))
552 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
553 (build-system meson-build-system)
556 (modify-phases %standard-phases
557 (add-after 'unpack 'link-with-hdf5
558 (lambda* (#:key inputs #:allow-other-keys)
559 (let ((hdf5 (assoc-ref inputs "hdf5")))
560 (substitute* "meson.build"
561 (("libblasr_deps = \\[" m)
564 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
565 cpp.find_library('hdf5_cpp', dirs : '~a'), "
568 (add-after 'unpack 'find-googletest
569 (lambda* (#:key inputs #:allow-other-keys)
570 ;; It doesn't find gtest_main because there's no pkg-config file
571 ;; for it. Find it another way.
572 (substitute* "unittest/meson.build"
573 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
574 (format #f "cpp = meson.get_compiler('cpp')
575 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
576 (assoc-ref inputs "googletest"))))
578 ;; TODO: unittest/libblasr_unittest cannot be linked
579 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
580 ;; undefined reference to symbol
581 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
582 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
583 ;; error adding symbols: DSO missing from command line
585 #:configure-flags '("-Dtests=false")))
592 `(("googletest" ,googletest)
593 ("pkg-config" ,pkg-config)))
594 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
595 (synopsis "Library for analyzing PacBio genomic sequences")
597 "This package provides three libraries used by applications for analyzing
598 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
600 (license license:bsd-3)))
609 (url "https://github.com/PacificBiosciences/blasr.git")
611 (file-name (git-file-name name version))
614 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
615 (build-system meson-build-system)
618 (modify-phases %standard-phases
619 (add-after 'unpack 'link-with-hdf5
620 (lambda* (#:key inputs #:allow-other-keys)
621 (let ((hdf5 (assoc-ref inputs "hdf5")))
622 (substitute* "meson.build"
623 (("blasr_deps = \\[" m)
626 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
627 cpp.find_library('hdf5_cpp', dirs : '~a'), "
630 ;; Tests require "cram" executable, which is not packaged.
632 #:configure-flags '("-Dtests=false")))
635 ("blasr-libcpp" ,blasr-libcpp)
640 `(("pkg-config" ,pkg-config)))
641 (home-page "https://github.com/PacificBiosciences/blasr")
642 (synopsis "PacBio long read aligner")
644 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
645 (license license:bsd-3)))
647 (define-public ribotaper
653 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
654 "files/RiboTaper/RiboTaper_Version_"
658 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
659 (build-system gnu-build-system)
662 (modify-phases %standard-phases
663 (add-after 'install 'wrap-executables
664 (lambda* (#:key inputs outputs #:allow-other-keys)
665 (let* ((out (assoc-ref outputs "out")))
668 (wrap-program (string-append out "/bin/" script)
669 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
670 '("create_annotations_files.bash"
671 "create_metaplots.bash"
672 "Ribotaper_ORF_find.sh"
676 `(("bedtools" ,bedtools-2.18)
677 ("samtools" ,samtools-0.1)
678 ("r-minimal" ,r-minimal)
679 ("r-foreach" ,r-foreach)
680 ("r-xnomial" ,r-xnomial)
682 ("r-multitaper" ,r-multitaper)
683 ("r-seqinr" ,r-seqinr)))
684 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
685 (synopsis "Define translated ORFs using ribosome profiling data")
687 "Ribotaper is a method for defining translated @dfn{open reading
688 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
689 provides the Ribotaper pipeline.")
690 (license license:gpl3+)))
692 (define-public ribodiff
700 (url "https://github.com/ratschlab/RiboDiff.git")
701 (commit (string-append "v" version))))
702 (file-name (git-file-name name version))
705 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
706 (build-system python-build-system)
710 (modify-phases %standard-phases
711 ;; Generate an installable executable script wrapper.
712 (add-after 'unpack 'patch-setup.py
714 (substitute* "setup.py"
715 (("^(.*)packages=.*" line prefix)
716 (string-append line "\n"
717 prefix "scripts=['scripts/TE.py'],\n")))
720 `(("python-numpy" ,python2-numpy)
721 ("python-matplotlib" ,python2-matplotlib)
722 ("python-scipy" ,python2-scipy)
723 ("python-statsmodels" ,python2-statsmodels)))
725 `(("python-mock" ,python2-mock)
726 ("python-nose" ,python2-nose)))
727 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
728 (synopsis "Detect translation efficiency changes from ribosome footprints")
729 (description "RiboDiff is a statistical tool that detects the protein
730 translational efficiency change from Ribo-Seq (ribosome footprinting) and
731 RNA-Seq data. It uses a generalized linear model to detect genes showing
732 difference in translational profile taking mRNA abundance into account. It
733 facilitates us to decipher the translational regulation that behave
734 independently with transcriptional regulation.")
735 (license license:gpl3+)))
737 (define-public bioawk
744 (url "https://github.com/lh3/bioawk.git")
745 (commit (string-append "v" version))))
746 (file-name (git-file-name name version))
749 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
750 (build-system gnu-build-system)
756 `(#:tests? #f ; There are no tests to run.
757 ;; Bison must generate files, before other targets can build.
760 (modify-phases %standard-phases
761 (delete 'configure) ; There is no configure phase.
763 (lambda* (#:key outputs #:allow-other-keys)
764 (let* ((out (assoc-ref outputs "out"))
765 (bin (string-append out "/bin"))
766 (man (string-append out "/share/man/man1")))
768 (copy-file "awk.1" (string-append man "/bioawk.1"))
769 (install-file "bioawk" bin))
771 (home-page "https://github.com/lh3/bioawk")
772 (synopsis "AWK with bioinformatics extensions")
773 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
774 support of several common biological data formats, including optionally gzip'ed
775 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
776 also adds a few built-in functions and a command line option to use TAB as the
777 input/output delimiter. When the new functionality is not used, bioawk is
778 intended to behave exactly the same as the original BWK awk.")
779 (license license:x11)))
781 (define-public python-pybedtools
783 (name "python-pybedtools")
787 (uri (pypi-uri "pybedtools" version))
790 "1xl454ijvd4dzfvqgfahad49b49j7qy710fq9xh1rvk42z6x5ssf"))))
791 (build-system python-build-system)
793 `(#:modules ((ice-9 ftw)
797 (guix build python-build-system))
798 ;; See https://github.com/daler/pybedtools/issues/192
800 (modify-phases %standard-phases
801 ;; See https://github.com/daler/pybedtools/issues/261
802 (add-after 'unpack 'disable-broken-tests
804 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
805 ;; graphical environment.
806 (substitute* "pybedtools/test/test_scripts.py"
807 (("def test_venn_mpl")
808 "def _do_not_test_venn_mpl"))
809 (substitute* "pybedtools/test/test_helpers.py"
810 ;; Requires internet access.
811 (("def test_chromsizes")
812 "def _do_not_test_chromsizes")
813 ;; Broken as a result of the workaround used in the check phase
814 ;; (see: https://github.com/daler/pybedtools/issues/192).
815 (("def test_getting_example_beds")
816 "def _do_not_test_getting_example_beds"))
818 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
820 ;; Force the Cythonization of C++ files to guard against compilation
822 (add-after 'unpack 'remove-cython-generated-files
824 (let ((cython-sources (map (cut string-drop-right <> 4)
825 (find-files "." "\\.pyx$")))
826 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
827 (define (strip-extension filename)
828 (string-take filename (string-index-right filename #\.)))
829 (define (cythonized? c/c++-file)
830 (member (strip-extension c/c++-file) cython-sources))
831 (for-each delete-file (filter cythonized? c/c++-files))
833 (add-after 'remove-cython-generated-files 'generate-cython-extensions
835 (invoke "python" "setup.py" "cythonize")))
838 (let* ((cwd (getcwd))
839 (build-root-directory (string-append cwd "/build/"))
840 (build (string-append
842 (find (cut string-prefix? "lib" <>)
843 (scandir (string-append
844 build-root-directory)))))
845 (scripts (string-append
847 (find (cut string-prefix? "scripts" <>)
848 (scandir build-root-directory)))))
850 (string-append build ":" (getenv "PYTHONPATH")))
851 ;; Executable scripts such as 'intron_exon_reads.py' must be
852 ;; available in the PATH.
854 (string-append scripts ":" (getenv "PATH"))))
855 ;; The tests need to be run from elsewhere...
856 (mkdir-p "/tmp/test")
857 (copy-recursively "pybedtools/test" "/tmp/test")
858 (with-directory-excursion "/tmp/test"
859 (invoke "pytest")))))))
861 `(("bedtools" ,bedtools)
862 ("samtools" ,samtools)
863 ("python-matplotlib" ,python-matplotlib)
864 ("python-pysam" ,python-pysam)
865 ("python-pyyaml" ,python-pyyaml)))
867 `(("python-numpy" ,python-numpy)
868 ("python-pandas" ,python-pandas)
869 ("python-cython" ,python-cython)
870 ("kentutils" ,kentutils) ; for bedGraphToBigWig
871 ("python-six" ,python-six)
872 ;; For the test suite.
873 ("python-pytest" ,python-pytest)
874 ("python-psutil" ,python-psutil)))
875 (home-page "https://pythonhosted.org/pybedtools/")
876 (synopsis "Python wrapper for BEDtools programs")
878 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
879 which are widely used for genomic interval manipulation or \"genome algebra\".
880 pybedtools extends BEDTools by offering feature-level manipulations from with
882 (license license:gpl2+)))
884 (define-public python2-pybedtools
885 (package-with-python2 python-pybedtools))
887 (define-public python-biom-format
889 (name "python-biom-format")
894 ;; Use GitHub as source because PyPI distribution does not contain
895 ;; test data: https://github.com/biocore/biom-format/issues/693
897 (url "https://github.com/biocore/biom-format.git")
899 (file-name (git-file-name name version))
902 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
903 (modules '((guix build utils)))
905 ;; Delete generated C files.
906 (for-each delete-file (find-files "." "\\.c"))
908 (build-system python-build-system)
911 (modify-phases %standard-phases
912 (add-after 'unpack 'use-cython
913 (lambda _ (setenv "USE_CYTHON" "1") #t))
914 (add-after 'unpack 'disable-broken-tests
916 (substitute* "biom/tests/test_cli/test_validate_table.py"
917 (("^(.+)def test_invalid_hdf5" m indent)
918 (string-append indent
919 "@npt.dec.skipif(True, msg='Guix')\n"
921 (substitute* "biom/tests/test_table.py"
922 (("^(.+)def test_from_hdf5_issue_731" m indent)
923 (string-append indent
924 "@npt.dec.skipif(True, msg='Guix')\n"
927 (add-before 'reset-gzip-timestamps 'make-files-writable
928 (lambda* (#:key outputs #:allow-other-keys)
929 (let ((out (assoc-ref outputs "out")))
930 (for-each (lambda (file) (chmod file #o644))
931 (find-files out "\\.gz"))
934 `(("python-numpy" ,python-numpy)
935 ("python-scipy" ,python-scipy)
936 ("python-flake8" ,python-flake8)
937 ("python-future" ,python-future)
938 ("python-click" ,python-click)
939 ("python-h5py" ,python-h5py)
940 ("python-pandas" ,python-pandas)))
942 `(("python-cython" ,python-cython)
943 ("python-pytest" ,python-pytest)
944 ("python-pytest-cov" ,python-pytest-cov)
945 ("python-nose" ,python-nose)))
946 (home-page "http://www.biom-format.org")
947 (synopsis "Biological Observation Matrix (BIOM) format utilities")
949 "The BIOM file format is designed to be a general-use format for
950 representing counts of observations e.g. operational taxonomic units, KEGG
951 orthology groups or lipid types, in one or more biological samples
952 e.g. microbiome samples, genomes, metagenomes.")
953 (license license:bsd-3)
954 (properties `((python2-variant . ,(delay python2-biom-format))))))
956 (define-public python2-biom-format
957 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
961 (substitute-keyword-arguments (package-arguments base)
963 `(modify-phases ,phases
964 ;; Do not require the unmaintained pyqi library.
965 (add-after 'unpack 'remove-pyqi
967 (substitute* "setup.py"
968 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
971 (define-public bioperl-minimal
972 (let* ((inputs `(("perl-module-build" ,perl-module-build)
973 ("perl-data-stag" ,perl-data-stag)
974 ("perl-libwww" ,perl-libwww)
975 ("perl-uri" ,perl-uri)))
977 (map (compose package-name cadr)
980 (map (compose package-transitive-target-inputs cadr) inputs))))))
982 (name "bioperl-minimal")
987 (uri (string-append "https://github.com/bioperl/bioperl-live/"
989 (string-map (lambda (c)
995 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
996 (build-system perl-build-system)
999 (modify-phases %standard-phases
1001 'install 'wrap-programs
1002 (lambda* (#:key outputs #:allow-other-keys)
1003 ;; Make sure all executables in "bin" find the required Perl
1004 ;; modules at runtime. As the PERL5LIB variable contains also
1005 ;; the paths of native inputs, we pick the transitive target
1006 ;; inputs from %build-inputs.
1007 (let* ((out (assoc-ref outputs "out"))
1008 (bin (string-append out "/bin/"))
1010 (cons (string-append out "/lib/perl5/site_perl")
1012 (assoc-ref %build-inputs name))
1013 ',transitive-inputs))
1015 (for-each (lambda (file)
1017 `("PERL5LIB" ":" prefix (,path))))
1018 (find-files bin "\\.pl$"))
1022 `(("perl-test-most" ,perl-test-most)))
1023 (home-page "https://metacpan.org/release/BioPerl")
1024 (synopsis "Bioinformatics toolkit")
1026 "BioPerl is the product of a community effort to produce Perl code which
1027 is useful in biology. Examples include Sequence objects, Alignment objects
1028 and database searching objects. These objects not only do what they are
1029 advertised to do in the documentation, but they also interact - Alignment
1030 objects are made from the Sequence objects, Sequence objects have access to
1031 Annotation and SeqFeature objects and databases, Blast objects can be
1032 converted to Alignment objects, and so on. This means that the objects
1033 provide a coordinated and extensible framework to do computational biology.")
1034 (license license:perl-license))))
1036 (define-public python-biopython
1038 (name "python-biopython")
1042 ;; use PyPi rather than biopython.org to ease updating
1043 (uri (pypi-uri "biopython" version))
1046 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1047 (build-system python-build-system)
1050 (modify-phases %standard-phases
1051 (add-before 'check 'set-home
1052 ;; Some tests require a home directory to be set.
1053 (lambda _ (setenv "HOME" "/tmp") #t)))))
1055 `(("python-numpy" ,python-numpy)))
1056 (home-page "http://biopython.org/")
1057 (synopsis "Tools for biological computation in Python")
1059 "Biopython is a set of tools for biological computation including parsers
1060 for bioinformatics files into Python data structures; interfaces to common
1061 bioinformatics programs; a standard sequence class and tools for performing
1062 common operations on them; code to perform data classification; code for
1063 dealing with alignments; code making it easy to split up parallelizable tasks
1064 into separate processes; and more.")
1065 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1067 (define-public python2-biopython
1068 (package-with-python2 python-biopython))
1070 (define-public python-fastalite
1072 (name "python-fastalite")
1077 (uri (pypi-uri "fastalite" version))
1080 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1081 (build-system python-build-system)
1083 `(#:tests? #f)) ; Test data is not distributed.
1084 (home-page "https://github.com/nhoffman/fastalite")
1085 (synopsis "Simplest possible FASTA parser")
1086 (description "This library implements a FASTA and a FASTQ parser without
1087 relying on a complex dependency tree.")
1088 (license license:expat)))
1090 (define-public python2-fastalite
1091 (package-with-python2 python-fastalite))
1093 (define-public bpp-core
1094 ;; The last release was in 2014 and the recommended way to install from source
1095 ;; is to clone the git repository, so we do this.
1096 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1097 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1100 (version (string-append "2.2.0-1." (string-take commit 7)))
1104 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1106 (file-name (string-append name "-" version "-checkout"))
1109 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1110 (build-system cmake-build-system)
1112 `(#:parallel-build? #f))
1114 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
1115 ; compile all of the bpp packages with GCC 5.
1116 (home-page "http://biopp.univ-montp2.fr")
1117 (synopsis "C++ libraries for Bioinformatics")
1119 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1120 analysis, phylogenetics, molecular evolution and population genetics. It is
1121 Object Oriented and is designed to be both easy to use and computer efficient.
1122 Bio++ intends to help programmers to write computer expensive programs, by
1123 providing them a set of re-usable tools.")
1124 (license license:cecill-c))))
1126 (define-public bpp-phyl
1127 ;; The last release was in 2014 and the recommended way to install from source
1128 ;; is to clone the git repository, so we do this.
1129 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1130 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1133 (version (string-append "2.2.0-1." (string-take commit 7)))
1137 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1139 (file-name (string-append name "-" version "-checkout"))
1142 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1143 (build-system cmake-build-system)
1145 `(#:parallel-build? #f
1146 ;; If out-of-source, test data is not copied into the build directory
1147 ;; so the tests fail.
1148 #:out-of-source? #f))
1150 `(("bpp-core" ,bpp-core)
1151 ("bpp-seq" ,bpp-seq)
1152 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
1155 (home-page "http://biopp.univ-montp2.fr")
1156 (synopsis "Bio++ phylogenetic Library")
1158 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1159 analysis, phylogenetics, molecular evolution and population genetics. This
1160 library provides phylogenetics-related modules.")
1161 (license license:cecill-c))))
1163 (define-public bpp-popgen
1164 ;; The last release was in 2014 and the recommended way to install from source
1165 ;; is to clone the git repository, so we do this.
1166 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1167 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1170 (version (string-append "2.2.0-1." (string-take commit 7)))
1174 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1176 (file-name (string-append name "-" version "-checkout"))
1179 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1180 (build-system cmake-build-system)
1182 `(#:parallel-build? #f
1183 #:tests? #f)) ; There are no tests.
1185 `(("bpp-core" ,bpp-core)
1186 ("bpp-seq" ,bpp-seq)
1188 (home-page "http://biopp.univ-montp2.fr")
1189 (synopsis "Bio++ population genetics library")
1191 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1192 analysis, phylogenetics, molecular evolution and population genetics. This
1193 library provides population genetics-related modules.")
1194 (license license:cecill-c))))
1196 (define-public bpp-seq
1197 ;; The last release was in 2014 and the recommended way to install from source
1198 ;; is to clone the git repository, so we do this.
1199 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1200 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1203 (version (string-append "2.2.0-1." (string-take commit 7)))
1207 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1209 (file-name (string-append name "-" version "-checkout"))
1212 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1213 (build-system cmake-build-system)
1215 `(#:parallel-build? #f
1216 ;; If out-of-source, test data is not copied into the build directory
1217 ;; so the tests fail.
1218 #:out-of-source? #f))
1220 `(("bpp-core" ,bpp-core)
1221 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1222 (home-page "http://biopp.univ-montp2.fr")
1223 (synopsis "Bio++ sequence library")
1225 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1226 analysis, phylogenetics, molecular evolution and population genetics. This
1227 library provides sequence-related modules.")
1228 (license license:cecill-c))))
1230 (define-public bppsuite
1231 ;; The last release was in 2014 and the recommended way to install from source
1232 ;; is to clone the git repository, so we do this.
1233 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1234 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1237 (version (string-append "2.2.0-1." (string-take commit 7)))
1241 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1243 (file-name (string-append name "-" version "-checkout"))
1246 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1247 (build-system cmake-build-system)
1249 `(#:parallel-build? #f
1250 #:tests? #f)) ; There are no tests.
1254 ("texinfo" ,texinfo)))
1256 `(("bpp-core" ,bpp-core)
1257 ("bpp-seq" ,bpp-seq)
1258 ("bpp-phyl" ,bpp-phyl)
1259 ("bpp-phyl" ,bpp-popgen)
1261 (home-page "http://biopp.univ-montp2.fr")
1262 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1264 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1265 analysis, phylogenetics, molecular evolution and population genetics. This
1266 package provides command line tools using the Bio++ library.")
1267 (license license:cecill-c))))
1269 (define-public blast+
1276 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1277 version "/ncbi-blast-" version "+-src.tar.gz"))
1280 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1281 (modules '((guix build utils)))
1284 ;; Remove bundled bzip2, zlib and pcre.
1285 (delete-file-recursively "c++/src/util/compress/bzip2")
1286 (delete-file-recursively "c++/src/util/compress/zlib")
1287 (delete-file-recursively "c++/src/util/regexp")
1288 (substitute* "c++/src/util/compress/Makefile.in"
1289 (("bzip2 zlib api") "api"))
1290 ;; Remove useless msbuild directory
1291 (delete-file-recursively
1292 "c++/src/build-system/project_tree_builder/msbuild")
1294 (build-system gnu-build-system)
1296 `(;; There are two(!) tests for this massive library, and both fail with
1297 ;; "unparsable timing stats".
1298 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1299 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1302 #:parallel-build? #f ; not supported
1304 (modify-phases %standard-phases
1305 (add-before 'configure 'set-HOME
1306 ;; $HOME needs to be set at some point during the configure phase
1307 (lambda _ (setenv "HOME" "/tmp") #t))
1308 (add-after 'unpack 'enter-dir
1309 (lambda _ (chdir "c++") #t))
1310 (add-after 'enter-dir 'fix-build-system
1312 (define (which* cmd)
1313 (cond ((string=? cmd "date")
1314 ;; make call to "date" deterministic
1319 (format (current-error-port)
1320 "WARNING: Unable to find absolute path for ~s~%"
1324 ;; Rewrite hardcoded paths to various tools
1325 (substitute* (append '("src/build-system/configure.ac"
1326 "src/build-system/configure"
1327 "src/build-system/helpers/run_with_lock.c"
1328 "scripts/common/impl/if_diff.sh"
1329 "scripts/common/impl/run_with_lock.sh"
1330 "src/build-system/Makefile.configurables.real"
1331 "src/build-system/Makefile.in.top"
1332 "src/build-system/Makefile.meta.gmake=no"
1333 "src/build-system/Makefile.meta.in"
1334 "src/build-system/Makefile.meta_l"
1335 "src/build-system/Makefile.meta_p"
1336 "src/build-system/Makefile.meta_r"
1337 "src/build-system/Makefile.mk.in"
1338 "src/build-system/Makefile.requirements"
1339 "src/build-system/Makefile.rules_with_autodep.in")
1340 (find-files "scripts/common/check" "\\.sh$"))
1341 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1342 (or (which* cmd) all)))
1344 (substitute* (find-files "src/build-system" "^config.*")
1345 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1348 ;; rewrite "/var/tmp" in check script
1349 (substitute* "scripts/common/check/check_make_unix.sh"
1350 (("/var/tmp") "/tmp"))
1352 ;; do not reset PATH
1353 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1355 (("action=/bin/") "action=")
1356 (("export PATH") ":"))
1359 (lambda* (#:key inputs outputs #:allow-other-keys)
1360 (let ((out (assoc-ref outputs "out"))
1361 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1362 (include (string-append (assoc-ref outputs "include")
1363 "/include/ncbi-tools++")))
1364 ;; The 'configure' script doesn't recognize things like
1365 ;; '--enable-fast-install'.
1366 (invoke "./configure.orig"
1367 (string-append "--with-build-root=" (getcwd) "/build")
1368 (string-append "--prefix=" out)
1369 (string-append "--libdir=" lib)
1370 (string-append "--includedir=" include)
1371 (string-append "--with-bz2="
1372 (assoc-ref inputs "bzip2"))
1373 (string-append "--with-z="
1374 (assoc-ref inputs "zlib"))
1375 (string-append "--with-pcre="
1376 (assoc-ref inputs "pcre"))
1377 ;; Each library is built twice by default, once
1378 ;; with "-static" in its name, and again
1383 (outputs '("out" ; 21 MB
1392 ("python" ,python-wrapper)))
1395 (home-page "http://blast.ncbi.nlm.nih.gov")
1396 (synopsis "Basic local alignment search tool")
1398 "BLAST is a popular method of performing a DNA or protein sequence
1399 similarity search, using heuristics to produce results quickly. It also
1400 calculates an “expect value” that estimates how many matches would have
1401 occurred at a given score by chance, which can aid a user in judging how much
1402 confidence to have in an alignment.")
1403 ;; Most of the sources are in the public domain, with the following
1406 ;; * ./c++/include/util/bitset/
1407 ;; * ./c++/src/html/ncbi_menu*.js
1409 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1411 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1413 ;; * ./c++/src/corelib/teamcity_*
1414 (license (list license:public-domain
1420 (define-public bless
1426 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1430 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1431 (modules '((guix build utils)))
1434 ;; Remove bundled boost, pigz, zlib, and .git directory
1435 ;; FIXME: also remove bundled sources for murmurhash3 and
1436 ;; kmc once packaged.
1437 (delete-file-recursively "boost")
1438 (delete-file-recursively "pigz")
1439 (delete-file-recursively "google-sparsehash")
1440 (delete-file-recursively "zlib")
1441 (delete-file-recursively ".git")
1443 (build-system gnu-build-system)
1445 '(#:tests? #f ;no "check" target
1447 (list (string-append "ZLIB="
1448 (assoc-ref %build-inputs "zlib:static")
1450 (string-append "LDFLAGS="
1451 (string-join '("-lboost_filesystem"
1458 (modify-phases %standard-phases
1459 (add-after 'unpack 'do-not-build-bundled-pigz
1460 (lambda* (#:key inputs outputs #:allow-other-keys)
1461 (substitute* "Makefile"
1462 (("cd pigz/pigz-2.3.3; make") ""))
1464 (add-after 'unpack 'patch-paths-to-executables
1465 (lambda* (#:key inputs outputs #:allow-other-keys)
1466 (substitute* "parse_args.cpp"
1467 (("kmc_binary = .*")
1468 (string-append "kmc_binary = \""
1469 (assoc-ref outputs "out")
1471 (("pigz_binary = .*")
1472 (string-append "pigz_binary = \""
1473 (assoc-ref inputs "pigz")
1477 (lambda* (#:key outputs #:allow-other-keys)
1478 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1479 (for-each (lambda (file)
1480 (install-file file bin))
1481 '("bless" "kmc/bin/kmc"))
1483 (delete 'configure))))
1487 `(("openmpi" ,openmpi)
1489 ("sparsehash" ,sparsehash)
1491 ("zlib:static" ,zlib "static")
1493 (supported-systems '("x86_64-linux"))
1494 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1495 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1497 "@dfn{Bloom-filter-based error correction solution for high-throughput
1498 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1499 correction tool for genomic reads produced by @dfn{Next-generation
1500 sequencing} (NGS). BLESS produces accurate correction results with much less
1501 memory compared with previous solutions and is also able to tolerate a higher
1502 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1503 errors at the end of reads.")
1504 (license license:gpl3+)))
1506 (define-public bowtie
1513 (url "https://github.com/BenLangmead/bowtie2.git")
1514 (commit (string-append "v" version))))
1515 (file-name (git-file-name name version))
1518 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1519 (modules '((guix build utils)))
1522 (substitute* "Makefile"
1523 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1524 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1525 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1527 (build-system gnu-build-system)
1532 (string-append "prefix=" (assoc-ref %outputs "out")))
1534 (modify-phases %standard-phases
1539 "scripts/test/simple_tests.pl"
1540 "--bowtie2=./bowtie2"
1541 "--bowtie2-build=./bowtie2-build")
1546 ("python" ,python-wrapper)))
1549 ("perl-clone" ,perl-clone)
1550 ("perl-test-deep" ,perl-test-deep)
1551 ("perl-test-simple" ,perl-test-simple)))
1552 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1553 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1555 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1556 reads to long reference sequences. It is particularly good at aligning reads
1557 of about 50 up to 100s or 1,000s of characters, and particularly good at
1558 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1559 genome with an FM Index to keep its memory footprint small: for the human
1560 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1561 gapped, local, and paired-end alignment modes.")
1562 (supported-systems '("x86_64-linux"))
1563 (license license:gpl3+)))
1565 (define-public bowtie1
1571 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1572 version "/bowtie-" version "-src.zip"))
1575 "1jl2cj9bz8lwz8dwnxbycn8yp8g4kky62fkcxifyf1ri0y6n2vc0"))
1576 (modules '((guix build utils)))
1578 '(substitute* "Makefile"
1579 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1580 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1581 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1582 (build-system gnu-build-system)
1584 '(#:tests? #f ; no "check" target
1587 (string-append "prefix=" (assoc-ref %outputs "out")))
1589 (modify-phases %standard-phases
1590 (delete 'configure))))
1594 (supported-systems '("x86_64-linux"))
1595 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1596 (synopsis "Fast aligner for short nucleotide sequence reads")
1598 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1599 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1600 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1601 keep its memory footprint small: typically about 2.2 GB for the human
1602 genome (2.9 GB for paired-end).")
1603 (license license:artistic2.0)))
1605 (define-public tophat
1612 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1616 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1617 (modules '((guix build utils)))
1620 ;; Remove bundled SeqAn and samtools
1621 (delete-file-recursively "src/SeqAn-1.4.2")
1622 (delete-file-recursively "src/samtools-0.1.18")
1624 (build-system gnu-build-system)
1626 '(#:parallel-build? #f ; not supported
1628 (modify-phases %standard-phases
1629 (add-after 'unpack 'use-system-samtools
1630 (lambda* (#:key inputs #:allow-other-keys)
1631 (substitute* "src/Makefile.in"
1632 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1633 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1634 (("SAMPROG = samtools_0\\.1\\.18") "")
1635 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1636 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1637 (substitute* '("src/common.cpp"
1639 (("samtools_0.1.18") (which "samtools")))
1640 (substitute* '("src/common.h"
1641 "src/bam2fastx.cpp")
1642 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1643 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1644 (substitute* '("src/bwt_map.h"
1646 "src/align_status.h")
1647 (("#include <bam.h>") "#include <samtools/bam.h>")
1648 (("#include <sam.h>") "#include <samtools/sam.h>"))
1653 ("samtools" ,samtools-0.1)
1654 ("ncurses" ,ncurses)
1655 ("python" ,python-2)
1658 ("seqan" ,seqan-1)))
1659 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1660 (synopsis "Spliced read mapper for RNA-Seq data")
1662 "TopHat is a fast splice junction mapper for nucleotide sequence
1663 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1664 mammalian-sized genomes using the ultra high-throughput short read
1665 aligner Bowtie, and then analyzes the mapping results to identify
1666 splice junctions between exons.")
1667 ;; TopHat is released under the Boost Software License, Version 1.0
1668 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1669 (license license:boost1.0)))
1678 "https://github.com/lh3/bwa/releases/download/v"
1679 version "/bwa-" version ".tar.bz2"))
1682 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1683 (build-system gnu-build-system)
1685 '(#:tests? #f ;no "check" target
1687 (modify-phases %standard-phases
1689 (lambda* (#:key outputs #:allow-other-keys)
1690 (let ((bin (string-append
1691 (assoc-ref outputs "out") "/bin"))
1693 (assoc-ref outputs "out") "/share/doc/bwa"))
1695 (assoc-ref outputs "out") "/share/man/man1")))
1696 (install-file "bwa" bin)
1697 (install-file "README.md" doc)
1698 (install-file "bwa.1" man))
1700 ;; no "configure" script
1701 (delete 'configure))))
1702 (inputs `(("zlib" ,zlib)))
1703 ;; Non-portable SSE instructions are used so building fails on platforms
1704 ;; other than x86_64.
1705 (supported-systems '("x86_64-linux"))
1706 (home-page "http://bio-bwa.sourceforge.net/")
1707 (synopsis "Burrows-Wheeler sequence aligner")
1709 "BWA is a software package for mapping low-divergent sequences against a
1710 large reference genome, such as the human genome. It consists of three
1711 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1712 designed for Illumina sequence reads up to 100bp, while the rest two for
1713 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1714 features such as long-read support and split alignment, but BWA-MEM, which is
1715 the latest, is generally recommended for high-quality queries as it is faster
1716 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1717 70-100bp Illumina reads.")
1718 (license license:gpl3+)))
1720 (define-public bwa-pssm
1721 (package (inherit bwa)
1727 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1729 (file-name (git-file-name name version))
1732 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1733 (build-system gnu-build-system)
1738 (home-page "http://bwa-pssm.binf.ku.dk/")
1739 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1741 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1742 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1743 existing aligners it is fast and sensitive. Unlike most other aligners,
1744 however, it is also adaptible in the sense that one can direct the alignment
1745 based on known biases within the data set. It is coded as a modification of
1746 the original BWA alignment program and shares the genome index structure as
1747 well as many of the command line options.")
1748 (license license:gpl3+)))
1750 (define-public bwa-meth
1757 (url "https://github.com/brentp/bwa-meth.git")
1758 (commit (string-append "v" version))))
1759 (file-name (git-file-name name version))
1762 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1763 (build-system python-build-system)
1766 (modify-phases %standard-phases
1767 (add-after 'unpack 'keep-references-to-bwa
1768 (lambda* (#:key inputs #:allow-other-keys)
1769 (substitute* "bwameth.py"
1771 (string-append (which "bwa") " mem"))
1772 ;; There's an ill-advised check for "samtools" on PATH.
1778 `(("python-toolshed" ,python-toolshed)))
1779 (home-page "https://github.com/brentp/bwa-meth")
1780 (synopsis "Fast and accurante alignment of BS-Seq reads")
1782 "BWA-Meth works for single-end reads and for paired-end reads from the
1783 directional protocol (most common). It uses the method employed by
1784 methylcoder and Bismark of in silico conversion of all C's to T's in both
1785 reference and reads. It recovers the original read (needed to tabulate
1786 methylation) by attaching it as a comment which BWA appends as a tag to the
1787 read. It performs favorably to existing aligners gauged by number of on and
1788 off-target reads for a capture method that targets CpG-rich region.")
1789 (license license:expat)))
1791 (define-public python-bx-python
1793 (name "python-bx-python")
1797 (uri (pypi-uri "bx-python" version))
1800 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1801 (build-system python-build-system)
1802 ;; Tests fail because test data are not included
1803 (arguments '(#:tests? #f))
1805 `(("python-numpy" ,python-numpy)
1806 ("python-six" ,python-six)))
1810 `(("python-lzo" ,python-lzo)
1811 ("python-nose" ,python-nose)
1812 ("python-cython" ,python-cython)))
1813 (home-page "https://github.com/bxlab/bx-python")
1814 (synopsis "Tools for manipulating biological data")
1816 "bx-python provides tools for manipulating biological data, particularly
1817 multiple sequence alignments.")
1818 (license license:expat)))
1820 (define-public python2-bx-python
1821 (package-with-python2 python-bx-python))
1823 (define-public python-pysam
1825 (name "python-pysam")
1829 ;; Test data is missing on PyPi.
1831 (url "https://github.com/pysam-developers/pysam.git")
1832 (commit (string-append "v" version))))
1833 (file-name (git-file-name name version))
1836 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1837 (modules '((guix build utils)))
1839 ;; Drop bundled htslib. TODO: Also remove samtools
1841 (delete-file-recursively "htslib")
1843 (build-system python-build-system)
1845 `(#:modules ((ice-9 ftw)
1847 (guix build python-build-system)
1850 (modify-phases %standard-phases
1851 (add-before 'build 'set-flags
1852 (lambda* (#:key inputs #:allow-other-keys)
1853 (setenv "HTSLIB_MODE" "external")
1854 (setenv "HTSLIB_LIBRARY_DIR"
1855 (string-append (assoc-ref inputs "htslib") "/lib"))
1856 (setenv "HTSLIB_INCLUDE_DIR"
1857 (string-append (assoc-ref inputs "htslib") "/include"))
1858 (setenv "LDFLAGS" "-lncurses")
1859 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1862 (lambda* (#:key inputs outputs #:allow-other-keys)
1863 ;; This file contains tests that require a connection to the
1865 (delete-file "tests/tabix_test.py")
1866 ;; FIXME: This test fails
1867 (delete-file "tests/AlignmentFile_test.py")
1868 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1869 (setenv "PYTHONPATH"
1871 (getenv "PYTHONPATH")
1872 ":" (getcwd) "/build/"
1873 (car (scandir "build"
1874 (negate (cut string-prefix? "." <>))))))
1875 ;; Step out of source dir so python does not import from CWD.
1876 (with-directory-excursion "tests"
1877 (setenv "HOME" "/tmp")
1878 (invoke "make" "-C" "pysam_data")
1879 (invoke "make" "-C" "cbcf_data")
1880 ;; Running nosetests without explicitly asking for a single
1881 ;; process leads to a crash. Running with multiple processes
1882 ;; fails because the tests are not designed to run in parallel.
1884 ;; FIXME: tests keep timing out on some systems.
1885 (invoke "nosetests" "-v" "--processes" "1")))))))
1887 `(("htslib" ,htslib))) ; Included from installed header files.
1889 `(("ncurses" ,ncurses)
1893 `(("python-cython" ,python-cython)
1894 ;; Dependencies below are are for tests only.
1895 ("samtools" ,samtools)
1896 ("bcftools" ,bcftools)
1897 ("python-nose" ,python-nose)))
1898 (home-page "https://github.com/pysam-developers/pysam")
1899 (synopsis "Python bindings to the SAMtools C API")
1901 "Pysam is a Python module for reading and manipulating files in the
1902 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1903 also includes an interface for tabix.")
1904 (license license:expat)))
1906 (define-public python2-pysam
1907 (package-with-python2 python-pysam))
1909 (define-public python-twobitreader
1911 (name "python-twobitreader")
1916 (url "https://github.com/benjschiller/twobitreader")
1918 (file-name (git-file-name name version))
1921 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1922 (build-system python-build-system)
1923 ;; Tests are not included
1924 (arguments '(#:tests? #f))
1926 `(("python-sphinx" ,python-sphinx)))
1927 (home-page "https://github.com/benjschiller/twobitreader")
1928 (synopsis "Python library for reading .2bit files")
1930 "twobitreader is a Python library for reading .2bit files as used by the
1931 UCSC genome browser.")
1932 (license license:artistic2.0)))
1934 (define-public python2-twobitreader
1935 (package-with-python2 python-twobitreader))
1937 (define-public python-plastid
1939 (name "python-plastid")
1943 (uri (pypi-uri "plastid" version))
1946 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1947 (build-system python-build-system)
1949 ;; Some test files are not included.
1952 `(("python-numpy" ,python-numpy)
1953 ("python-scipy" ,python-scipy)
1954 ("python-pandas" ,python-pandas)
1955 ("python-pysam" ,python-pysam)
1956 ("python-matplotlib" ,python-matplotlib)
1957 ("python-biopython" ,python-biopython)
1958 ("python-twobitreader" ,python-twobitreader)
1959 ("python-termcolor" ,python-termcolor)))
1961 `(("python-cython" ,python-cython)
1962 ("python-nose" ,python-nose)))
1963 (home-page "https://github.com/joshuagryphon/plastid")
1964 (synopsis "Python library for genomic analysis")
1966 "plastid is a Python library for genomic analysis – in particular,
1967 high-throughput sequencing data – with an emphasis on simplicity.")
1968 (license license:bsd-3)))
1970 (define-public python2-plastid
1971 (package-with-python2 python-plastid))
1973 (define-public tetoolkit
1980 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1982 (file-name (git-file-name name version))
1985 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1986 (build-system python-build-system)
1988 `(#:python ,python-2 ; not guaranteed to work with Python 3
1990 (modify-phases %standard-phases
1991 (add-after 'unpack 'make-writable
1993 (for-each make-file-writable (find-files "."))
1995 (add-after 'unpack 'patch-invocations
1996 (lambda* (#:key inputs #:allow-other-keys)
1997 (substitute* '("bin/TEtranscripts"
2000 (string-append "'" (which "sort") " "))
2002 (string-append "'" (which "rm") " -f "))
2003 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2004 (substitute* "TEToolkit/IO/ReadInputs.py"
2005 (("BamToBED") (which "bamToBed")))
2006 (substitute* "TEToolkit/Normalization.py"
2008 (string-append "\"" (which "Rscript") "\"")))
2010 (add-after 'install 'wrap-program
2011 (lambda* (#:key outputs #:allow-other-keys)
2012 ;; Make sure the executables find R packages.
2013 (let ((out (assoc-ref outputs "out")))
2016 (wrap-program (string-append out "/bin/" script)
2017 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2022 `(("coreutils" ,coreutils)
2023 ("bedtools" ,bedtools)
2024 ("python-argparse" ,python2-argparse)
2025 ("python-pysam" ,python2-pysam)
2026 ("r-minimal" ,r-minimal)
2027 ("r-deseq2" ,r-deseq2)))
2028 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2029 (synopsis "Transposable elements in differential enrichment analysis")
2031 "This is package for including transposable elements in differential
2032 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2033 RNA-seq (and similar data) and annotates reads to both genes and transposable
2034 elements. TEtranscripts then performs differential analysis using DESeq2.
2035 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2036 are not included due to their size.")
2037 (license license:gpl3+)))
2039 (define-public cd-hit
2045 (uri (string-append "https://github.com/weizhongli/cdhit"
2046 "/releases/download/V" version
2048 "-2017-0621-source.tar.gz"))
2051 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2052 (build-system gnu-build-system)
2054 `(#:tests? #f ; there are no tests
2056 ;; Executables are copied directly to the PREFIX.
2057 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2058 ;; Support longer sequences (e.g. Pacbio sequences)
2061 (modify-phases %standard-phases
2062 ;; No "configure" script
2064 ;; Remove sources of non-determinism
2065 (add-after 'unpack 'be-timeless
2067 (substitute* "cdhit-utility.c++"
2068 ((" \\(built on \" __DATE__ \"\\)") ""))
2069 (substitute* "cdhit-common.c++"
2070 (("__DATE__") "\"0\"")
2071 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2073 ;; The "install" target does not create the target directory.
2074 (add-before 'install 'create-target-dir
2075 (lambda* (#:key outputs #:allow-other-keys)
2076 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2080 (home-page "http://weizhongli-lab.org/cd-hit/")
2081 (synopsis "Cluster and compare protein or nucleotide sequences")
2083 "CD-HIT is a program for clustering and comparing protein or nucleotide
2084 sequences. CD-HIT is designed to be fast and handle extremely large
2086 ;; The manual says: "It can be copied under the GNU General Public License
2087 ;; version 2 (GPLv2)."
2088 (license license:gpl2)))
2090 (define-public clipper
2097 (url "https://github.com/YeoLab/clipper.git")
2099 (file-name (git-file-name name version))
2102 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2103 (modules '((guix build utils)))
2106 ;; remove unnecessary setup dependency
2107 (substitute* "setup.py"
2108 (("setup_requires = .*") ""))
2110 (build-system python-build-system)
2112 `(#:python ,python-2 ; only Python 2 is supported
2114 (modify-phases %standard-phases
2115 ;; This is fixed in upstream commit
2116 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2117 (add-after 'unpack 'fix-typo
2119 (substitute* "clipper/src/readsToWiggle.pyx"
2123 `(("htseq" ,python2-htseq)
2124 ("python-pybedtools" ,python2-pybedtools)
2125 ("python-cython" ,python2-cython)
2126 ("python-scikit-learn" ,python2-scikit-learn)
2127 ("python-matplotlib" ,python2-matplotlib)
2128 ("python-pandas" ,python2-pandas)
2129 ("python-pysam" ,python2-pysam)
2130 ("python-numpy" ,python2-numpy)
2131 ("python-scipy" ,python2-scipy)))
2133 `(("python-mock" ,python2-mock) ; for tests
2134 ("python-nose" ,python2-nose) ; for tests
2135 ("python-pytz" ,python2-pytz))) ; for tests
2136 (home-page "https://github.com/YeoLab/clipper")
2137 (synopsis "CLIP peak enrichment recognition")
2139 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2140 (license license:gpl2)))
2142 (define-public codingquarry
2144 (name "codingquarry")
2149 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2153 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2154 (build-system gnu-build-system)
2156 '(#:tests? #f ; no "check" target
2158 (modify-phases %standard-phases
2161 (lambda* (#:key outputs #:allow-other-keys)
2162 (let* ((out (assoc-ref outputs "out"))
2163 (bin (string-append out "/bin"))
2164 (doc (string-append out "/share/doc/codingquarry")))
2165 (install-file "INSTRUCTIONS.pdf" doc)
2166 (copy-recursively "QuarryFiles"
2167 (string-append out "/QuarryFiles"))
2168 (install-file "CodingQuarry" bin)
2169 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2171 (inputs `(("openmpi" ,openmpi)))
2172 (native-search-paths
2173 (list (search-path-specification
2174 (variable "QUARRY_PATH")
2175 (files '("QuarryFiles")))))
2176 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2177 (synopsis "Fungal gene predictor")
2178 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2179 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2180 (home-page "https://sourceforge.net/projects/codingquarry/")
2181 (license license:gpl3+)))
2183 (define-public couger
2190 "http://couger.oit.duke.edu/static/assets/COUGER"
2194 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2195 (build-system gnu-build-system)
2199 (modify-phases %standard-phases
2204 (lambda* (#:key outputs #:allow-other-keys)
2205 (let* ((out (assoc-ref outputs "out"))
2206 (bin (string-append out "/bin")))
2207 (copy-recursively "src" (string-append out "/src"))
2209 ;; Add "src" directory to module lookup path.
2210 (substitute* "couger"
2212 (string-append "import sys\nsys.path.append(\""
2213 out "\")\nfrom argparse")))
2214 (install-file "couger" bin))
2217 'install 'wrap-program
2218 (lambda* (#:key inputs outputs #:allow-other-keys)
2219 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2220 (let* ((out (assoc-ref outputs "out"))
2221 (path (getenv "PYTHONPATH")))
2222 (wrap-program (string-append out "/bin/couger")
2223 `("PYTHONPATH" ":" prefix (,path))))
2226 `(("python" ,python-2)
2227 ("python2-pillow" ,python2-pillow)
2228 ("python2-numpy" ,python2-numpy)
2229 ("python2-scipy" ,python2-scipy)
2230 ("python2-matplotlib" ,python2-matplotlib)))
2232 `(("r-minimal" ,r-minimal)
2234 ("randomjungle" ,randomjungle)))
2236 `(("unzip" ,unzip)))
2237 (home-page "http://couger.oit.duke.edu")
2238 (synopsis "Identify co-factors in sets of genomic regions")
2240 "COUGER can be applied to any two sets of genomic regions bound by
2241 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2242 putative co-factors that provide specificity to each TF. The framework
2243 determines the genomic targets uniquely-bound by each TF, and identifies a
2244 small set of co-factors that best explain the in vivo binding differences
2245 between the two TFs.
2247 COUGER uses classification algorithms (support vector machines and random
2248 forests) with features that reflect the DNA binding specificities of putative
2249 co-factors. The features are generated either from high-throughput TF-DNA
2250 binding data (from protein binding microarray experiments), or from large
2251 collections of DNA motifs.")
2252 (license license:gpl3+)))
2254 (define-public clustal-omega
2256 (name "clustal-omega")
2260 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2264 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2265 (build-system gnu-build-system)
2267 `(("argtable" ,argtable)))
2268 (home-page "http://www.clustal.org/omega/")
2269 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2271 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2272 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2273 of handling data-sets of hundreds of thousands of sequences in reasonable
2275 (license license:gpl2+)))
2277 (define-public crossmap
2283 (uri (pypi-uri "CrossMap" version))
2286 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2287 (build-system python-build-system)
2288 (arguments `(#:python ,python-2))
2290 `(("python-bx-python" ,python2-bx-python)
2291 ("python-numpy" ,python2-numpy)
2292 ("python-pysam" ,python2-pysam)
2295 `(("python-cython" ,python2-cython)
2296 ("python-nose" ,python2-nose)))
2297 (home-page "http://crossmap.sourceforge.net/")
2298 (synopsis "Convert genome coordinates between assemblies")
2300 "CrossMap is a program for conversion of genome coordinates or annotation
2301 files between different genome assemblies. It supports most commonly used
2302 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2303 (license license:gpl2+)))
2305 (define-public python-dnaio
2307 (name "python-dnaio")
2312 (uri (pypi-uri "dnaio" version))
2315 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2316 (build-system python-build-system)
2318 `(("python-cython" ,python-cython)
2319 ("python-pytest" ,python-pytest)
2320 ("python-xopen" ,python-xopen)))
2321 (home-page "https://github.com/marcelm/dnaio/")
2322 (synopsis "Read FASTA and FASTQ files efficiently")
2324 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2325 files. The code was previously part of the cutadapt tool.")
2326 (license license:expat)))
2328 (define-public cutadapt
2334 (uri (pypi-uri "cutadapt" version))
2337 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2338 (build-system python-build-system)
2340 `(("python-dnaio" ,python-dnaio)
2341 ("python-xopen" ,python-xopen)))
2343 `(("python-cython" ,python-cython)
2344 ("python-pytest" ,python-pytest)
2345 ("python-setuptools-scm" ,python-setuptools-scm)))
2346 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2347 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2349 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2350 other types of unwanted sequence from high-throughput sequencing reads.")
2351 (license license:expat)))
2353 (define-public libbigwig
2360 (url "https://github.com/dpryan79/libBigWig.git")
2362 (file-name (string-append name "-" version "-checkout"))
2365 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2366 (build-system gnu-build-system)
2368 `(#:test-target "test"
2369 #:tests? #f ; tests require access to the web
2372 (string-append "prefix=" (assoc-ref %outputs "out")))
2374 (modify-phases %standard-phases
2375 (delete 'configure))))
2380 `(("doxygen" ,doxygen)
2382 ("python" ,python-2)))
2383 (home-page "https://github.com/dpryan79/libBigWig")
2384 (synopsis "C library for handling bigWig files")
2386 "This package provides a C library for parsing local and remote BigWig
2388 (license license:expat)))
2390 (define-public python-pybigwig
2392 (name "python-pybigwig")
2396 (uri (pypi-uri "pyBigWig" version))
2399 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2400 (modules '((guix build utils)))
2403 ;; Delete bundled libBigWig sources
2404 (delete-file-recursively "libBigWig")
2406 (build-system python-build-system)
2409 (modify-phases %standard-phases
2410 (add-after 'unpack 'link-with-libBigWig
2411 (lambda* (#:key inputs #:allow-other-keys)
2412 (substitute* "setup.py"
2413 (("libs=\\[") "libs=[\"BigWig\", "))
2416 `(("python-numpy" ,python-numpy)))
2418 `(("libbigwig" ,libbigwig)
2421 (home-page "https://github.com/dpryan79/pyBigWig")
2422 (synopsis "Access bigWig files in Python using libBigWig")
2424 "This package provides Python bindings to the libBigWig library for
2425 accessing bigWig files.")
2426 (license license:expat)))
2428 (define-public python2-pybigwig
2429 (package-with-python2 python-pybigwig))
2431 (define-public python-dendropy
2433 (name "python-dendropy")
2438 ;; Source from GitHub so that tests are included.
2440 (url "https://github.com/jeetsukumaran/DendroPy.git")
2441 (commit (string-append "v" version))))
2442 (file-name (git-file-name name version))
2445 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2446 (build-system python-build-system)
2447 (home-page "http://packages.python.org/DendroPy/")
2448 (synopsis "Library for phylogenetics and phylogenetic computing")
2450 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2451 writing, simulation, processing and manipulation of phylogenetic
2452 trees (phylogenies) and characters.")
2453 (license license:bsd-3)))
2455 (define-public python2-dendropy
2456 (let ((base (package-with-python2 python-dendropy)))
2461 (modify-phases %standard-phases
2462 (add-after 'unpack 'remove-failing-test
2464 ;; This test fails when the full test suite is run, as documented
2465 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2466 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2467 (("test_collection_comments_and_annotations")
2468 "do_not_test_collection_comments_and_annotations"))
2470 ,@(package-arguments base))))))
2472 (define-public python-py2bit
2474 (name "python-py2bit")
2479 (uri (pypi-uri "py2bit" version))
2482 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2483 (build-system python-build-system)
2484 (home-page "https://github.com/dpryan79/py2bit")
2485 (synopsis "Access 2bit files using lib2bit")
2487 "This package provides Python bindings for lib2bit to access 2bit files
2489 (license license:expat)))
2491 (define-public deeptools
2498 (url "https://github.com/deeptools/deepTools.git")
2500 (file-name (git-file-name name version))
2503 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2504 (build-system python-build-system)
2507 (modify-phases %standard-phases
2508 ;; This phase fails, but it's not needed.
2509 (delete 'reset-gzip-timestamps))))
2511 `(("python-plotly" ,python-plotly)
2512 ("python-scipy" ,python-scipy)
2513 ("python-numpy" ,python-numpy)
2514 ("python-numpydoc" ,python-numpydoc)
2515 ("python-matplotlib" ,python-matplotlib)
2516 ("python-pysam" ,python-pysam)
2517 ("python-py2bit" ,python-py2bit)
2518 ("python-pybigwig" ,python-pybigwig)))
2520 `(("python-mock" ,python-mock) ;for tests
2521 ("python-nose" ,python-nose) ;for tests
2522 ("python-pytz" ,python-pytz))) ;for tests
2523 (home-page "https://github.com/deeptools/deepTools")
2524 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2526 "DeepTools addresses the challenge of handling the large amounts of data
2527 that are now routinely generated from DNA sequencing centers. To do so,
2528 deepTools contains useful modules to process the mapped reads data to create
2529 coverage files in standard bedGraph and bigWig file formats. By doing so,
2530 deepTools allows the creation of normalized coverage files or the comparison
2531 between two files (for example, treatment and control). Finally, using such
2532 normalized and standardized files, multiple visualizations can be created to
2533 identify enrichments with functional annotations of the genome.")
2534 (license license:gpl3+)))
2536 (define-public delly
2543 (url "https://github.com/dellytools/delly.git")
2544 (commit (string-append "v" version))))
2545 (file-name (git-file-name name version))
2547 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2548 (modules '((guix build utils)))
2551 (delete-file-recursively "src/htslib")
2553 (build-system gnu-build-system)
2555 `(#:tests? #f ; There are no tests to run.
2557 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2558 (string-append "prefix=" (assoc-ref %outputs "out")))
2560 (modify-phases %standard-phases
2561 (delete 'configure) ; There is no configure phase.
2562 (add-after 'install 'install-templates
2563 (lambda* (#:key outputs #:allow-other-keys)
2564 (let ((templates (string-append (assoc-ref outputs "out")
2565 "/share/delly/templates")))
2567 (copy-recursively "excludeTemplates" templates)
2574 (home-page "https://github.com/dellytools/delly")
2575 (synopsis "Integrated structural variant prediction method")
2576 (description "Delly is an integrated structural variant prediction method
2577 that can discover and genotype deletions, tandem duplications, inversions and
2578 translocations at single-nucleotide resolution in short-read massively parallel
2579 sequencing data. It uses paired-ends and split-reads to sensitively and
2580 accurately delineate genomic rearrangements throughout the genome.")
2581 (license license:gpl3+)))
2583 (define-public diamond
2590 (url "https://github.com/bbuchfink/diamond.git")
2591 (commit (string-append "v" version))))
2592 (file-name (git-file-name name version))
2595 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2596 (build-system cmake-build-system)
2598 '(#:tests? #f ; no "check" target
2600 (modify-phases %standard-phases
2601 (add-after 'unpack 'remove-native-compilation
2603 (substitute* "CMakeLists.txt" (("-march=native") ""))
2607 (home-page "https://github.com/bbuchfink/diamond")
2608 (synopsis "Accelerated BLAST compatible local sequence aligner")
2610 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2611 translated DNA query sequences against a protein reference database (BLASTP
2612 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2613 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2614 data and settings.")
2615 (license license:agpl3+)))
2617 (define-public discrover
2625 (url "https://github.com/maaskola/discrover.git")
2627 (file-name (git-file-name name version))
2630 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2631 (build-system cmake-build-system)
2633 `(#:tests? #f ; there are no tests
2635 (modify-phases %standard-phases
2636 (add-after 'unpack 'fix-latex-errors
2638 (with-fluids ((%default-port-encoding #f))
2639 (substitute* "doc/references.bib"
2640 (("\\{S\\}illanp[^,]+,")
2641 "{S}illanp{\\\"a}{\\\"a},")))
2642 ;; XXX: I just can't get pdflatex to not complain about these
2643 ;; characters. They end up in the manual via the generated
2644 ;; discrover-cli-help.txt.
2645 (substitute* "src/hmm/cli.cpp"
2649 ;; This seems to be a syntax error.
2650 (substitute* "doc/discrover-manual.tex"
2651 (("theverbbox\\[t\\]") "theverbbox"))
2653 (add-after 'unpack 'add-missing-includes
2655 (substitute* "src/executioninformation.hpp"
2656 (("#define EXECUTIONINFORMATION_HPP" line)
2657 (string-append line "\n#include <random>")))
2658 (substitute* "src/plasma/fasta.hpp"
2659 (("#define FASTA_HPP" line)
2660 (string-append line "\n#include <random>")))
2662 ;; FIXME: this is needed because we're using texlive-union, which
2663 ;; doesn't handle fonts correctly. It expects to be able to generate
2664 ;; fonts in the home directory.
2665 (add-before 'build 'setenv-HOME
2666 (lambda _ (setenv "HOME" "/tmp") #t)))))
2670 ("rmath-standalone" ,rmath-standalone)))
2672 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2673 texlive-fonts-amsfonts
2676 texlive-latex-examplep
2677 texlive-latex-hyperref
2679 texlive-latex-natbib
2680 texlive-bibtex ; style files used by natbib
2681 texlive-latex-pgf ; tikz
2682 texlive-latex-verbatimbox)))
2683 ("imagemagick" ,imagemagick)))
2684 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2685 (synopsis "Discover discriminative nucleotide sequence motifs")
2686 (description "Discrover is a motif discovery method to find binding sites
2687 of nucleic acid binding proteins.")
2688 (license license:gpl3+)))
2690 (define-public eigensoft
2698 (url "https://github.com/DReichLab/EIG.git")
2699 (commit (string-append "v" version))))
2700 (file-name (git-file-name name version))
2703 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2704 (modules '((guix build utils)))
2705 ;; Remove pre-built binaries.
2707 (delete-file-recursively "bin")
2710 (build-system gnu-build-system)
2712 `(#:tests? #f ; There are no tests.
2713 #:make-flags '("CC=gcc")
2715 (modify-phases %standard-phases
2716 ;; There is no configure phase, but the Makefile is in a
2719 (lambda _ (chdir "src") #t))
2720 ;; The provided install target only copies executables to
2721 ;; the "bin" directory in the build root.
2722 (add-after 'install 'actually-install
2723 (lambda* (#:key outputs #:allow-other-keys)
2724 (let* ((out (assoc-ref outputs "out"))
2725 (bin (string-append out "/bin")))
2726 (for-each (lambda (file)
2727 (install-file file bin))
2728 (find-files "../bin" ".*"))
2733 ("openblas" ,openblas)
2735 ("gfortran" ,gfortran "lib")))
2736 (home-page "https://github.com/DReichLab/EIG")
2737 (synopsis "Tools for population genetics")
2738 (description "The EIGENSOFT package provides tools for population
2739 genetics and stratification correction. EIGENSOFT implements methods commonly
2740 used in population genetics analyses such as PCA, computation of Tracy-Widom
2741 statistics, and finding related individuals in structured populations. It
2742 comes with a built-in plotting script and supports multiple file formats and
2743 quantitative phenotypes.")
2744 ;; The license of the eigensoft tools is Expat, but since it's
2745 ;; linking with the GNU Scientific Library (GSL) the effective
2746 ;; license is the GPL.
2747 (license license:gpl3+)))
2749 (define-public edirect
2752 (version "10.2.20181018")
2755 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2756 "/versions/" version
2757 "/edirect-" version ".tar.gz"))
2760 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2761 (build-system perl-build-system)
2764 (modify-phases %standard-phases
2767 (delete 'check) ; simple check after install
2769 (lambda* (#:key outputs #:allow-other-keys)
2770 (install-file "edirect.pl"
2771 (string-append (assoc-ref outputs "out") "/bin"))
2773 (add-after 'install 'wrap-program
2774 (lambda* (#:key outputs #:allow-other-keys)
2775 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2776 (let* ((out (assoc-ref outputs "out"))
2777 (path (getenv "PERL5LIB")))
2778 (wrap-program (string-append out "/bin/edirect.pl")
2779 `("PERL5LIB" ":" prefix (,path))))
2781 (add-after 'wrap-program 'check
2782 (lambda* (#:key outputs #:allow-other-keys)
2783 (invoke (string-append (assoc-ref outputs "out")
2788 `(("perl-html-parser" ,perl-html-parser)
2789 ("perl-encode-locale" ,perl-encode-locale)
2790 ("perl-file-listing" ,perl-file-listing)
2791 ("perl-html-tagset" ,perl-html-tagset)
2792 ("perl-html-tree" ,perl-html-tree)
2793 ("perl-http-cookies" ,perl-http-cookies)
2794 ("perl-http-date" ,perl-http-date)
2795 ("perl-http-message" ,perl-http-message)
2796 ("perl-http-negotiate" ,perl-http-negotiate)
2797 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2798 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2799 ("perl-net-http" ,perl-net-http)
2800 ("perl-uri" ,perl-uri)
2801 ("perl-www-robotrules" ,perl-www-robotrules)
2802 ("perl-xml-simple" ,perl-xml-simple)
2804 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2805 (synopsis "Tools for accessing the NCBI's set of databases")
2807 "Entrez Direct (EDirect) is a method for accessing the National Center
2808 for Biotechnology Information's (NCBI) set of interconnected
2809 databases (publication, sequence, structure, gene, variation, expression,
2810 etc.) from a terminal. Functions take search terms from command-line
2811 arguments. Individual operations are combined to build multi-step queries.
2812 Record retrieval and formatting normally complete the process.
2814 EDirect also provides an argument-driven function that simplifies the
2815 extraction of data from document summaries or other results that are returned
2816 in structured XML format. This can eliminate the need for writing custom
2817 software to answer ad hoc questions.")
2818 (license license:public-domain)))
2820 (define-public exonerate
2829 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2830 "exonerate-" version ".tar.gz"))
2833 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2834 (build-system gnu-build-system)
2836 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2838 `(("pkg-config" ,pkg-config)))
2842 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2843 (synopsis "Generic tool for biological sequence alignment")
2845 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2846 the alignment of sequences using a many alignment models, either exhaustive
2847 dynamic programming or a variety of heuristics.")
2848 (license license:gpl3)))
2850 (define-public express
2858 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2859 version "/express-" version "-src.tgz"))
2862 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2863 (build-system cmake-build-system)
2865 `(#:tests? #f ;no "check" target
2867 (modify-phases %standard-phases
2868 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2869 (lambda* (#:key inputs #:allow-other-keys)
2870 (substitute* "CMakeLists.txt"
2871 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2872 "set(Boost_USE_STATIC_LIBS OFF)")
2873 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2874 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2875 (substitute* "src/CMakeLists.txt"
2876 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2877 (string-append (assoc-ref inputs "bamtools") "/lib"))
2878 (("libprotobuf.a") "libprotobuf.so"))
2882 ("bamtools" ,bamtools)
2883 ("protobuf" ,protobuf)
2885 (home-page "http://bio.math.berkeley.edu/eXpress")
2886 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2888 "eXpress is a streaming tool for quantifying the abundances of a set of
2889 target sequences from sampled subsequences. Example applications include
2890 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2891 analysis (from RNA-Seq), transcription factor binding quantification in
2892 ChIP-Seq, and analysis of metagenomic data.")
2893 (license license:artistic2.0)))
2895 (define-public express-beta-diversity
2897 (name "express-beta-diversity")
2902 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2903 (commit (string-append "v" version))))
2904 (file-name (git-file-name name version))
2907 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2908 (build-system gnu-build-system)
2911 (modify-phases %standard-phases
2913 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2915 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2917 (lambda* (#:key outputs #:allow-other-keys)
2918 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2919 (install-file "../scripts/convertToEBD.py" bin)
2920 (install-file "../bin/ExpressBetaDiversity" bin)
2923 `(("python" ,python-2)))
2924 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2925 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2927 "Express Beta Diversity (EBD) calculates ecological beta diversity
2928 (dissimilarity) measures between biological communities. EBD implements a
2929 variety of diversity measures including those that make use of phylogenetic
2930 similarity of community members.")
2931 (license license:gpl3+)))
2933 (define-public fasttree
2940 "http://www.microbesonline.org/fasttree/FastTree-"
2944 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2945 (build-system gnu-build-system)
2947 `(#:tests? #f ; no "check" target
2949 (modify-phases %standard-phases
2953 (lambda* (#:key source #:allow-other-keys)
2956 "-finline-functions"
2967 "-finline-functions"
2976 (lambda* (#:key outputs #:allow-other-keys)
2977 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2978 (install-file "FastTree" bin)
2979 (install-file "FastTreeMP" bin)
2981 (home-page "http://www.microbesonline.org/fasttree")
2982 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2984 "FastTree can handle alignments with up to a million of sequences in a
2985 reasonable amount of time and memory. For large alignments, FastTree is
2986 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2987 (license license:gpl2+)))
2989 (define-public fastx-toolkit
2991 (name "fastx-toolkit")
2997 "https://github.com/agordon/fastx_toolkit/releases/download/"
2998 version "/fastx_toolkit-" version ".tar.bz2"))
3001 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3002 (build-system gnu-build-system)
3004 `(("libgtextutils" ,libgtextutils)))
3006 `(("pkg-config" ,pkg-config)))
3007 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3008 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3010 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3011 FASTA/FASTQ files preprocessing.
3013 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3014 containing multiple short-reads sequences. The main processing of such
3015 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3016 is sometimes more productive to preprocess the files before mapping the
3017 sequences to the genome---manipulating the sequences to produce better mapping
3018 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3019 (license license:agpl3+)))
3021 (define-public flexbar
3028 (url "https://github.com/seqan/flexbar.git")
3029 (commit (string-append "v" version))))
3030 (file-name (git-file-name name version))
3033 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3034 (build-system cmake-build-system)
3037 (modify-phases %standard-phases
3038 (add-after 'unpack 'do-not-tune-to-CPU
3040 (substitute* "src/CMakeLists.txt"
3041 ((" -march=native") ""))
3044 (lambda* (#:key outputs #:allow-other-keys)
3045 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3046 (with-directory-excursion "../source/test"
3047 (invoke "bash" "flexbar_test.sh"))
3050 (lambda* (#:key outputs #:allow-other-keys)
3051 (let* ((out (string-append (assoc-ref outputs "out")))
3052 (bin (string-append out "/bin/")))
3053 (install-file "flexbar" bin))
3059 `(("pkg-config" ,pkg-config)
3061 (home-page "https://github.com/seqan/flexbar")
3062 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3064 "Flexbar preprocesses high-throughput nucleotide sequencing data
3065 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3066 Moreover, trimming and filtering features are provided. Flexbar increases
3067 read mapping rates and improves genome and transcriptome assemblies. It
3068 supports next-generation sequencing data in fasta/q and csfasta/q format from
3069 Illumina, Roche 454, and the SOLiD platform.")
3070 (license license:bsd-3)))
3072 (define-public fraggenescan
3074 (name "fraggenescan")
3080 (string-append "mirror://sourceforge/fraggenescan/"
3081 "FragGeneScan" version ".tar.gz"))
3083 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3084 (build-system gnu-build-system)
3087 (modify-phases %standard-phases
3089 (add-before 'build 'patch-paths
3090 (lambda* (#:key outputs #:allow-other-keys)
3091 (let* ((out (string-append (assoc-ref outputs "out")))
3092 (share (string-append out "/share/fraggenescan/")))
3093 (substitute* "run_FragGeneScan.pl"
3095 (string-append "system(\"" (which "rm")))
3097 (string-append "system(\"" (which "mv")))
3098 (("\\\"awk") (string-append "\"" (which "awk")))
3099 ;; This script and other programs expect the training files
3100 ;; to be in the non-standard location bin/train/XXX. Change
3101 ;; this to be share/fraggenescan/train/XXX instead.
3102 (("^\\$train.file = \\$dir.*")
3103 (string-append "$train_file = \""
3105 "train/\".$FGS_train_file;")))
3106 (substitute* "run_hmm.c"
3107 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3108 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3112 (invoke "make" "clean")
3113 (invoke "make" "fgs")
3116 (lambda* (#:key outputs #:allow-other-keys)
3117 (let* ((out (string-append (assoc-ref outputs "out")))
3118 (bin (string-append out "/bin/"))
3119 (share (string-append out "/share/fraggenescan/train")))
3120 (install-file "run_FragGeneScan.pl" bin)
3121 (install-file "FragGeneScan" bin)
3122 (copy-recursively "train" share))
3125 (add-after 'install 'post-install-check
3126 ;; In lieu of 'make check', run one of the examples and check the
3127 ;; output files gets created.
3128 (lambda* (#:key outputs #:allow-other-keys)
3129 (let* ((out (string-append (assoc-ref outputs "out")))
3130 (bin (string-append out "/bin/"))
3131 (frag (string-append bin "run_FragGeneScan.pl")))
3132 ;; Test complete genome.
3134 "-genome=./example/NC_000913.fna"
3138 (unless (and (file-exists? "test2.faa")
3139 (file-exists? "test2.ffn")
3140 (file-exists? "test2.gff")
3141 (file-exists? "test2.out"))
3142 (error "Expected files do not exist."))
3143 ;; Test incomplete sequences.
3145 "-genome=./example/NC_000913-fgs.ffn"
3152 ("python" ,python-2))) ;not compatible with python 3.
3153 (home-page "https://sourceforge.net/projects/fraggenescan/")
3154 (synopsis "Finds potentially fragmented genes in short reads")
3156 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3157 short and error-prone DNA sequencing reads. It can also be applied to predict
3158 genes in incomplete assemblies or complete genomes.")
3159 ;; GPL3+ according to private correspondense with the authors.
3160 (license license:gpl3+)))
3162 (define-public fxtract
3163 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3171 (url "https://github.com/ctSkennerton/fxtract.git")
3173 (file-name (git-file-name name version))
3176 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3177 (build-system gnu-build-system)
3179 `(#:make-flags (list
3180 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3182 #:test-target "fxtract_test"
3184 (modify-phases %standard-phases
3186 (add-before 'build 'copy-util
3187 (lambda* (#:key inputs #:allow-other-keys)
3189 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3191 ;; Do not use make install as this requires additional dependencies.
3193 (lambda* (#:key outputs #:allow-other-keys)
3194 (let* ((out (assoc-ref outputs "out"))
3195 (bin (string-append out"/bin")))
3196 (install-file "fxtract" bin)
3202 ;; ctskennerton-util is licensed under GPL2.
3203 `(("ctskennerton-util"
3207 (url "https://github.com/ctSkennerton/util.git")
3208 (commit util-commit)))
3209 (file-name (string-append
3210 "ctstennerton-util-" util-commit "-checkout"))
3213 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3214 (home-page "https://github.com/ctSkennerton/fxtract")
3215 (synopsis "Extract sequences from FASTA and FASTQ files")
3217 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3218 or FASTQ) file given a subsequence. It uses a simple substring search for
3219 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3220 lookups or multi-pattern searching as required. By default fxtract looks in
3221 the sequence of each record but can also be told to look in the header,
3222 comment or quality sections.")
3223 ;; 'util' requires SSE instructions.
3224 (supported-systems '("x86_64-linux"))
3225 (license license:expat))))
3227 (define-public gemma
3234 (url "https://github.com/xiangzhou/GEMMA.git")
3235 (commit (string-append "v" version))))
3236 (file-name (git-file-name name version))
3239 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3242 ("gfortran" ,gfortran "lib")
3245 ("openblas" ,openblas)
3247 (build-system gnu-build-system)
3250 '(,@(match (%current-system)
3252 '("FORCE_DYNAMIC=1"))
3254 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3256 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3258 (modify-phases %standard-phases
3260 (add-after 'unpack 'find-eigen
3261 (lambda* (#:key inputs #:allow-other-keys)
3262 ;; Ensure that Eigen headers can be found
3263 (setenv "CPLUS_INCLUDE_PATH"
3264 (string-append (getenv "CPLUS_INCLUDE_PATH")
3266 (assoc-ref inputs "eigen")
3269 (add-before 'build 'bin-mkdir
3274 (lambda* (#:key outputs #:allow-other-keys)
3275 (let ((out (assoc-ref outputs "out")))
3276 (install-file "bin/gemma"
3280 #:tests? #f)) ; no tests included yet
3281 (home-page "https://github.com/xiangzhou/GEMMA")
3282 (synopsis "Tool for genome-wide efficient mixed model association")
3284 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3285 standard linear mixed model resolver with application in genome-wide
3286 association studies (GWAS).")
3287 (license license:gpl3)))
3296 (url "https://github.com/nboley/grit.git")
3298 (file-name (git-file-name name version))
3301 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3302 (build-system python-build-system)
3304 `(#:python ,python-2
3306 (modify-phases %standard-phases
3307 (add-after 'unpack 'generate-from-cython-sources
3308 (lambda* (#:key inputs outputs #:allow-other-keys)
3309 ;; Delete these C files to force fresh generation from pyx sources.
3310 (delete-file "grit/sparsify_support_fns.c")
3311 (delete-file "grit/call_peaks_support_fns.c")
3312 (substitute* "setup.py"
3313 (("Cython.Setup") "Cython.Build"))
3316 `(("python-scipy" ,python2-scipy)
3317 ("python-numpy" ,python2-numpy)
3318 ("python-pysam" ,python2-pysam)
3319 ("python-networkx" ,python2-networkx)))
3321 `(("python-cython" ,python2-cython)))
3322 (home-page "http://grit-bio.org")
3323 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3325 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3326 full length transcript models. When none of these data sources are available,
3327 GRIT can be run by providing a candidate set of TES or TSS sites. In
3328 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3329 also be run in quantification mode, where it uses a provided GTF file and just
3330 estimates transcript expression.")
3331 (license license:gpl3+)))
3333 (define-public hisat
3340 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3341 version "-beta-source.zip"))
3344 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3345 (build-system gnu-build-system)
3347 `(#:tests? #f ;no check target
3348 #:make-flags '("allall"
3349 ;; Disable unsupported `popcnt' instructions on
3350 ;; architectures other than x86_64
3351 ,@(if (string-prefix? "x86_64"
3352 (or (%current-target-system)
3355 '("POPCNT_CAPABILITY=0")))
3357 (modify-phases %standard-phases
3358 (add-after 'unpack 'patch-sources
3360 ;; XXX Cannot use snippet because zip files are not supported
3361 (substitute* "Makefile"
3362 (("^CC = .*$") "CC = gcc")
3363 (("^CPP = .*$") "CPP = g++")
3364 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3365 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3366 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3367 (substitute* '("hisat-build" "hisat-inspect")
3368 (("/usr/bin/env") (which "env")))
3371 (lambda* (#:key outputs #:allow-other-keys)
3372 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3373 (for-each (lambda (file)
3374 (install-file file bin))
3377 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3379 (delete 'configure))))
3381 `(("unzip" ,unzip)))
3386 ;; Non-portable SSE instructions are used so building fails on platforms
3387 ;; other than x86_64.
3388 (supported-systems '("x86_64-linux"))
3389 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3390 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3392 "HISAT is a fast and sensitive spliced alignment program for mapping
3393 RNA-seq reads. In addition to one global FM index that represents a whole
3394 genome, HISAT uses a large set of small FM indexes that collectively cover the
3395 whole genome. These small indexes (called local indexes) combined with
3396 several alignment strategies enable effective alignment of RNA-seq reads, in
3397 particular, reads spanning multiple exons.")
3398 (license license:gpl3+)))
3400 (define-public hisat2
3407 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3408 "/downloads/hisat2-" version "-source.zip"))
3411 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3412 (build-system gnu-build-system)
3414 `(#:tests? #f ; no check target
3415 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3416 #:modules ((guix build gnu-build-system)
3420 (modify-phases %standard-phases
3421 (add-after 'unpack 'make-deterministic
3423 (substitute* "Makefile"
3428 (lambda* (#:key outputs #:allow-other-keys)
3429 (let* ((out (assoc-ref outputs "out"))
3430 (bin (string-append out "/bin/"))
3431 (doc (string-append out "/share/doc/hisat2/")))
3433 (cut install-file <> bin)
3435 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3437 (install-file "doc/manual.inc.html" doc))
3440 `(("unzip" ,unzip) ; needed for archive from ftp
3442 ("pandoc" ,ghc-pandoc))) ; for documentation
3443 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3444 (synopsis "Graph-based alignment of genomic sequencing reads")
3445 (description "HISAT2 is a fast and sensitive alignment program for mapping
3446 next-generation sequencing reads (both DNA and RNA) to a population of human
3447 genomes (as well as to a single reference genome). In addition to using one
3448 global @dfn{graph FM} (GFM) index that represents a population of human
3449 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3450 the whole genome. These small indexes, combined with several alignment
3451 strategies, enable rapid and accurate alignment of sequencing reads. This new
3452 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3453 ;; HISAT2 contains files from Bowtie2, which is released under
3454 ;; GPLv2 or later. The HISAT2 source files are released under
3456 (license license:gpl3+)))
3458 (define-public hmmer
3466 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3469 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3470 (build-system gnu-build-system)
3471 (native-inputs `(("perl" ,perl)))
3472 (home-page "http://hmmer.org/")
3473 (synopsis "Biosequence analysis using profile hidden Markov models")
3475 "HMMER is used for searching sequence databases for homologs of protein
3476 sequences, and for making protein sequence alignments. It implements methods
3477 using probabilistic models called profile hidden Markov models (profile
3479 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3481 (supported-systems '("x86_64-linux" "i686-linux"))
3482 (license license:bsd-3)))
3484 (define-public htseq
3490 (uri (pypi-uri "HTSeq" version))
3493 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3494 (build-system python-build-system)
3496 `(("python-cython" ,python-cython)))
3497 ;; Numpy needs to be propagated when htseq is used as a Python library.
3499 `(("python-numpy" ,python-numpy)))
3501 `(("python-pysam" ,python-pysam)
3502 ("python-matplotlib" ,python-matplotlib)))
3503 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3504 (synopsis "Analysing high-throughput sequencing data with Python")
3506 "HTSeq is a Python package that provides infrastructure to process data
3507 from high-throughput sequencing assays.")
3508 (license license:gpl3+)))
3510 (define-public python2-htseq
3511 (package-with-python2 htseq))
3513 (define-public java-htsjdk
3515 (name "java-htsjdk")
3516 (version "2.3.0") ; last version without build dependency on gradle
3520 (url "https://github.com/samtools/htsjdk.git")
3522 (file-name (git-file-name name version))
3525 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3526 (modules '((guix build utils)))
3528 ;; Delete pre-built binaries
3530 (delete-file-recursively "lib")
3533 (build-system ant-build-system)
3535 `(#:tests? #f ; test require Internet access
3538 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3539 "/share/java/htsjdk/"))
3540 #:build-target "all"
3542 (modify-phases %standard-phases
3543 ;; The build phase also installs the jars
3544 (delete 'install))))
3546 `(("java-ngs" ,java-ngs)
3547 ("java-snappy-1" ,java-snappy-1)
3548 ("java-commons-compress" ,java-commons-compress)
3549 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3550 ("java-commons-jexl-2" ,java-commons-jexl-2)
3551 ("java-xz" ,java-xz)))
3553 `(("java-testng" ,java-testng)))
3554 (home-page "http://samtools.github.io/htsjdk/")
3555 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3557 "HTSJDK is an implementation of a unified Java library for accessing
3558 common file formats, such as SAM and VCF, used for high-throughput
3559 sequencing (HTS) data. There are also an number of useful utilities for
3560 manipulating HTS data.")
3561 (license license:expat)))
3563 (define-public java-htsjdk-latest
3565 (name "java-htsjdk")
3570 (url "https://github.com/samtools/htsjdk.git")
3572 (file-name (string-append name "-" version "-checkout"))
3575 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3576 (build-system ant-build-system)
3578 `(#:tests? #f ; test require Scala
3580 #:jar-name "htsjdk.jar"
3582 (modify-phases %standard-phases
3583 (add-after 'unpack 'remove-useless-build.xml
3584 (lambda _ (delete-file "build.xml") #t))
3585 ;; The tests require the scalatest package.
3586 (add-after 'unpack 'remove-tests
3587 (lambda _ (delete-file-recursively "src/test") #t)))))
3589 `(("java-ngs" ,java-ngs)
3590 ("java-snappy-1" ,java-snappy-1)
3591 ("java-commons-compress" ,java-commons-compress)
3592 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3593 ("java-commons-jexl-2" ,java-commons-jexl-2)
3594 ("java-xz" ,java-xz)))
3596 `(("java-junit" ,java-junit)))
3597 (home-page "http://samtools.github.io/htsjdk/")
3598 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3600 "HTSJDK is an implementation of a unified Java library for accessing
3601 common file formats, such as SAM and VCF, used for high-throughput
3602 sequencing (HTS) data. There are also an number of useful utilities for
3603 manipulating HTS data.")
3604 (license license:expat)))
3606 ;; This is needed for picard 2.10.3
3607 (define-public java-htsjdk-2.10.1
3608 (package (inherit java-htsjdk-latest)
3609 (name "java-htsjdk")
3614 (url "https://github.com/samtools/htsjdk.git")
3616 (file-name (string-append name "-" version "-checkout"))
3619 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3620 (build-system ant-build-system)
3622 `(#:tests? #f ; tests require Scala
3624 #:jar-name "htsjdk.jar"
3626 (modify-phases %standard-phases
3627 (add-after 'unpack 'remove-useless-build.xml
3628 (lambda _ (delete-file "build.xml") #t))
3629 ;; The tests require the scalatest package.
3630 (add-after 'unpack 'remove-tests
3631 (lambda _ (delete-file-recursively "src/test") #t)))))))
3633 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3634 ;; recent version of java-htsjdk, which depends on gradle.
3635 (define-public java-picard
3637 (name "java-picard")
3642 (url "https://github.com/broadinstitute/picard.git")
3644 (file-name (string-append "java-picard-" version "-checkout"))
3647 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3648 (modules '((guix build utils)))
3651 ;; Delete pre-built binaries.
3652 (delete-file-recursively "lib")
3654 (substitute* "build.xml"
3655 ;; Remove build-time dependency on git.
3656 (("failifexecutionfails=\"true\"")
3657 "failifexecutionfails=\"false\"")
3659 (("depends=\"compile-htsjdk, ")
3661 (("depends=\"compile-htsjdk-tests, ")
3663 ;; Build picard-lib.jar before building picard.jar
3664 (("name=\"picard-jar\" depends=\"" line)
3665 (string-append line "picard-lib-jar, ")))
3667 (build-system ant-build-system)
3669 `(#:build-target "picard-jar"
3670 #:test-target "test"
3671 ;; Tests require jacoco:coverage.
3674 (list (string-append "-Dhtsjdk_lib_dir="
3675 (assoc-ref %build-inputs "java-htsjdk")
3676 "/share/java/htsjdk/")
3677 "-Dhtsjdk-classes=dist/tmp"
3678 (string-append "-Dhtsjdk-version="
3679 ,(package-version java-htsjdk)))
3682 (modify-phases %standard-phases
3683 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3684 (delete 'generate-jar-indices)
3685 (add-after 'unpack 'use-our-htsjdk
3686 (lambda* (#:key inputs #:allow-other-keys)
3687 (substitute* "build.xml"
3688 (("\\$\\{htsjdk\\}/lib")
3689 (string-append (assoc-ref inputs "java-htsjdk")
3690 "/share/java/htsjdk/")))
3692 (add-after 'unpack 'make-test-target-independent
3693 (lambda* (#:key inputs #:allow-other-keys)
3694 (substitute* "build.xml"
3695 (("name=\"test\" depends=\"compile, ")
3696 "name=\"test\" depends=\""))
3698 (replace 'install (install-jars "dist")))))
3700 `(("java-htsjdk" ,java-htsjdk)
3701 ("java-guava" ,java-guava)))
3703 `(("java-testng" ,java-testng)))
3704 (home-page "http://broadinstitute.github.io/picard/")
3705 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3706 (description "Picard is a set of Java command line tools for manipulating
3707 high-throughput sequencing (HTS) data and formats. Picard is implemented
3708 using the HTSJDK Java library to support accessing file formats that are
3709 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3711 (license license:expat)))
3713 ;; This is needed for dropseq-tools
3714 (define-public java-picard-2.10.3
3716 (name "java-picard")
3721 (url "https://github.com/broadinstitute/picard.git")
3723 (file-name (string-append "java-picard-" version "-checkout"))
3726 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3727 (build-system ant-build-system)
3729 `(#:jar-name "picard.jar"
3730 ;; Tests require jacoco:coverage.
3733 #:main-class "picard.cmdline.PicardCommandLine"
3734 #:modules ((guix build ant-build-system)
3736 (guix build java-utils)
3741 (modify-phases %standard-phases
3742 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3743 (delete 'generate-jar-indices)
3744 (add-after 'unpack 'remove-useless-build.xml
3745 (lambda _ (delete-file "build.xml") #t))
3746 ;; This is necessary to ensure that htsjdk is found when using
3747 ;; picard.jar as an executable.
3748 (add-before 'build 'edit-classpath-in-manifest
3749 (lambda* (#:key inputs #:allow-other-keys)
3750 (chmod "build.xml" #o664)
3751 (call-with-output-file "build.xml.new"
3755 (with-input-from-file "build.xml"
3756 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3757 `((target . ,(lambda (tag . kids)
3758 (let ((name ((sxpath '(name *text*))
3760 ;; FIXME: We're breaking the line
3761 ;; early with a dummy path to
3762 ;; ensure that the store reference
3763 ;; isn't broken apart and can still
3764 ;; be found by the reference
3769 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3770 ;; maximum line length is 70
3771 (string-tabulate (const #\b) 57)
3772 (assoc-ref inputs "java-htsjdk"))))
3773 (if (member "manifest" name)
3776 (@ (file "${manifest.file}")
3777 (match "\\r\\n\\r\\n")
3778 (replace "${line.separator}")))
3781 (file "${manifest.file}")
3784 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3785 (*text* . ,(lambda (_ txt) txt))))
3787 (rename-file "build.xml.new" "build.xml")
3790 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3792 `(("java-testng" ,java-testng)
3793 ("java-guava" ,java-guava)))
3794 (home-page "http://broadinstitute.github.io/picard/")
3795 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3796 (description "Picard is a set of Java command line tools for manipulating
3797 high-throughput sequencing (HTS) data and formats. Picard is implemented
3798 using the HTSJDK Java library to support accessing file formats that are
3799 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3801 (license license:expat)))
3803 ;; This is the last version of Picard to provide net.sf.samtools
3804 (define-public java-picard-1.113
3805 (package (inherit java-picard)
3806 (name "java-picard")
3811 (url "https://github.com/broadinstitute/picard.git")
3813 (file-name (string-append "java-picard-" version "-checkout"))
3816 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3817 (modules '((guix build utils)))
3820 ;; Delete pre-built binaries.
3821 (delete-file-recursively "lib")
3824 (build-system ant-build-system)
3826 `(#:build-target "picard-jar"
3827 #:test-target "test"
3828 ;; FIXME: the class path at test time is wrong.
3829 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3830 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3833 ;; This is only used for tests.
3835 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3837 (modify-phases %standard-phases
3838 ;; FIXME: This phase fails.
3839 (delete 'generate-jar-indices)
3840 ;; Do not use bundled ant bzip2.
3841 (add-after 'unpack 'use-ant-bzip
3842 (lambda* (#:key inputs #:allow-other-keys)
3843 (substitute* "build.xml"
3844 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3845 (string-append (assoc-ref inputs "ant")
3848 (add-after 'unpack 'make-test-target-independent
3849 (lambda* (#:key inputs #:allow-other-keys)
3850 (substitute* "build.xml"
3851 (("name=\"test\" depends=\"compile, ")
3852 "name=\"test\" depends=\"compile-tests, ")
3853 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3854 "name=\"compile\" depends=\"compile-src\""))
3856 (add-after 'unpack 'fix-deflater-path
3857 (lambda* (#:key outputs #:allow-other-keys)
3858 (substitute* "src/java/net/sf/samtools/Defaults.java"
3859 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3860 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3861 (assoc-ref outputs "out")
3862 "/lib/jni/libIntelDeflater.so"
3865 ;; Build the deflater library, because we've previously deleted the
3866 ;; pre-built one. This can only be built with access to the JDK
3868 (add-after 'build 'build-jni
3869 (lambda* (#:key inputs #:allow-other-keys)
3872 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3873 "-xf" (assoc-ref inputs "jdk-src"))
3874 (invoke "javah" "-jni"
3875 "-classpath" "classes"
3877 "net.sf.samtools.util.zip.IntelDeflater")
3878 (with-directory-excursion "src/c/inteldeflater"
3879 (invoke "gcc" "-I../../../lib" "-I."
3880 (string-append "-I" (assoc-ref inputs "jdk")
3882 "-I../../../jdk-src/src/share/native/common/"
3883 "-I../../../jdk-src/src/solaris/native/common/"
3884 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3885 (invoke "gcc" "-shared"
3886 "-o" "../../../lib/jni/libIntelDeflater.so"
3887 "IntelDeflater.o" "-lz" "-lstdc++"))
3889 ;; We can only build everything else after building the JNI library.
3890 (add-after 'build-jni 'build-rest
3891 (lambda* (#:key make-flags #:allow-other-keys)
3892 (apply invoke `("ant" "all" ,@make-flags))
3894 (add-before 'build 'set-JAVA6_HOME
3896 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3898 (replace 'install (install-jars "dist"))
3899 (add-after 'install 'install-jni-lib
3900 (lambda* (#:key outputs #:allow-other-keys)
3901 (let ((jni (string-append (assoc-ref outputs "out")
3904 (install-file "lib/jni/libIntelDeflater.so" jni)
3907 `(("java-snappy-1" ,java-snappy-1)
3908 ("java-commons-jexl-2" ,java-commons-jexl-2)
3909 ("java-cofoja" ,java-cofoja)
3910 ("ant" ,ant) ; for bzip2 support at runtime
3913 `(("ant-apache-bcel" ,ant-apache-bcel)
3914 ("ant-junit" ,ant-junit)
3915 ("java-testng" ,java-testng)
3916 ("java-commons-bcel" ,java-commons-bcel)
3917 ("java-jcommander" ,java-jcommander)
3918 ("jdk" ,icedtea-8 "jdk")
3919 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3921 (define-public fastqc
3928 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3929 "projects/fastqc/fastqc_v"
3930 version "_source.zip"))
3933 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3934 (build-system ant-build-system)
3936 `(#:tests? #f ; there are no tests
3937 #:build-target "build"
3939 (modify-phases %standard-phases
3940 (add-after 'unpack 'fix-dependencies
3941 (lambda* (#:key inputs #:allow-other-keys)
3942 (substitute* "build.xml"
3944 (string-append (assoc-ref inputs "java-jbzip2")
3945 "/share/java/jbzip2.jar"))
3947 (string-append (assoc-ref inputs "java-picard-1.113")
3948 "/share/java/sam-1.112.jar"))
3950 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3951 "/share/java/sis-jhdf5.jar")))
3953 ;; There is no installation target
3955 (lambda* (#:key inputs outputs #:allow-other-keys)
3956 (let* ((out (assoc-ref outputs "out"))
3957 (bin (string-append out "/bin"))
3958 (share (string-append out "/share/fastqc/"))
3959 (exe (string-append share "/fastqc")))
3960 (for-each mkdir-p (list bin share))
3961 (copy-recursively "bin" share)
3963 (("my \\$java_bin = 'java';")
3964 (string-append "my $java_bin = '"
3965 (assoc-ref inputs "java")
3968 (symlink exe (string-append bin "/fastqc"))
3972 ("perl" ,perl) ; needed for the wrapper script
3973 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3974 ("java-picard-1.113" ,java-picard-1.113)
3975 ("java-jbzip2" ,java-jbzip2)))
3977 `(("unzip" ,unzip)))
3978 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3979 (synopsis "Quality control tool for high throughput sequence data")
3981 "FastQC aims to provide a simple way to do some quality control
3982 checks on raw sequence data coming from high throughput sequencing
3983 pipelines. It provides a modular set of analyses which you can use to
3984 give a quick impression of whether your data has any problems of which
3985 you should be aware before doing any further analysis.
3987 The main functions of FastQC are:
3990 @item Import of data from BAM, SAM or FastQ files (any variant);
3991 @item Providing a quick overview to tell you in which areas there may
3993 @item Summary graphs and tables to quickly assess your data;
3994 @item Export of results to an HTML based permanent report;
3995 @item Offline operation to allow automated generation of reports
3996 without running the interactive application.
3998 (license license:gpl3+)))
4000 (define-public fastp
4008 (url "https://github.com/OpenGene/fastp.git")
4009 (commit (string-append "v" version))))
4010 (file-name (git-file-name name version))
4013 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4014 (build-system gnu-build-system)
4016 `(#:tests? #f ; there are none
4018 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4020 (modify-phases %standard-phases
4022 (add-before 'install 'create-target-dir
4023 (lambda* (#:key outputs #:allow-other-keys)
4024 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4028 (home-page "https://github.com/OpenGene/fastp/")
4029 (synopsis "All-in-one FastQ preprocessor")
4031 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4032 FastQ files. This tool has multi-threading support to afford high
4034 (license license:expat)))
4036 (define-public htslib
4043 "https://github.com/samtools/htslib/releases/download/"
4044 version "/htslib-" version ".tar.bz2"))
4047 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4048 (build-system gnu-build-system)
4051 ("openssl" ,openssl)))
4052 ;; This is referred to in the pkg-config file as a required library.
4057 (home-page "http://www.htslib.org")
4058 (synopsis "C library for reading/writing high-throughput sequencing data")
4060 "HTSlib is a C library for reading/writing high-throughput sequencing
4061 data. It also provides the @command{bgzip}, @command{htsfile}, and
4062 @command{tabix} utilities.")
4063 ;; Files under cram/ are released under the modified BSD license;
4064 ;; the rest is released under the Expat license
4065 (license (list license:expat license:bsd-3))))
4067 ;; This package should be removed once no packages rely upon it.
4075 "https://github.com/samtools/htslib/releases/download/"
4076 version "/htslib-" version ".tar.bz2"))
4079 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4088 (url "https://github.com/nboley/idr.git")
4090 (file-name (git-file-name name version))
4093 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4094 ;; Delete generated C code.
4096 '(begin (delete-file "idr/inv_cdf.c") #t))))
4097 (build-system python-build-system)
4098 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4099 ;; are no longer part of this package. It also asserts False, which
4100 ;; causes the tests to always fail.
4101 (arguments `(#:tests? #f))
4103 `(("python-scipy" ,python-scipy)
4104 ("python-sympy" ,python-sympy)
4105 ("python-numpy" ,python-numpy)
4106 ("python-matplotlib" ,python-matplotlib)))
4108 `(("python-cython" ,python-cython)))
4109 (home-page "https://github.com/nboley/idr")
4110 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4112 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4113 to measure the reproducibility of findings identified from replicate
4114 experiments and provide highly stable thresholds based on reproducibility.")
4115 (license license:gpl2+)))
4117 (define-public jellyfish
4123 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4124 "releases/download/v" version
4125 "/jellyfish-" version ".tar.gz"))
4128 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4129 (build-system gnu-build-system)
4130 (outputs '("out" ;for library
4131 "ruby" ;for Ruby bindings
4132 "python")) ;for Python bindings
4135 (list (string-append "--enable-ruby-binding="
4136 (assoc-ref %outputs "ruby"))
4137 (string-append "--enable-python-binding="
4138 (assoc-ref %outputs "python")))
4140 (modify-phases %standard-phases
4141 (add-before 'check 'set-SHELL-variable
4143 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4145 (setenv "SHELL" (which "bash"))
4151 ("python" ,python-2)
4152 ("pkg-config" ,pkg-config)))
4154 `(("htslib" ,htslib)))
4155 (synopsis "Tool for fast counting of k-mers in DNA")
4157 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4158 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4159 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4160 is a command-line program that reads FASTA and multi-FASTA files containing
4161 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4162 translated into a human-readable text format using the @code{jellyfish dump}
4163 command, or queried for specific k-mers with @code{jellyfish query}.")
4164 (home-page "http://www.genome.umd.edu/jellyfish.html")
4165 ;; JELLYFISH seems to be 64-bit only.
4166 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4167 ;; The combined work is published under the GPLv3 or later. Individual
4168 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4169 (license (list license:gpl3+ license:expat))))
4171 (define-public khmer
4179 (url "https://github.com/dib-lab/khmer.git")
4180 (commit (string-append "v" version))))
4181 (file-name (git-file-name name version))
4184 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4185 (modules '((guix build utils)))
4188 ;; Delete bundled libraries. We do not replace the bundled seqan
4189 ;; as it is a modified subset of the old version 1.4.1.
4191 ;; We do not replace the bundled MurmurHash as the canonical
4192 ;; repository for this code 'SMHasher' is unsuitable for providing
4194 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4195 (delete-file-recursively "third-party/zlib")
4196 (delete-file-recursively "third-party/bzip2")
4197 (delete-file-recursively "third-party/seqan")
4198 (substitute* "setup.cfg"
4199 (("# libraries = z,bz2")
4200 "libraries = z,bz2")
4201 (("include:third-party/zlib:third-party/bzip2")
4204 (build-system python-build-system)
4207 (modify-phases %standard-phases
4208 (add-after 'unpack 'set-cc
4209 (lambda _ (setenv "CC" "gcc") #t))
4211 (add-before 'reset-gzip-timestamps 'make-files-writable
4212 (lambda* (#:key outputs #:allow-other-keys)
4213 ;; Make sure .gz files are writable so that the
4214 ;; 'reset-gzip-timestamps' phase can do its work.
4215 (let ((out (assoc-ref outputs "out")))
4216 (for-each make-file-writable
4217 (find-files out "\\.gz$"))
4220 `(("python-cython" ,python-cython)
4221 ("python-pytest" ,python-pytest)
4222 ("python-pytest-runner" ,python-pytest-runner)))
4227 ("python-screed" ,python-screed)
4228 ("python-bz2file" ,python-bz2file)))
4229 (home-page "https://khmer.readthedocs.org/")
4230 (synopsis "K-mer counting, filtering and graph traversal library")
4231 (description "The khmer software is a set of command-line tools for
4232 working with DNA shotgun sequencing data from genomes, transcriptomes,
4233 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4234 sometimes better. Khmer can also identify and fix problems with shotgun
4236 ;; When building on i686, armhf and mips64el, we get the following error:
4237 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4238 (supported-systems '("x86_64-linux" "aarch64-linux"))
4239 (license license:bsd-3)))
4241 (define-public kaiju
4248 (url "https://github.com/bioinformatics-centre/kaiju")
4249 (commit (string-append "v" version))))
4250 (file-name (git-file-name name version))
4253 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4254 (build-system gnu-build-system)
4256 `(#:tests? #f ; There are no tests.
4258 (modify-phases %standard-phases
4260 (add-before 'build 'move-to-src-dir
4261 (lambda _ (chdir "src") #t))
4263 (lambda* (#:key inputs outputs #:allow-other-keys)
4264 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4267 (copy-recursively "bin" bin))
4272 (home-page "http://kaiju.binf.ku.dk/")
4273 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4274 (description "Kaiju is a program for sensitive taxonomic classification
4275 of high-throughput sequencing reads from metagenomic whole genome sequencing
4277 (license license:gpl3+)))
4282 (version "2.1.1.20160309")
4285 (uri (pypi-uri "MACS2" version))
4288 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
4289 (build-system python-build-system)
4291 `(#:python ,python-2 ; only compatible with Python 2.7
4292 #:tests? #f)) ; no test target
4294 `(("python-numpy" ,python2-numpy)))
4295 (home-page "https://github.com/taoliu/MACS/")
4296 (synopsis "Model based analysis for ChIP-Seq data")
4298 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4299 identifying transcript factor binding sites named Model-based Analysis of
4300 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4301 the significance of enriched ChIP regions and it improves the spatial
4302 resolution of binding sites through combining the information of both
4303 sequencing tag position and orientation.")
4304 (license license:bsd-3)))
4306 (define-public mafft
4313 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4314 "-without-extensions-src.tgz"))
4315 (file-name (string-append name "-" version ".tgz"))
4318 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4319 (build-system gnu-build-system)
4321 `(#:tests? #f ; no automated tests, though there are tests in the read me
4322 #:make-flags (let ((out (assoc-ref %outputs "out")))
4323 (list (string-append "PREFIX=" out)
4324 (string-append "BINDIR="
4325 (string-append out "/bin"))))
4327 (modify-phases %standard-phases
4328 (add-after 'unpack 'enter-dir
4329 (lambda _ (chdir "core") #t))
4330 (add-after 'enter-dir 'patch-makefile
4332 ;; on advice from the MAFFT authors, there is no need to
4333 ;; distribute mafft-profile, mafft-distance, or
4334 ;; mafft-homologs.rb as they are too "specialised".
4335 (substitute* "Makefile"
4336 ;; remove mafft-homologs.rb from SCRIPTS
4337 (("^SCRIPTS = mafft mafft-homologs.rb")
4339 ;; remove mafft-homologs from MANPAGES
4340 (("^MANPAGES = mafft.1 mafft-homologs.1")
4341 "MANPAGES = mafft.1")
4342 ;; remove mafft-distance from PROGS
4343 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4344 "PROGS = dvtditr dndfast7 dndblast sextet5")
4345 ;; remove mafft-profile from PROGS
4346 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4347 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4348 (("^rm -f mafft-profile mafft-profile.exe") "#")
4349 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4350 ;; do not install MAN pages in libexec folder
4351 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4352 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4354 (add-after 'enter-dir 'patch-paths
4355 (lambda* (#:key inputs #:allow-other-keys)
4356 (substitute* '("pairash.c"
4358 (("perl") (which "perl"))
4359 (("([\"`| ])awk" _ prefix)
4360 (string-append prefix (which "awk")))
4361 (("grep") (which "grep")))
4364 (add-after 'install 'wrap-programs
4365 (lambda* (#:key outputs #:allow-other-keys)
4366 (let* ((out (assoc-ref outputs "out"))
4367 (bin (string-append out "/bin"))
4368 (path (string-append
4369 (assoc-ref %build-inputs "coreutils") "/bin:")))
4370 (for-each (lambda (file)
4372 `("PATH" ":" prefix (,path))))
4380 ("coreutils" ,coreutils)))
4381 (home-page "http://mafft.cbrc.jp/alignment/software/")
4382 (synopsis "Multiple sequence alignment program")
4384 "MAFFT offers a range of multiple alignment methods for nucleotide and
4385 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4386 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4388 (license (license:non-copyleft
4389 "http://mafft.cbrc.jp/alignment/software/license.txt"
4390 "BSD-3 with different formatting"))))
4399 (url "https://github.com/marbl/mash.git")
4400 (commit (string-append "v" version))))
4401 (file-name (git-file-name name version))
4404 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4405 (modules '((guix build utils)))
4408 ;; Delete bundled kseq.
4409 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4410 (delete-file "src/mash/kseq.h")
4412 (build-system gnu-build-system)
4414 `(#:tests? #f ; No tests.
4417 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4418 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4419 #:make-flags (list "CC=gcc")
4421 (modify-phases %standard-phases
4422 (add-after 'unpack 'fix-includes
4424 (substitute* '("src/mash/Sketch.cpp"
4425 "src/mash/CommandFind.cpp"
4426 "src/mash/CommandScreen.cpp")
4427 (("^#include \"kseq\\.h\"")
4428 "#include \"htslib/kseq.h\""))
4430 (add-after 'fix-includes 'use-c++14
4432 ;; capnproto 0.7 requires c++14 to build
4433 (substitute* "configure.ac"
4434 (("c\\+\\+11") "c++14"))
4435 (substitute* "Makefile.in"
4436 (("c\\+\\+11") "c++14"))
4439 `(("autoconf" ,autoconf)
4440 ;; Capnproto and htslib are statically embedded in the final
4441 ;; application. Therefore we also list their licenses, below.
4442 ("capnproto" ,capnproto)
4443 ("htslib" ,htslib)))
4447 (supported-systems '("x86_64-linux"))
4448 (home-page "https://mash.readthedocs.io")
4449 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4450 (description "Mash is a fast sequence distance estimator that uses the
4451 MinHash algorithm and is designed to work with genomes and metagenomes in the
4452 form of assemblies or reads.")
4453 (license (list license:bsd-3 ; Mash
4454 license:expat ; HTSlib and capnproto
4455 license:public-domain ; MurmurHash 3
4456 license:cpl1.0)))) ; Open Bloom Filter
4458 (define-public metabat
4466 (url "https://bitbucket.org/berkeleylab/metabat.git")
4467 (commit (string-append "v" version))))
4468 (file-name (git-file-name name version))
4471 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4472 (patches (search-patches "metabat-fix-compilation.patch"))))
4473 (build-system scons-build-system)
4475 `(#:scons ,scons-python2
4477 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4478 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4479 #:tests? #f ;; Tests are run during the build phase.
4481 (modify-phases %standard-phases
4482 (add-after 'unpack 'fix-includes
4484 (substitute* "src/BamUtils.h"
4485 (("^#include \"bam/bam\\.h\"")
4486 "#include \"samtools/bam.h\"")
4487 (("^#include \"bam/sam\\.h\"")
4488 "#include \"samtools/sam.h\""))
4489 (substitute* "src/KseqReader.h"
4490 (("^#include \"bam/kseq\\.h\"")
4491 "#include \"htslib/kseq.h\""))
4493 (add-after 'unpack 'fix-scons
4494 (lambda* (#:key inputs #:allow-other-keys)
4495 (substitute* "SConstruct"
4496 (("^htslib_dir += 'samtools'")
4497 (string-append "htslib_dir = '"
4498 (assoc-ref inputs "htslib")
4500 (("^samtools_dir = 'samtools'")
4501 (string-append "samtools_dir = '"
4502 (assoc-ref inputs "samtools")
4504 (("^findStaticOrShared\\('bam', hts_lib")
4505 (string-append "findStaticOrShared('bam', '"
4506 (assoc-ref inputs "samtools")
4508 ;; Do not distribute README.
4509 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4514 ("samtools" ,samtools)
4517 (home-page "https://bitbucket.org/berkeleylab/metabat")
4519 "Reconstruction of single genomes from complex microbial communities")
4521 "Grouping large genomic fragments assembled from shotgun metagenomic
4522 sequences to deconvolute complex microbial communities, or metagenome binning,
4523 enables the study of individual organisms and their interactions. MetaBAT is
4524 an automated metagenome binning software, which integrates empirical
4525 probabilistic distances of genome abundance and tetranucleotide frequency.")
4526 ;; The source code contains inline assembly.
4527 (supported-systems '("x86_64-linux" "i686-linux"))
4528 (license (license:non-copyleft "file://license.txt"
4529 "See license.txt in the distribution."))))
4531 (define-public minced
4538 (url "https://github.com/ctSkennerton/minced.git")
4540 (file-name (git-file-name name version))
4543 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4544 (build-system gnu-build-system)
4546 `(#:test-target "test"
4548 (modify-phases %standard-phases
4550 (add-before 'check 'fix-test
4552 ;; Fix test for latest version.
4553 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4554 (("minced:0.1.6") "minced:0.2.0"))
4556 (replace 'install ; No install target.
4557 (lambda* (#:key inputs outputs #:allow-other-keys)
4558 (let* ((out (assoc-ref outputs "out"))
4559 (bin (string-append out "/bin"))
4560 (wrapper (string-append bin "/minced")))
4561 ;; Minced comes with a wrapper script that tries to figure out where
4562 ;; it is located before running the JAR. Since these paths are known
4563 ;; to us, we build our own wrapper to avoid coreutils dependency.
4564 (install-file "minced.jar" bin)
4565 (with-output-to-file wrapper
4569 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4570 (assoc-ref inputs "jre") "/bin/java -jar "
4571 bin "/minced.jar \"$@\"\n"))))
4572 (chmod wrapper #o555))
4575 `(("jdk" ,icedtea "jdk")))
4578 ("jre" ,icedtea "out")))
4579 (home-page "https://github.com/ctSkennerton/minced")
4580 (synopsis "Mining CRISPRs in Environmental Datasets")
4582 "MinCED is a program to find Clustered Regularly Interspaced Short
4583 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4584 unassembled metagenomic reads, but is mainly designed for full genomes and
4585 assembled metagenomic sequence.")
4586 (license license:gpl3+)))
4594 (uri (pypi-uri "misopy" version))
4597 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4598 (modules '((guix build utils)))
4600 (substitute* "setup.py"
4601 ;; Use setuptools, or else the executables are not
4603 (("distutils.core") "setuptools")
4604 ;; use "gcc" instead of "cc" for compilation
4606 "cc.set_executables(
4610 linker_so='gcc -shared'); defines"))
4612 (build-system python-build-system)
4614 `(#:python ,python-2 ; only Python 2 is supported
4615 #:tests? #f)) ; no "test" target
4617 `(("samtools" ,samtools)
4618 ("python-numpy" ,python2-numpy)
4619 ("python-pysam" ,python2-pysam)
4620 ("python-scipy" ,python2-scipy)
4621 ("python-matplotlib" ,python2-matplotlib)))
4623 `(("python-mock" ,python2-mock) ;for tests
4624 ("python-pytz" ,python2-pytz))) ;for tests
4625 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4626 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4628 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4629 the expression level of alternatively spliced genes from RNA-Seq data, and
4630 identifies differentially regulated isoforms or exons across samples. By
4631 modeling the generative process by which reads are produced from isoforms in
4632 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4633 that a read originated from a particular isoform.")
4634 (license license:gpl2)))
4636 (define-public muscle
4639 (version "3.8.1551")
4641 (method url-fetch/tarbomb)
4643 "http://www.drive5.com/muscle/muscle_src_"
4647 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4648 (build-system gnu-build-system)
4650 `(#:make-flags (list "LDLIBS = -lm")
4652 (modify-phases %standard-phases
4655 ;; There are no tests, so just test if it runs.
4656 (lambda _ (invoke "./muscle" "-version") #t))
4658 (lambda* (#:key outputs #:allow-other-keys)
4659 (let* ((out (assoc-ref outputs "out"))
4660 (bin (string-append out "/bin")))
4661 (install-file "muscle" bin)
4663 (home-page "http://www.drive5.com/muscle")
4664 (synopsis "Multiple sequence alignment program")
4666 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4667 program for nucleotide and protein sequences.")
4668 ;; License information found in 'muscle -h' and usage.cpp.
4669 (license license:public-domain)))
4671 (define-public newick-utils
4672 ;; There are no recent releases so we package from git.
4673 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4675 (name "newick-utils")
4676 (version (string-append "1.6-1." (string-take commit 8)))
4680 (url "https://github.com/tjunier/newick_utils.git")
4682 (file-name (string-append name "-" version "-checkout"))
4685 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4686 (build-system gnu-build-system)
4688 ;; XXX: TODO: Enable Lua and Guile bindings.
4689 ;; https://github.com/tjunier/newick_utils/issues/13
4690 `(("libxml2" ,libxml2)
4694 `(("autoconf" ,autoconf)
4695 ("automake" ,automake)
4696 ("libtool" ,libtool)))
4697 (synopsis "Programs for working with newick format phylogenetic trees")
4699 "Newick-utils is a suite of utilities for processing phylogenetic trees
4700 in Newick format. Functions include re-rooting, extracting subtrees,
4701 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4702 (home-page "https://github.com/tjunier/newick_utils")
4703 (license license:bsd-3))))
4712 "https://github.com/wwood/OrfM/releases/download/v"
4713 version "/orfm-" version ".tar.gz"))
4716 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4717 (build-system gnu-build-system)
4718 (inputs `(("zlib" ,zlib)))
4720 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4721 ("ruby-rspec" ,ruby-rspec)
4723 (synopsis "Simple and not slow open reading frame (ORF) caller")
4725 "An ORF caller finds stretches of DNA that, when translated, are not
4726 interrupted by stop codons. OrfM finds and prints these ORFs.")
4727 (home-page "https://github.com/wwood/OrfM")
4728 (license license:lgpl3+)))
4730 (define-public python2-pbcore
4732 (name "python2-pbcore")
4736 (uri (pypi-uri "pbcore" version))
4739 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4740 (build-system python-build-system)
4741 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4743 `(("python-cython" ,python2-cython)
4744 ("python-numpy" ,python2-numpy)
4745 ("python-pysam" ,python2-pysam)
4746 ("python-h5py" ,python2-h5py)))
4748 `(("python-nose" ,python2-nose)
4749 ("python-sphinx" ,python2-sphinx)
4750 ("python-pyxb" ,python2-pyxb)))
4751 (home-page "http://pacificbiosciences.github.io/pbcore/")
4752 (synopsis "Library for reading and writing PacBio data files")
4754 "The pbcore package provides Python APIs for interacting with PacBio data
4755 files and writing bioinformatics applications.")
4756 (license license:bsd-3)))
4758 (define-public python2-warpedlmm
4760 (name "python2-warpedlmm")
4765 (uri (pypi-uri "WarpedLMM" version ".zip"))
4768 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4769 (build-system python-build-system)
4771 `(#:python ,python-2)) ; requires Python 2.7
4773 `(("python-scipy" ,python2-scipy)
4774 ("python-numpy" ,python2-numpy)
4775 ("python-matplotlib" ,python2-matplotlib)
4776 ("python-fastlmm" ,python2-fastlmm)
4777 ("python-pandas" ,python2-pandas)
4778 ("python-pysnptools" ,python2-pysnptools)))
4780 `(("python-mock" ,python2-mock)
4781 ("python-nose" ,python2-nose)
4783 (home-page "https://github.com/PMBio/warpedLMM")
4784 (synopsis "Implementation of warped linear mixed models")
4786 "WarpedLMM is a Python implementation of the warped linear mixed model,
4787 which automatically learns an optimal warping function (or transformation) for
4788 the phenotype as it models the data.")
4789 (license license:asl2.0)))
4791 (define-public pbtranscript-tofu
4792 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4794 (name "pbtranscript-tofu")
4795 (version (string-append "2.2.3." (string-take commit 7)))
4799 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4801 (file-name (string-append name "-" version "-checkout"))
4804 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4805 (modules '((guix build utils)))
4808 ;; remove bundled Cython sources
4809 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4811 (build-system python-build-system)
4813 `(#:python ,python-2
4814 ;; FIXME: Tests fail with "No such file or directory:
4815 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4818 (modify-phases %standard-phases
4819 (add-after 'unpack 'enter-directory
4821 (chdir "pbtranscript-tofu/pbtranscript/")
4823 ;; With setuptools version 18.0 and later this setup.py hack causes
4824 ;; a build error, so we disable it.
4825 (add-after 'enter-directory 'patch-setuppy
4827 (substitute* "setup.py"
4828 (("if 'setuptools.extension' in sys.modules:")
4832 `(("python-numpy" ,python2-numpy)
4833 ("python-bx-python" ,python2-bx-python)
4834 ("python-networkx" ,python2-networkx)
4835 ("python-scipy" ,python2-scipy)
4836 ("python-pbcore" ,python2-pbcore)
4837 ("python-h5py" ,python2-h5py)))
4839 `(("python-cython" ,python2-cython)
4840 ("python-nose" ,python2-nose)))
4841 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4842 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4844 "pbtranscript-tofu contains scripts to analyze transcriptome data
4845 generated using the PacBio Iso-Seq protocol.")
4846 (license license:bsd-3))))
4848 (define-public prank
4855 "http://wasabiapp.org/download/prank/prank.source."
4859 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4860 (build-system gnu-build-system)
4863 (modify-phases %standard-phases
4864 (add-after 'unpack 'enter-src-dir
4868 (add-after 'unpack 'remove-m64-flag
4869 ;; Prank will build with the correct 'bit-ness' without this flag
4870 ;; and this allows building on 32-bit machines.
4871 (lambda _ (substitute* "src/Makefile"
4876 (lambda* (#:key outputs #:allow-other-keys)
4877 (let* ((out (assoc-ref outputs "out"))
4878 (bin (string-append out "/bin"))
4879 (man (string-append out "/share/man/man1"))
4880 (path (string-append
4881 (assoc-ref %build-inputs "mafft") "/bin:"
4882 (assoc-ref %build-inputs "exonerate") "/bin:"
4883 (assoc-ref %build-inputs "bppsuite") "/bin")))
4884 (install-file "prank" bin)
4885 (wrap-program (string-append bin "/prank")
4886 `("PATH" ":" prefix (,path)))
4887 (install-file "prank.1" man))
4891 ("exonerate" ,exonerate)
4892 ("bppsuite" ,bppsuite)))
4893 (home-page "http://wasabiapp.org/software/prank/")
4894 (synopsis "Probabilistic multiple sequence alignment program")
4896 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4897 codon and amino-acid sequences. It is based on a novel algorithm that treats
4898 insertions correctly and avoids over-estimation of the number of deletion
4899 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4900 in phylogenetics and correctly takes into account the evolutionary distances
4901 between sequences. Lastly, PRANK allows for defining a potential structure
4902 for sequences to be aligned and then, simultaneously with the alignment,
4903 predicts the locations of structural units in the sequences.")
4904 (license license:gpl2+)))
4906 (define-public proteinortho
4908 (name "proteinortho")
4915 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4916 version "_src.tar.gz"))
4919 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4920 (build-system gnu-build-system)
4922 `(#:test-target "test"
4924 (modify-phases %standard-phases
4926 ;; There is no configure script, so we modify the Makefile directly.
4927 (lambda* (#:key outputs #:allow-other-keys)
4928 (substitute* "Makefile"
4931 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4933 (add-before 'install 'make-install-directory
4934 ;; The install directory is not created during 'make install'.
4935 (lambda* (#:key outputs #:allow-other-keys)
4936 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4938 (add-after 'install 'wrap-programs
4939 (lambda* (#:key inputs outputs #:allow-other-keys)
4940 (let* ((path (getenv "PATH"))
4941 (out (assoc-ref outputs "out"))
4942 (binary (string-append out "/bin/proteinortho5.pl")))
4943 (wrap-program binary `("PATH" ":" prefix (,path))))
4947 ("python" ,python-2)
4948 ("blast+" ,blast+)))
4949 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4950 (synopsis "Detect orthologous genes across species")
4952 "Proteinortho is a tool to detect orthologous genes across different
4953 species. For doing so, it compares similarities of given gene sequences and
4954 clusters them to find significant groups. The algorithm was designed to handle
4955 large-scale data and can be applied to hundreds of species at once.")
4956 (license license:gpl2+)))
4958 (define-public pyicoteo
4966 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4967 (commit (string-append "v" version))))
4968 (file-name (git-file-name name version))
4971 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4972 (build-system python-build-system)
4974 `(#:python ,python-2 ; does not work with Python 3
4975 #:tests? #f)) ; there are no tests
4977 `(("python2-matplotlib" ,python2-matplotlib)))
4978 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4979 (synopsis "Analyze high-throughput genetic sequencing data")
4981 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4982 sequencing data. It works with genomic coordinates. There are currently six
4983 different command-line tools:
4986 @item pyicoregion: for generating exploratory regions automatically;
4987 @item pyicoenrich: for differential enrichment between two conditions;
4988 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4989 @item pyicos: for genomic coordinates manipulation;
4990 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4991 @item pyicount: to count how many reads from N experiment files overlap in a
4993 @item pyicotrocol: to combine operations from pyicoteo.
4995 (license license:gpl3+)))
4997 (define-public prodigal
5004 (url "https://github.com/hyattpd/Prodigal.git")
5005 (commit (string-append "v" version))))
5006 (file-name (git-file-name name version))
5009 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5010 (build-system gnu-build-system)
5012 `(#:tests? #f ;no check target
5013 #:make-flags (list (string-append "INSTALLDIR="
5014 (assoc-ref %outputs "out")
5017 (modify-phases %standard-phases
5018 (delete 'configure))))
5019 (home-page "http://prodigal.ornl.gov")
5020 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5022 "Prodigal runs smoothly on finished genomes, draft genomes, and
5023 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5024 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5025 partial genes, and identifies translation initiation sites.")
5026 (license license:gpl3+)))
5028 (define-public roary
5036 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5040 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5041 (build-system perl-build-system)
5044 (modify-phases %standard-phases
5049 ;; The tests are not run by default, so we run each test file
5051 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5053 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5054 (getenv "PERL5LIB")))
5055 (for-each (lambda (file)
5056 (display file)(display "\n")
5057 (invoke "perl" file))
5058 (find-files "t" ".*\\.t$"))
5061 ;; There is no 'install' target in the Makefile.
5062 (lambda* (#:key outputs #:allow-other-keys)
5063 (let* ((out (assoc-ref outputs "out"))
5064 (bin (string-append out "/bin"))
5065 (perl (string-append out "/lib/perl5/site_perl"))
5066 (roary-plots "contrib/roary_plots"))
5069 (copy-recursively "bin" bin)
5070 (copy-recursively "lib" perl)
5072 (add-after 'install 'wrap-programs
5073 (lambda* (#:key inputs outputs #:allow-other-keys)
5074 (let* ((out (assoc-ref outputs "out"))
5075 (perl5lib (getenv "PERL5LIB"))
5076 (path (getenv "PATH")))
5077 (for-each (lambda (prog)
5078 (let ((binary (string-append out "/" prog)))
5079 (wrap-program binary
5080 `("PERL5LIB" ":" prefix
5081 (,(string-append perl5lib ":" out
5082 "/lib/perl5/site_perl"))))
5083 (wrap-program binary
5085 (,(string-append path ":" out "/bin"))))))
5086 (find-files "bin" ".*[^R]$"))
5088 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5089 (r-site-lib (getenv "R_LIBS_SITE"))
5091 (string-append (assoc-ref inputs "coreutils") "/bin")))
5093 `("R_LIBS_SITE" ":" prefix
5094 (,(string-append r-site-lib ":" out "/site-library/"))))
5097 (,(string-append coreutils-path ":" out "/bin"))))))
5100 `(("perl-env-path" ,perl-env-path)
5101 ("perl-test-files" ,perl-test-files)
5102 ("perl-test-most" ,perl-test-most)
5103 ("perl-test-output" ,perl-test-output)))
5105 `(("perl-array-utils" ,perl-array-utils)
5106 ("bioperl" ,bioperl-minimal)
5107 ("perl-digest-md5-file" ,perl-digest-md5-file)
5108 ("perl-exception-class" ,perl-exception-class)
5109 ("perl-file-find-rule" ,perl-file-find-rule)
5110 ("perl-file-grep" ,perl-file-grep)
5111 ("perl-file-slurper" ,perl-file-slurper)
5112 ("perl-file-which" ,perl-file-which)
5113 ("perl-graph" ,perl-graph)
5114 ("perl-graph-readwrite" ,perl-graph-readwrite)
5115 ("perl-log-log4perl" ,perl-log-log4perl)
5116 ("perl-moose" ,perl-moose)
5117 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5118 ("perl-text-csv" ,perl-text-csv)
5119 ("bedtools" ,bedtools)
5123 ("parallel" ,parallel)
5126 ("fasttree" ,fasttree)
5130 ("r-minimal" ,r-minimal)
5131 ("r-ggplot2" ,r-ggplot2)
5132 ("coreutils" ,coreutils)))
5133 (home-page "http://sanger-pathogens.github.io/Roary")
5134 (synopsis "High speed stand-alone pan genome pipeline")
5136 "Roary is a high speed stand alone pan genome pipeline, which takes
5137 annotated assemblies in GFF3 format (produced by the Prokka program) and
5138 calculates the pan genome. Using a standard desktop PC, it can analyse
5139 datasets with thousands of samples, without compromising the quality of the
5140 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5141 single processor. Roary is not intended for metagenomics or for comparing
5142 extremely diverse sets of genomes.")
5143 (license license:gpl3)))
5145 (define-public raxml
5153 (url "https://github.com/stamatak/standard-RAxML.git")
5154 (commit (string-append "v" version))))
5155 (file-name (git-file-name name version))
5158 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5159 (build-system gnu-build-system)
5161 `(#:tests? #f ; There are no tests.
5162 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5163 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5165 (modify-phases %standard-phases
5168 (lambda* (#:key outputs #:allow-other-keys)
5169 (let* ((out (assoc-ref outputs "out"))
5170 (bin (string-append out "/bin"))
5171 (executable "raxmlHPC-HYBRID"))
5172 (install-file executable bin)
5173 (symlink (string-append bin "/" executable) "raxml"))
5176 `(("openmpi" ,openmpi)))
5177 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
5178 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5180 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5182 ;; The source includes x86 specific code
5183 (supported-systems '("x86_64-linux" "i686-linux"))
5184 (license license:gpl2+)))
5194 (url "https://github.com/deweylab/RSEM.git")
5195 (commit (string-append "v" version))))
5197 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5198 (file-name (git-file-name name version))
5199 (modules '((guix build utils)))
5202 ;; remove bundled copy of boost and samtools
5203 (delete-file-recursively "boost")
5204 (delete-file-recursively "samtools-1.3")
5206 (build-system gnu-build-system)
5208 `(#:tests? #f ;no "check" target
5210 (list (string-append "BOOST="
5211 (assoc-ref %build-inputs "boost")
5213 (string-append "SAMHEADERS="
5214 (assoc-ref %build-inputs "htslib")
5215 "/include/htslib/sam.h")
5216 (string-append "SAMLIBS="
5217 (assoc-ref %build-inputs "htslib")
5220 (modify-phases %standard-phases
5221 ;; No "configure" script.
5222 ;; Do not build bundled samtools library.
5225 (substitute* "Makefile"
5226 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5227 (("^\\$\\(SAMLIBS\\).*") ""))
5230 (lambda* (#:key outputs #:allow-other-keys)
5231 (let* ((out (string-append (assoc-ref outputs "out")))
5232 (bin (string-append out "/bin/"))
5233 (perl (string-append out "/lib/perl5/site_perl")))
5236 (for-each (lambda (file)
5237 (install-file file bin))
5238 (find-files "." "rsem-.*"))
5239 (install-file "rsem_perl_utils.pm" perl))
5241 (add-after 'install 'wrap-program
5242 (lambda* (#:key outputs #:allow-other-keys)
5243 (let ((out (assoc-ref outputs "out")))
5244 (for-each (lambda (prog)
5245 (wrap-program (string-append out "/bin/" prog)
5246 `("PERL5LIB" ":" prefix
5247 (,(string-append out "/lib/perl5/site_perl")))))
5248 '("rsem-calculate-expression"
5250 "rsem-generate-data-matrix"
5251 "rsem-generate-ngvector"
5252 "rsem-plot-transcript-wiggles"
5253 "rsem-prepare-reference"
5255 "rsem-run-prsem-testing-procedure")))
5259 ("r-minimal" ,r-minimal)
5261 ("htslib" ,htslib-1.3)
5263 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5264 (synopsis "Estimate gene expression levels from RNA-Seq data")
5266 "RSEM is a software package for estimating gene and isoform expression
5267 levels from RNA-Seq data. The RSEM package provides a user-friendly
5268 interface, supports threads for parallel computation of the EM algorithm,
5269 single-end and paired-end read data, quality scores, variable-length reads and
5270 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5271 interval estimates for expression levels. For visualization, it can generate
5272 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5273 (license license:gpl3+)))
5275 (define-public rseqc
5283 (string-append "mirror://sourceforge/rseqc/"
5284 "RSeQC-" version ".tar.gz"))
5286 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5287 (modules '((guix build utils)))
5290 ;; remove bundled copy of pysam
5291 (delete-file-recursively "lib/pysam")
5292 (substitute* "setup.py"
5293 ;; remove dependency on outdated "distribute" module
5294 (("^from distribute_setup import use_setuptools") "")
5295 (("^use_setuptools\\(\\)") "")
5296 ;; do not use bundled copy of pysam
5297 (("^have_pysam = False") "have_pysam = True"))
5299 (build-system python-build-system)
5300 (arguments `(#:python ,python-2))
5302 `(("python-cython" ,python2-cython)
5303 ("python-pysam" ,python2-pysam)
5304 ("python-numpy" ,python2-numpy)
5307 `(("python-nose" ,python2-nose)))
5308 (home-page "http://rseqc.sourceforge.net/")
5309 (synopsis "RNA-seq quality control package")
5311 "RSeQC provides a number of modules that can comprehensively evaluate
5312 high throughput sequence data, especially RNA-seq data. Some basic modules
5313 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5314 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5315 distribution, coverage uniformity, strand specificity, etc.")
5316 (license license:gpl3+)))
5319 ;; There are no release tarballs. According to the installation
5320 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5321 ;; stable release is identified by this changeset ID.
5322 (let ((changeset "2329130")
5326 (version (string-append "0-" revision "." changeset))
5330 (url "https://bitbucket.org/libsleipnir/sleipnir")
5331 (changeset changeset)))
5332 (file-name (string-append name "-" version "-checkout"))
5335 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5336 (build-system gnu-build-system)
5338 `(#:modules ((srfi srfi-1)
5339 (guix build gnu-build-system)
5342 (let ((dirs '("SeekMiner"
5348 (modify-phases %standard-phases
5351 (substitute* "gen_tools_am"
5352 (("/usr/bin/env.*") (which "perl")))
5353 (invoke "bash" "gen_auto")
5355 (add-after 'build 'build-additional-tools
5356 (lambda* (#:key make-flags #:allow-other-keys)
5357 (for-each (lambda (dir)
5358 (with-directory-excursion (string-append "tools/" dir)
5359 (apply invoke "make" make-flags)))
5362 (add-after 'install 'install-additional-tools
5363 (lambda* (#:key make-flags #:allow-other-keys)
5364 (for-each (lambda (dir)
5365 (with-directory-excursion (string-append "tools/" dir)
5366 (apply invoke `("make" ,@make-flags "install"))))
5373 ("readline" ,readline)
5374 ("gengetopt" ,gengetopt)
5375 ("log4cpp" ,log4cpp)))
5377 `(("autoconf" ,autoconf)
5378 ("automake" ,automake)
5380 (home-page "http://seek.princeton.edu")
5381 (synopsis "Gene co-expression search engine")
5383 "SEEK is a computational gene co-expression search engine. SEEK provides
5384 biologists with a way to navigate the massive human expression compendium that
5385 now contains thousands of expression datasets. SEEK returns a robust ranking
5386 of co-expressed genes in the biological area of interest defined by the user's
5387 query genes. It also prioritizes thousands of expression datasets according
5388 to the user's query of interest.")
5389 (license license:cc-by3.0))))
5391 (define-public samtools
5399 (string-append "mirror://sourceforge/samtools/samtools/"
5400 version "/samtools-" version ".tar.bz2"))
5403 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5404 (modules '((guix build utils)))
5406 ;; Delete bundled htslib.
5407 (delete-file-recursively "htslib-1.9")
5409 (build-system gnu-build-system)
5411 `(#:modules ((ice-9 ftw)
5413 (guix build gnu-build-system)
5415 #:configure-flags (list "--with-ncurses")
5417 (modify-phases %standard-phases
5418 (add-after 'unpack 'patch-tests
5420 (substitute* "test/test.pl"
5421 ;; The test script calls out to /bin/bash
5422 (("/bin/bash") (which "bash")))
5424 (add-after 'install 'install-library
5425 (lambda* (#:key outputs #:allow-other-keys)
5426 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5427 (install-file "libbam.a" lib)
5429 (add-after 'install 'install-headers
5430 (lambda* (#:key outputs #:allow-other-keys)
5431 (let ((include (string-append (assoc-ref outputs "out")
5432 "/include/samtools/")))
5433 (for-each (lambda (file)
5434 (install-file file include))
5435 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5437 (native-inputs `(("pkg-config" ,pkg-config)))
5439 `(("htslib" ,htslib)
5440 ("ncurses" ,ncurses)
5444 (home-page "http://samtools.sourceforge.net")
5445 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5447 "Samtools implements various utilities for post-processing nucleotide
5448 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5449 variant calling (in conjunction with bcftools), and a simple alignment
5451 (license license:expat)))
5453 (define-public samtools-0.1
5454 ;; This is the most recent version of the 0.1 line of samtools. The input
5455 ;; and output formats differ greatly from that used and produced by samtools
5456 ;; 1.x and is still used in many bioinformatics pipelines.
5457 (package (inherit samtools)
5463 (string-append "mirror://sourceforge/samtools/samtools/"
5464 version "/samtools-" version ".tar.bz2"))
5466 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5468 `(#:tests? #f ;no "check" target
5470 (list "LIBCURSES=-lncurses")
5471 ,@(substitute-keyword-arguments (package-arguments samtools)
5473 `(modify-phases ,phases
5475 (lambda* (#:key outputs #:allow-other-keys)
5476 (let ((bin (string-append
5477 (assoc-ref outputs "out") "/bin")))
5479 (install-file "samtools" bin)
5481 (delete 'patch-tests)
5482 (delete 'configure))))))))
5484 (define-public mosaik
5485 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5490 ;; There are no release tarballs nor tags.
5493 (url "https://github.com/wanpinglee/MOSAIK.git")
5495 (file-name (string-append name "-" version))
5498 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5499 (build-system gnu-build-system)
5501 `(#:tests? #f ; no tests
5502 #:make-flags (list "CC=gcc")
5504 (modify-phases %standard-phases
5506 (lambda _ (chdir "src") #t))
5508 (lambda* (#:key outputs #:allow-other-keys)
5509 (let ((bin (string-append (assoc-ref outputs "out")
5512 (copy-recursively "../bin" bin)
5516 ("zlib:static" ,zlib "static")
5518 (supported-systems '("x86_64-linux"))
5519 (home-page "https://github.com/wanpinglee/MOSAIK")
5520 (synopsis "Map nucleotide sequence reads to reference genomes")
5522 "MOSAIK is a program for mapping second and third-generation sequencing
5523 reads to a reference genome. MOSAIK can align reads generated by all the
5524 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5525 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5526 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5527 ;; code released into the public domain:
5528 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5529 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5530 (license (list license:gpl2+ license:public-domain)))))
5532 (define-public ngs-sdk
5539 (url "https://github.com/ncbi/ngs.git")
5541 (file-name (git-file-name name version))
5544 "0d5k5kabgl15as37kj9x65xc92j4gcqms86hvihw3yb6wag0r0q3"))))
5545 (build-system gnu-build-system)
5547 `(#:parallel-build? #f ; not supported
5548 #:tests? #f ; no "check" target
5550 (modify-phases %standard-phases
5552 (lambda* (#:key outputs #:allow-other-keys)
5553 (let ((out (assoc-ref outputs "out")))
5554 ;; Allow 'konfigure.perl' to find 'package.prl'.
5556 (string-append ".:" (getenv "PERL5LIB")))
5558 ;; The 'configure' script doesn't recognize things like
5559 ;; '--enable-fast-install'.
5560 (invoke "./configure"
5561 (string-append "--build-prefix=" (getcwd) "/build")
5562 (string-append "--prefix=" out))
5564 (add-after 'unpack 'enter-dir
5565 (lambda _ (chdir "ngs-sdk") #t)))))
5566 (native-inputs `(("perl" ,perl)))
5567 ;; According to the test
5568 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5569 ;; in ngs-sdk/setup/konfigure.perl
5570 (supported-systems '("i686-linux" "x86_64-linux"))
5571 (home-page "https://github.com/ncbi/ngs")
5572 (synopsis "API for accessing Next Generation Sequencing data")
5574 "NGS is a domain-specific API for accessing reads, alignments and pileups
5575 produced from Next Generation Sequencing. The API itself is independent from
5576 any particular back-end implementation, and supports use of multiple back-ends
5578 (license license:public-domain)))
5580 (define-public java-ngs
5581 (package (inherit ngs-sdk)
5584 `(,@(substitute-keyword-arguments
5585 `(#:modules ((guix build gnu-build-system)
5589 ,@(package-arguments ngs-sdk))
5591 `(modify-phases ,phases
5592 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5594 `(("jdk" ,icedtea "jdk")
5595 ("ngs-sdk" ,ngs-sdk)))
5596 (synopsis "Java bindings for NGS SDK")))
5598 (define-public ncbi-vdb
5605 (url "https://github.com/ncbi/ncbi-vdb.git")
5607 (file-name (git-file-name name version))
5610 "0knkj1sq34hlivgv5qd6jlczqrs3ldmfgn6vbbw7p4mqxvb9mirk"))))
5611 (build-system gnu-build-system)
5613 `(#:parallel-build? #f ; not supported
5614 #:tests? #f ; no "check" target
5615 #:make-flags '("HAVE_HDF5=1")
5617 (modify-phases %standard-phases
5618 (add-after 'unpack 'make-files-writable
5619 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5620 (add-before 'configure 'set-perl-search-path
5622 ;; Work around "dotless @INC" build failure.
5624 (string-append (getcwd) "/setup:"
5625 (getenv "PERL5LIB")))
5627 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5628 (add-after 'unpack 'patch-krypto-flags
5630 (substitute* "libs/krypto/Makefile"
5631 (("-Wa,-march=generic64\\+aes") "")
5632 (("-Wa,-march=generic64\\+sse4") ""))
5635 (lambda* (#:key inputs outputs #:allow-other-keys)
5636 (let ((out (assoc-ref outputs "out")))
5637 ;; Override include path for libmagic
5638 (substitute* "setup/package.prl"
5639 (("name => 'magic', Include => '/usr/include'")
5640 (string-append "name=> 'magic', Include => '"
5641 (assoc-ref inputs "libmagic")
5644 ;; Install kdf5 library (needed by sra-tools)
5645 (substitute* "build/Makefile.install"
5646 (("LIBRARIES_TO_INSTALL =")
5647 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5649 (substitute* "build/Makefile.env"
5650 (("CFLAGS =" prefix)
5651 (string-append prefix "-msse2 ")))
5653 ;; Override search path for ngs-java
5654 (substitute* "setup/package.prl"
5655 (("/usr/local/ngs/ngs-java")
5656 (assoc-ref inputs "java-ngs")))
5658 ;; The 'configure' script doesn't recognize things like
5659 ;; '--enable-fast-install'.
5660 (invoke "./configure"
5661 (string-append "--build-prefix=" (getcwd) "/build")
5662 (string-append "--prefix=" (assoc-ref outputs "out"))
5663 (string-append "--debug")
5664 (string-append "--with-xml2-prefix="
5665 (assoc-ref inputs "libxml2"))
5666 (string-append "--with-ngs-sdk-prefix="
5667 (assoc-ref inputs "ngs-sdk"))
5668 (string-append "--with-hdf5-prefix="
5669 (assoc-ref inputs "hdf5")))
5671 (add-after 'install 'install-interfaces
5672 (lambda* (#:key outputs #:allow-other-keys)
5673 ;; Install interface libraries. On i686 the interface libraries
5674 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5675 ;; architecture name ("i386") instead of the target system prefix
5677 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5678 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5679 ,(system->linux-architecture
5680 (or (%current-target-system)
5683 (string-append (assoc-ref outputs "out")
5685 ;; Install interface headers
5686 (copy-recursively "interfaces"
5687 (string-append (assoc-ref outputs "out")
5690 ;; These files are needed by sra-tools.
5691 (add-after 'install 'install-configuration-files
5692 (lambda* (#:key outputs #:allow-other-keys)
5693 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5695 (install-file "libs/kfg/default.kfg" target)
5696 (install-file "libs/kfg/certs.kfg" target))
5699 `(("libxml2" ,libxml2)
5700 ("ngs-sdk" ,ngs-sdk)
5701 ("java-ngs" ,java-ngs)
5704 (native-inputs `(("perl" ,perl)))
5705 ;; NCBI-VDB requires SSE capability.
5706 (supported-systems '("i686-linux" "x86_64-linux"))
5707 (home-page "https://github.com/ncbi/ncbi-vdb")
5708 (synopsis "Database engine for genetic information")
5710 "The NCBI-VDB library implements a highly compressed columnar data
5711 warehousing engine that is most often used to store genetic information.
5712 Databases are stored in a portable image within the file system, and can be
5713 accessed/downloaded on demand across HTTP.")
5714 (license license:public-domain)))
5716 (define-public plink
5724 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5725 version "-src.zip"))
5727 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5728 (patches (search-patches "plink-1.07-unclobber-i.patch"
5729 "plink-endian-detection.patch"))))
5730 (build-system gnu-build-system)
5732 '(#:tests? #f ;no "check" target
5733 #:make-flags (list (string-append "LIB_LAPACK="
5734 (assoc-ref %build-inputs "lapack")
5735 "/lib/liblapack.so")
5738 ;; disable phoning home
5741 (modify-phases %standard-phases
5742 ;; no "configure" script
5745 (lambda* (#:key outputs #:allow-other-keys)
5746 (let ((bin (string-append (assoc-ref outputs "out")
5748 (install-file "plink" bin)
5752 ("lapack" ,lapack)))
5754 `(("unzip" ,unzip)))
5755 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5756 (synopsis "Whole genome association analysis toolset")
5758 "PLINK is a whole genome association analysis toolset, designed to
5759 perform a range of basic, large-scale analyses in a computationally efficient
5760 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5761 so there is no support for steps prior to this (e.g. study design and
5762 planning, generating genotype or CNV calls from raw data). Through
5763 integration with gPLINK and Haploview, there is some support for the
5764 subsequent visualization, annotation and storage of results.")
5765 ;; Code is released under GPLv2, except for fisher.h, which is under
5767 (license (list license:gpl2 license:lgpl2.1+))))
5769 (define-public plink-ng
5770 (package (inherit plink)
5777 (url "https://github.com/chrchang/plink-ng.git")
5778 (commit (string-append "v" version))))
5779 (file-name (git-file-name name version))
5781 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5782 (build-system gnu-build-system)
5784 '(#:tests? #f ;no "check" target
5785 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5786 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5788 "-f" "Makefile.std")
5790 (modify-phases %standard-phases
5791 (add-after 'unpack 'chdir
5792 (lambda _ (chdir "1.9") #t))
5793 (delete 'configure) ; no "configure" script
5795 (lambda* (#:key outputs #:allow-other-keys)
5796 (let ((bin (string-append (assoc-ref outputs "out")
5798 (install-file "plink" bin)
5803 ("openblas" ,openblas)))
5804 (home-page "https://www.cog-genomics.org/plink/")
5805 (license license:gpl3+)))
5807 (define-public smithlab-cpp
5808 (let ((revision "1")
5809 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5811 (name "smithlab-cpp")
5812 (version (string-append "0." revision "." (string-take commit 7)))
5816 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5818 (file-name (string-append name "-" version "-checkout"))
5821 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5822 (build-system gnu-build-system)
5824 `(#:modules ((guix build gnu-build-system)
5827 #:tests? #f ;no "check" target
5829 (modify-phases %standard-phases
5830 (add-after 'unpack 'use-samtools-headers
5832 (substitute* '("SAM.cpp"
5834 (("sam.h") "samtools/sam.h"))
5837 (lambda* (#:key outputs #:allow-other-keys)
5838 (let* ((out (assoc-ref outputs "out"))
5839 (lib (string-append out "/lib"))
5840 (include (string-append out "/include/smithlab-cpp")))
5843 (for-each (cut install-file <> lib)
5844 (find-files "." "\\.o$"))
5845 (for-each (cut install-file <> include)
5846 (find-files "." "\\.hpp$")))
5848 (delete 'configure))))
5850 `(("samtools" ,samtools-0.1)
5852 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5853 (synopsis "C++ helper library for functions used in Smith lab projects")
5855 "Smithlab CPP is a C++ library that includes functions used in many of
5856 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5857 structures, classes for genomic regions, mapped sequencing reads, etc.")
5858 (license license:gpl3+))))
5860 (define-public preseq
5866 (uri (string-append "https://github.com/smithlabcode/preseq/"
5867 "releases/download/v" version
5868 "/preseq_v" version ".tar.bz2"))
5870 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5871 (modules '((guix build utils)))
5873 ;; Remove bundled samtools.
5874 (delete-file-recursively "samtools")
5876 (build-system gnu-build-system)
5878 `(#:tests? #f ;no "check" target
5880 (modify-phases %standard-phases
5881 (delete 'configure))
5883 (list (string-append "PREFIX="
5884 (assoc-ref %outputs "out"))
5885 (string-append "LIBBAM="
5886 (assoc-ref %build-inputs "samtools")
5888 (string-append "SMITHLAB_CPP="
5889 (assoc-ref %build-inputs "smithlab-cpp")
5892 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5895 ("samtools" ,samtools-0.1)
5896 ("smithlab-cpp" ,smithlab-cpp)
5898 (home-page "http://smithlabresearch.org/software/preseq/")
5899 (synopsis "Program for analyzing library complexity")
5901 "The preseq package is aimed at predicting and estimating the complexity
5902 of a genomic sequencing library, equivalent to predicting and estimating the
5903 number of redundant reads from a given sequencing depth and how many will be
5904 expected from additional sequencing using an initial sequencing experiment.
5905 The estimates can then be used to examine the utility of further sequencing,
5906 optimize the sequencing depth, or to screen multiple libraries to avoid low
5907 complexity samples.")
5908 (license license:gpl3+)))
5910 (define-public python-screed
5912 (name "python-screed")
5917 (uri (pypi-uri "screed" version))
5920 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5921 (build-system python-build-system)
5924 (modify-phases %standard-phases
5925 ;; Tests must be run after installation, as the "screed" command does
5926 ;; not exist right after building.
5928 (add-after 'install 'check
5929 (lambda* (#:key inputs outputs #:allow-other-keys)
5930 (let ((out (assoc-ref outputs "out")))
5931 (setenv "PYTHONPATH"
5932 (string-append out "/lib/python"
5933 (string-take (string-take-right
5934 (assoc-ref inputs "python")
5937 (getenv "PYTHONPATH")))
5938 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5939 (invoke "python" "setup.py" "test")
5942 `(("python-pytest" ,python-pytest)
5943 ("python-pytest-cov" ,python-pytest-cov)
5944 ("python-pytest-runner" ,python-pytest-runner)))
5946 `(("python-bz2file" ,python-bz2file)))
5947 (home-page "https://github.com/dib-lab/screed/")
5948 (synopsis "Short read sequence database utilities")
5949 (description "Screed parses FASTA and FASTQ files and generates databases.
5950 Values such as sequence name, sequence description, sequence quality and the
5951 sequence itself can be retrieved from these databases.")
5952 (license license:bsd-3)))
5954 (define-public python2-screed
5955 (package-with-python2 python-screed))
5957 (define-public sra-tools
5965 (url "https://github.com/ncbi/sra-tools.git")
5967 (file-name (git-file-name name version))
5970 "0vqzap68v81k0zif2mnqfy8pnw2nrhsg87p6mgq8qk3nk2jv2rgy"))))
5971 (build-system gnu-build-system)
5973 `(#:parallel-build? #f ; not supported
5974 #:tests? #f ; no "check" target
5976 (list (string-append "DEFAULT_CRT="
5977 (assoc-ref %build-inputs "ncbi-vdb")
5979 (string-append "DEFAULT_KFG="
5980 (assoc-ref %build-inputs "ncbi-vdb")
5982 (string-append "VDB_LIBDIR="
5983 (assoc-ref %build-inputs "ncbi-vdb")
5984 ,(if (string-prefix? "x86_64"
5985 (or (%current-target-system)
5990 (modify-phases %standard-phases
5991 (add-before 'configure 'set-perl-search-path
5993 ;; Work around "dotless @INC" build failure.
5995 (string-append (getcwd) "/setup:"
5996 (getenv "PERL5LIB")))
5999 (lambda* (#:key inputs outputs #:allow-other-keys)
6000 ;; The build system expects a directory containing the sources and
6001 ;; raw build output of ncbi-vdb, including files that are not
6002 ;; installed. Since we are building against an installed version of
6003 ;; ncbi-vdb, the following modifications are needed.
6004 (substitute* "setup/konfigure.perl"
6005 ;; Make the configure script look for the "ilib" directory of
6006 ;; "ncbi-vdb" without first checking for the existence of a
6007 ;; matching library in its "lib" directory.
6008 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6009 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6010 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6011 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6012 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6015 (substitute* "tools/copycat/Makefile"
6016 (("smagic-static") "lmagic"))
6018 ;; The 'configure' script doesn't recognize things like
6019 ;; '--enable-fast-install'.
6020 (invoke "./configure"
6021 (string-append "--build-prefix=" (getcwd) "/build")
6022 (string-append "--prefix=" (assoc-ref outputs "out"))
6023 (string-append "--debug")
6024 (string-append "--with-fuse-prefix="
6025 (assoc-ref inputs "fuse"))
6026 (string-append "--with-magic-prefix="
6027 (assoc-ref inputs "libmagic"))
6028 ;; TODO: building with libxml2 fails with linker errors
6029 ;; (string-append "--with-xml2-prefix="
6030 ;; (assoc-ref inputs "libxml2"))
6031 (string-append "--with-ncbi-vdb-sources="
6032 (assoc-ref inputs "ncbi-vdb"))
6033 (string-append "--with-ncbi-vdb-build="
6034 (assoc-ref inputs "ncbi-vdb"))
6035 (string-append "--with-ngs-sdk-prefix="
6036 (assoc-ref inputs "ngs-sdk"))
6037 (string-append "--with-hdf5-prefix="
6038 (assoc-ref inputs "hdf5")))
6040 (native-inputs `(("perl" ,perl)))
6042 `(("ngs-sdk" ,ngs-sdk)
6043 ("ncbi-vdb" ,ncbi-vdb)
6048 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6049 (synopsis "Tools and libraries for reading and writing sequencing data")
6051 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6052 reading of sequencing files from the Sequence Read Archive (SRA) database and
6053 writing files into the .sra format.")
6054 (license license:public-domain)))
6056 (define-public seqan
6062 (uri (string-append "https://github.com/seqan/seqan/releases/"
6063 "download/seqan-v" version
6064 "/seqan-library-" version ".tar.xz"))
6067 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6068 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6069 ;; makes sense to split the outputs.
6070 (outputs '("out" "doc"))
6071 (build-system trivial-build-system)
6073 `(#:modules ((guix build utils))
6076 (use-modules (guix build utils))
6077 (let ((tar (assoc-ref %build-inputs "tar"))
6078 (xz (assoc-ref %build-inputs "xz"))
6079 (out (assoc-ref %outputs "out"))
6080 (doc (assoc-ref %outputs "doc")))
6081 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6082 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6083 (chdir (string-append "seqan-library-" ,version))
6084 (copy-recursively "include" (string-append out "/include"))
6085 (copy-recursively "share" (string-append doc "/share"))
6088 `(("source" ,source)
6091 (home-page "http://www.seqan.de")
6092 (synopsis "Library for nucleotide sequence analysis")
6094 "SeqAn is a C++ library of efficient algorithms and data structures for
6095 the analysis of sequences with the focus on biological data. It contains
6096 algorithms and data structures for string representation and their
6097 manipulation, online and indexed string search, efficient I/O of
6098 bioinformatics file formats, sequence alignment, and more.")
6099 (license license:bsd-3)))
6101 (define-public seqan-1
6102 (package (inherit seqan)
6107 (uri (string-append "http://packages.seqan.de/seqan-library/"
6108 "seqan-library-" version ".tar.bz2"))
6111 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6112 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6113 ;; makes sense to split the outputs.
6114 (outputs '("out" "doc"))
6115 (build-system trivial-build-system)
6117 `(#:modules ((guix build utils))
6120 (use-modules (guix build utils))
6121 (let ((tar (assoc-ref %build-inputs "tar"))
6122 (bzip (assoc-ref %build-inputs "bzip2"))
6123 (out (assoc-ref %outputs "out"))
6124 (doc (assoc-ref %outputs "doc")))
6125 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6126 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6127 (chdir (string-append "seqan-library-" ,version))
6128 (copy-recursively "include" (string-append out "/include"))
6129 (copy-recursively "share" (string-append doc "/share"))
6132 `(("source" ,source)
6134 ("bzip2" ,bzip2)))))
6136 (define-public seqmagick
6143 (uri (pypi-uri "seqmagick" version))
6146 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6147 (build-system python-build-system)
6149 `(("python-biopython" ,python-biopython)))
6151 `(("python-nose" ,python-nose)))
6152 (home-page "https://github.com/fhcrc/seqmagick")
6153 (synopsis "Tools for converting and modifying sequence files")
6155 "Bioinformaticians often have to convert sequence files between formats
6156 and do little manipulations on them, and it's not worth writing scripts for
6157 that. Seqmagick is a utility to expose the file format conversion in
6158 BioPython in a convenient way. Instead of having a big mess of scripts, there
6159 is one that takes arguments.")
6160 (license license:gpl3)))
6162 (define-public seqtk
6169 (url "https://github.com/lh3/seqtk.git")
6170 (commit (string-append "v" version))))
6171 (file-name (git-file-name name version))
6174 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6175 (build-system gnu-build-system)
6178 (modify-phases %standard-phases
6181 ;; There are no tests, so we just run a sanity check.
6182 (lambda _ (invoke "./seqtk" "seq") #t))
6184 (lambda* (#:key outputs #:allow-other-keys)
6185 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6186 (install-file "seqtk" bin)
6190 (home-page "https://github.com/lh3/seqtk")
6191 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6193 "Seqtk is a fast and lightweight tool for processing sequences in the
6194 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6195 optionally compressed by gzip.")
6196 (license license:expat)))
6198 (define-public snap-aligner
6200 (name "snap-aligner")
6201 (version "1.0beta.18")
6205 (url "https://github.com/amplab/snap.git")
6206 (commit (string-append "v" version))))
6207 (file-name (git-file-name name version))
6210 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6211 (build-system gnu-build-system)
6214 (modify-phases %standard-phases
6216 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6218 (lambda* (#:key outputs #:allow-other-keys)
6219 (let* ((out (assoc-ref outputs "out"))
6220 (bin (string-append out "/bin")))
6221 (install-file "snap-aligner" bin)
6222 (install-file "SNAPCommand" bin)
6226 (home-page "http://snap.cs.berkeley.edu/")
6227 (synopsis "Short read DNA sequence aligner")
6229 "SNAP is a fast and accurate aligner for short DNA reads. It is
6230 optimized for modern read lengths of 100 bases or higher, and takes advantage
6231 of these reads to align data quickly through a hash-based indexing scheme.")
6232 ;; 32-bit systems are not supported by the unpatched code.
6233 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6234 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6235 ;; systems without a lot of memory cannot make good use of this program.
6236 (supported-systems '("x86_64-linux"))
6237 (license license:asl2.0)))
6239 (define-public sortmerna
6247 (url "https://github.com/biocore/sortmerna.git")
6249 (file-name (git-file-name name version))
6252 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6253 (build-system gnu-build-system)
6254 (outputs '("out" ;for binaries
6255 "db")) ;for sequence databases
6258 (modify-phases %standard-phases
6260 (lambda* (#:key outputs #:allow-other-keys)
6261 (let* ((out (assoc-ref outputs "out"))
6262 (bin (string-append out "/bin"))
6263 (db (assoc-ref outputs "db"))
6265 (string-append db "/share/sortmerna/rRNA_databases")))
6266 (install-file "sortmerna" bin)
6267 (install-file "indexdb_rna" bin)
6268 (for-each (lambda (file)
6269 (install-file file share))
6270 (find-files "rRNA_databases" ".*fasta"))
6274 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6275 (synopsis "Biological sequence analysis tool for NGS reads")
6277 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6278 and operational taxonomic unit (OTU) picking of next generation
6279 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6280 allows for fast and sensitive analyses of nucleotide sequences. The main
6281 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6282 ;; The source includes x86 specific code
6283 (supported-systems '("x86_64-linux" "i686-linux"))
6284 (license license:lgpl3)))
6293 (url "https://github.com/alexdobin/STAR.git")
6295 (file-name (string-append name "-" version "-checkout"))
6298 "0n6g4s4hgw7qygs1z97j7a2dgz8gfaa4cv5pjvvvmarvk0x07hyg"))
6299 (modules '((guix build utils)))
6302 (substitute* "source/Makefile"
6304 ;; Remove pre-built binaries and bundled htslib sources.
6305 (delete-file-recursively "bin/MacOSX_x86_64")
6306 (delete-file-recursively "bin/Linux_x86_64")
6307 (delete-file-recursively "bin/Linux_x86_64_static")
6308 (delete-file-recursively "source/htslib")
6310 (build-system gnu-build-system)
6312 '(#:tests? #f ;no check target
6313 #:make-flags '("STAR")
6315 (modify-phases %standard-phases
6316 (add-after 'unpack 'enter-source-dir
6317 (lambda _ (chdir "source") #t))
6318 (add-after 'enter-source-dir 'make-reproducible
6320 (substitute* "Makefile"
6321 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6322 (string-append pre "Built with Guix" post)))
6324 ;; See https://github.com/alexdobin/STAR/pull/562
6325 (add-after 'enter-source-dir 'add-missing-header
6327 (substitute* "SoloReadFeature_inputRecords.cpp"
6328 (("#include \"binarySearch2.h\"" h)
6329 (string-append h "\n#include <math.h>")))
6331 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6333 (substitute* "Makefile"
6334 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6336 (substitute* '("BAMfunctions.cpp"
6341 "bamRemoveDuplicates.cpp")
6342 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6343 (string-append "#include <" header ">")))
6344 (substitute* "IncludeDefine.h"
6345 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6346 (string-append "<" header ">")))
6349 (lambda* (#:key outputs #:allow-other-keys)
6350 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6351 (install-file "STAR" bin))
6353 (delete 'configure))))
6357 `(("htslib" ,htslib)
6359 (home-page "https://github.com/alexdobin/STAR")
6360 (synopsis "Universal RNA-seq aligner")
6362 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6363 based on a previously undescribed RNA-seq alignment algorithm that uses
6364 sequential maximum mappable seed search in uncompressed suffix arrays followed
6365 by seed clustering and stitching procedure. In addition to unbiased de novo
6366 detection of canonical junctions, STAR can discover non-canonical splices and
6367 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6369 ;; Only 64-bit systems are supported according to the README.
6370 (supported-systems '("x86_64-linux" "mips64el-linux"))
6371 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6372 (license license:gpl3+)))
6374 (define-public starlong
6375 (package (inherit star)
6378 (substitute-keyword-arguments (package-arguments star)
6379 ((#:make-flags flags)
6382 `(modify-phases ,phases
6383 ;; Allow extra long sequence reads.
6384 (add-after 'unpack 'make-extra-long
6386 (substitute* "source/IncludeDefine.h"
6387 (("(#define DEF_readNameLengthMax ).*" _ match)
6388 (string-append match "900000\n")))
6391 (lambda* (#:key outputs #:allow-other-keys)
6392 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6393 (install-file "STARlong" bin))
6396 (define-public subread
6402 (uri (string-append "mirror://sourceforge/subread/subread-"
6403 version "/subread-" version "-source.tar.gz"))
6406 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6407 (build-system gnu-build-system)
6409 `(#:tests? #f ;no "check" target
6410 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6411 ;; optimizations by default, so we override these flags such that x86_64
6412 ;; flags are only added when the build target is an x86_64 system.
6414 (list (let ((system ,(or (%current-target-system)
6416 (flags '("-ggdb" "-fomit-frame-pointer"
6417 "-ffast-math" "-funroll-loops"
6418 "-fmessage-length=0"
6419 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6421 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6422 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6423 (if (string-prefix? "x86_64" system)
6424 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6425 (string-append "CCFLAGS=" (string-join flags))))
6426 "-f" "Makefile.Linux"
6427 "CC=gcc ${CCFLAGS}")
6429 (modify-phases %standard-phases
6430 (add-after 'unpack 'enter-dir
6431 (lambda _ (chdir "src") #t))
6433 (lambda* (#:key outputs #:allow-other-keys)
6434 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6436 (copy-recursively "../bin" bin))
6438 ;; no "configure" script
6439 (delete 'configure))))
6440 (inputs `(("zlib" ,zlib)))
6441 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6442 (synopsis "Tool kit for processing next-gen sequencing data")
6444 "The subread package contains the following tools: subread aligner, a
6445 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6446 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6447 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6448 against local background noises.")
6449 (license license:gpl3+)))
6451 (define-public stringtie
6457 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6458 "stringtie-" version ".tar.gz"))
6461 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6462 (modules '((guix build utils)))
6465 (delete-file-recursively "samtools-0.1.18")
6467 (build-system gnu-build-system)
6469 `(#:tests? #f ;no test suite
6471 (modify-phases %standard-phases
6472 ;; no configure script
6474 (add-before 'build 'use-system-samtools
6476 (substitute* "Makefile"
6477 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6479 (substitute* '("gclib/GBam.h"
6481 (("#include \"(bam|sam|kstring).h\"" _ header)
6482 (string-append "#include <samtools/" header ".h>")))
6484 (add-after 'unpack 'remove-duplicate-typedef
6486 ;; This typedef conflicts with the typedef in
6487 ;; glibc-2.25/include/bits/types.h
6488 (substitute* "gclib/GThreads.h"
6489 (("typedef long long __intmax_t;") ""))
6492 (lambda* (#:key outputs #:allow-other-keys)
6493 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6494 (install-file "stringtie" bin)
6497 `(("samtools" ,samtools-0.1)
6499 (home-page "http://ccb.jhu.edu/software/stringtie/")
6500 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6502 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6503 alignments into potential transcripts. It uses a novel network flow algorithm
6504 as well as an optional de novo assembly step to assemble and quantitate
6505 full-length transcripts representing multiple splice variants for each gene
6506 locus. Its input can include not only the alignments of raw reads used by
6507 other transcript assemblers, but also alignments of longer sequences that have
6508 been assembled from those reads. To identify differentially expressed genes
6509 between experiments, StringTie's output can be processed either by the
6510 Cuffdiff or Ballgown programs.")
6511 (license license:artistic2.0)))
6513 (define-public taxtastic
6519 (uri (pypi-uri "taxtastic" version))
6522 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6523 (build-system python-build-system)
6525 `(#:python ,python-2
6527 (modify-phases %standard-phases
6529 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6531 `(("python-sqlalchemy" ,python2-sqlalchemy)
6532 ("python-decorator" ,python2-decorator)
6533 ("python-biopython" ,python2-biopython)
6534 ("python-pandas" ,python2-pandas)
6535 ("python-psycopg2" ,python2-psycopg2)
6536 ("python-fastalite" ,python2-fastalite)
6537 ("python-pyyaml" ,python2-pyyaml)
6538 ("python-six" ,python2-six)
6539 ("python-jinja2" ,python2-jinja2)
6540 ("python-dendropy" ,python2-dendropy)))
6541 (home-page "https://github.com/fhcrc/taxtastic")
6542 (synopsis "Tools for taxonomic naming and annotation")
6544 "Taxtastic is software written in python used to build and maintain
6545 reference packages i.e. collections of reference trees, reference alignments,
6546 profiles, and associated taxonomic information.")
6547 (license license:gpl3+)))
6549 (define-public vcftools
6556 "https://github.com/vcftools/vcftools/releases/download/v"
6557 version "/vcftools-" version ".tar.gz"))
6560 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6561 (build-system gnu-build-system)
6563 `(#:tests? #f ; no "check" target
6565 "CFLAGS=-O2" ; override "-m64" flag
6566 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6567 (string-append "MANDIR=" (assoc-ref %outputs "out")
6568 "/share/man/man1"))))
6570 `(("pkg-config" ,pkg-config)))
6574 (home-page "https://vcftools.github.io/")
6575 (synopsis "Tools for working with VCF files")
6577 "VCFtools is a program package designed for working with VCF files, such
6578 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6579 provide easily accessible methods for working with complex genetic variation
6580 data in the form of VCF files.")
6581 ;; The license is declared as LGPLv3 in the README and
6582 ;; at https://vcftools.github.io/license.html
6583 (license license:lgpl3)))
6585 (define-public infernal
6591 (uri (string-append "http://eddylab.org/software/infernal/"
6592 "infernal-" version ".tar.gz"))
6595 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6596 (build-system gnu-build-system)
6598 `(("perl" ,perl))) ; for tests
6599 (home-page "http://eddylab.org/infernal/")
6600 (synopsis "Inference of RNA alignments")
6601 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6602 searching DNA sequence databases for RNA structure and sequence similarities.
6603 It is an implementation of a special case of profile stochastic context-free
6604 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6605 profile, but it scores a combination of sequence consensus and RNA secondary
6606 structure consensus, so in many cases, it is more capable of identifying RNA
6607 homologs that conserve their secondary structure more than their primary
6609 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6610 (supported-systems '("i686-linux" "x86_64-linux"))
6611 (license license:bsd-3)))
6613 (define-public r-scde
6620 (url "https://github.com/hms-dbmi/scde.git")
6622 (file-name (git-file-name name version))
6625 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6626 (build-system r-build-system)
6628 `(("r-rcpp" ,r-rcpp)
6629 ("r-rcpparmadillo" ,r-rcpparmadillo)
6632 ("r-rjson" ,r-rjson)
6633 ("r-cairo" ,r-cairo)
6634 ("r-rcolorbrewer" ,r-rcolorbrewer)
6635 ("r-edger" ,r-edger)
6636 ("r-quantreg" ,r-quantreg)
6638 ("r-rmtstat" ,r-rmtstat)
6639 ("r-extremes" ,r-extremes)
6640 ("r-pcamethods" ,r-pcamethods)
6641 ("r-biocparallel" ,r-biocparallel)
6642 ("r-flexmix" ,r-flexmix)))
6643 (home-page "https://hms-dbmi.github.io/scde/")
6644 (synopsis "R package for analyzing single-cell RNA-seq data")
6645 (description "The SCDE package implements a set of statistical methods for
6646 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6647 single-cell RNA-seq measurements. These models can then be used for
6648 assessment of differential expression between groups of cells, as well as
6649 other types of analysis. The SCDE package also contains the pagoda framework
6650 which applies pathway and gene set overdispersion analysis to identify aspects
6651 of transcriptional heterogeneity among single cells.")
6652 ;; See https://github.com/hms-dbmi/scde/issues/38
6653 (license license:gpl2)))
6655 (define-public r-centipede
6657 (name "r-centipede")
6661 (uri (string-append "http://download.r-forge.r-project.org/"
6662 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6665 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6666 (build-system r-build-system)
6667 (home-page "http://centipede.uchicago.edu/")
6668 (synopsis "Predict transcription factor binding sites")
6670 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6671 of the genome that are bound by particular transcription factors. It starts
6672 by identifying a set of candidate binding sites, and then aims to classify the
6673 sites according to whether each site is bound or not bound by a transcription
6674 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6675 between two different types of motif instances using as much relevant
6676 information as possible.")
6677 (license (list license:gpl2+ license:gpl3+))))
6679 (define-public r-genefilter
6681 (name "r-genefilter")
6686 (uri (bioconductor-uri "genefilter" version))
6689 "1jq7lam4dnbvz55lx93kcl9afl8xfjd6xs374d35m21bkay418kj"))))
6690 (build-system r-build-system)
6692 `(("gfortran" ,gfortran)))
6694 `(("r-annotate" ,r-annotate)
6695 ("r-annotationdbi" ,r-annotationdbi)
6696 ("r-biobase" ,r-biobase)
6697 ("r-s4vectors" ,r-s4vectors)
6698 ("r-survival" ,r-survival)))
6699 (home-page "https://bioconductor.org/packages/genefilter")
6700 (synopsis "Filter genes from high-throughput experiments")
6702 "This package provides basic functions for filtering genes from
6703 high-throughput sequencing experiments.")
6704 (license license:artistic2.0)))
6706 (define-public r-deseq2
6713 (uri (bioconductor-uri "DESeq2" version))
6716 "0fkk326addm2cw688gnmdzsmri5qx8j6ldnr4xin6kjnwicqhlqd"))))
6717 (properties `((upstream-name . "DESeq2")))
6718 (build-system r-build-system)
6720 `(("r-biobase" ,r-biobase)
6721 ("r-biocgenerics" ,r-biocgenerics)
6722 ("r-biocparallel" ,r-biocparallel)
6723 ("r-genefilter" ,r-genefilter)
6724 ("r-geneplotter" ,r-geneplotter)
6725 ("r-genomicranges" ,r-genomicranges)
6726 ("r-ggplot2" ,r-ggplot2)
6727 ("r-hmisc" ,r-hmisc)
6728 ("r-iranges" ,r-iranges)
6729 ("r-locfit" ,r-locfit)
6731 ("r-rcpparmadillo" ,r-rcpparmadillo)
6732 ("r-s4vectors" ,r-s4vectors)
6733 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6734 (home-page "https://bioconductor.org/packages/DESeq2")
6735 (synopsis "Differential gene expression analysis")
6737 "This package provides functions to estimate variance-mean dependence in
6738 count data from high-throughput nucleotide sequencing assays and test for
6739 differential expression based on a model using the negative binomial
6741 (license license:lgpl3+)))
6743 (define-public r-dexseq
6750 (uri (bioconductor-uri "DEXSeq" version))
6753 "1b2s0vwm97g0wgm4ms0f4pqkqiqmxscnhg700aybl5vx0m2fa8xm"))))
6754 (properties `((upstream-name . "DEXSeq")))
6755 (build-system r-build-system)
6757 `(("r-annotationdbi" ,r-annotationdbi)
6758 ("r-biobase" ,r-biobase)
6759 ("r-biocgenerics" ,r-biocgenerics)
6760 ("r-biocparallel" ,r-biocparallel)
6761 ("r-biomart" ,r-biomart)
6762 ("r-deseq2" ,r-deseq2)
6763 ("r-genefilter" ,r-genefilter)
6764 ("r-geneplotter" ,r-geneplotter)
6765 ("r-genomicranges" ,r-genomicranges)
6766 ("r-hwriter" ,r-hwriter)
6767 ("r-iranges" ,r-iranges)
6768 ("r-rcolorbrewer" ,r-rcolorbrewer)
6769 ("r-rsamtools" ,r-rsamtools)
6770 ("r-s4vectors" ,r-s4vectors)
6771 ("r-statmod" ,r-statmod)
6772 ("r-stringr" ,r-stringr)
6773 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6774 (home-page "https://bioconductor.org/packages/DEXSeq")
6775 (synopsis "Inference of differential exon usage in RNA-Seq")
6777 "This package is focused on finding differential exon usage using RNA-seq
6778 exon counts between samples with different experimental designs. It provides
6779 functions that allows the user to make the necessary statistical tests based
6780 on a model that uses the negative binomial distribution to estimate the
6781 variance between biological replicates and generalized linear models for
6782 testing. The package also provides functions for the visualization and
6783 exploration of the results.")
6784 (license license:gpl3+)))
6786 (define-public r-annotationforge
6788 (name "r-annotationforge")
6793 (uri (bioconductor-uri "AnnotationForge" version))
6796 "0m4w8n2711wr28znv646cfc7m5jqlr8friz334zdyjmhg7m2xkb7"))))
6798 `((upstream-name . "AnnotationForge")))
6799 (build-system r-build-system)
6801 `(("r-annotationdbi" ,r-annotationdbi)
6802 ("r-biobase" ,r-biobase)
6803 ("r-biocgenerics" ,r-biocgenerics)
6805 ("r-rcurl" ,r-rcurl)
6806 ("r-rsqlite" ,r-rsqlite)
6807 ("r-s4vectors" ,r-s4vectors)
6809 (home-page "https://bioconductor.org/packages/AnnotationForge")
6810 (synopsis "Code for building annotation database packages")
6812 "This package provides code for generating Annotation packages and their
6813 databases. Packages produced are intended to be used with AnnotationDbi.")
6814 (license license:artistic2.0)))
6816 (define-public r-rbgl
6823 (uri (bioconductor-uri "RBGL" version))
6826 "06brn9hl6lybx6hdfp1sycwj6wn1bjfi8xyhpy0v122v1z8d5mbz"))))
6827 (properties `((upstream-name . "RBGL")))
6828 (build-system r-build-system)
6831 ("r-graph" ,r-graph)))
6832 (home-page "https://www.bioconductor.org/packages/RBGL")
6833 (synopsis "Interface to the Boost graph library")
6835 "This package provides a fairly extensive and comprehensive interface to
6836 the graph algorithms contained in the Boost library.")
6837 (license license:artistic2.0)))
6839 (define-public r-gseabase
6846 (uri (bioconductor-uri "GSEABase" version))
6849 "0vh53xk2prjbdkbr3hwfiflx1gh7ilrqs3j1p3lyd6syy3rn9n83"))))
6850 (properties `((upstream-name . "GSEABase")))
6851 (build-system r-build-system)
6853 `(("r-annotate" ,r-annotate)
6854 ("r-annotationdbi" ,r-annotationdbi)
6855 ("r-biobase" ,r-biobase)
6856 ("r-biocgenerics" ,r-biocgenerics)
6857 ("r-graph" ,r-graph)
6859 (home-page "https://bioconductor.org/packages/GSEABase")
6860 (synopsis "Gene set enrichment data structures and methods")
6862 "This package provides classes and methods to support @dfn{Gene Set
6863 Enrichment Analysis} (GSEA).")
6864 (license license:artistic2.0)))
6866 (define-public r-category
6873 (uri (bioconductor-uri "Category" version))
6876 "1n36xfnwn2np5f0lix9abvv9w6jb25jqz3xzvqzklz9s1af4k6x4"))))
6877 (properties `((upstream-name . "Category")))
6878 (build-system r-build-system)
6880 `(("r-annotate" ,r-annotate)
6881 ("r-annotationdbi" ,r-annotationdbi)
6882 ("r-biobase" ,r-biobase)
6883 ("r-biocgenerics" ,r-biocgenerics)
6884 ("r-genefilter" ,r-genefilter)
6885 ("r-graph" ,r-graph)
6886 ("r-gseabase" ,r-gseabase)
6887 ("r-matrix" ,r-matrix)
6890 (home-page "https://bioconductor.org/packages/Category")
6891 (synopsis "Category analysis")
6893 "This package provides a collection of tools for performing category
6895 (license license:artistic2.0)))
6897 (define-public r-gostats
6904 (uri (bioconductor-uri "GOstats" version))
6907 "1a95i6awm2a8xv42fg2z3n29fg9z29i45kd80hxf6mvqqgzj80xp"))))
6908 (properties `((upstream-name . "GOstats")))
6909 (build-system r-build-system)
6911 `(("r-annotate" ,r-annotate)
6912 ("r-annotationdbi" ,r-annotationdbi)
6913 ("r-annotationforge" ,r-annotationforge)
6914 ("r-biobase" ,r-biobase)
6915 ("r-category" ,r-category)
6916 ("r-go-db" ,r-go-db)
6917 ("r-graph" ,r-graph)
6918 ("r-rgraphviz" ,r-rgraphviz)
6919 ("r-rbgl" ,r-rbgl)))
6920 (home-page "https://bioconductor.org/packages/GOstats")
6921 (synopsis "Tools for manipulating GO and microarrays")
6923 "This package provides a set of tools for interacting with GO and
6924 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6925 testing and other simple calculations.")
6926 (license license:artistic2.0)))
6928 (define-public r-shortread
6930 (name "r-shortread")
6935 (uri (bioconductor-uri "ShortRead" version))
6938 "1irqzdgsavjqsq0vva4966qh8qgn7xn9382dmhahm1hxb94qmi59"))))
6939 (properties `((upstream-name . "ShortRead")))
6940 (build-system r-build-system)
6944 `(("r-biobase" ,r-biobase)
6945 ("r-biocgenerics" ,r-biocgenerics)
6946 ("r-biocparallel" ,r-biocparallel)
6947 ("r-biostrings" ,r-biostrings)
6948 ("r-genomeinfodb" ,r-genomeinfodb)
6949 ("r-genomicalignments" ,r-genomicalignments)
6950 ("r-genomicranges" ,r-genomicranges)
6951 ("r-hwriter" ,r-hwriter)
6952 ("r-iranges" ,r-iranges)
6953 ("r-lattice" ,r-lattice)
6954 ("r-latticeextra" ,r-latticeextra)
6955 ("r-rsamtools" ,r-rsamtools)
6956 ("r-s4vectors" ,r-s4vectors)
6957 ("r-xvector" ,r-xvector)
6958 ("r-zlibbioc" ,r-zlibbioc)))
6959 (home-page "https://bioconductor.org/packages/ShortRead")
6960 (synopsis "FASTQ input and manipulation tools")
6962 "This package implements sampling, iteration, and input of FASTQ files.
6963 It includes functions for filtering and trimming reads, and for generating a
6964 quality assessment report. Data are represented as
6965 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6966 purposes. The package also contains legacy support for early single-end,
6967 ungapped alignment formats.")
6968 (license license:artistic2.0)))
6970 (define-public r-systempiper
6972 (name "r-systempiper")
6977 (uri (bioconductor-uri "systemPipeR" version))
6980 "18s5vpmw766pm64w7bwwfgpsv9yzhwclf0ya1rpqz8qslw7bbdjf"))))
6981 (properties `((upstream-name . "systemPipeR")))
6982 (build-system r-build-system)
6984 `(("r-annotate" ,r-annotate)
6985 ("r-batchtools" ,r-batchtools)
6986 ("r-biocgenerics" ,r-biocgenerics)
6987 ("r-biostrings" ,r-biostrings)
6988 ("r-deseq2" ,r-deseq2)
6989 ("r-edger" ,r-edger)
6990 ("r-genomicfeatures" ,r-genomicfeatures)
6991 ("r-genomicranges" ,r-genomicranges)
6992 ("r-ggplot2" ,r-ggplot2)
6993 ("r-go-db" ,r-go-db)
6994 ("r-gostats" ,r-gostats)
6995 ("r-limma" ,r-limma)
6996 ("r-pheatmap" ,r-pheatmap)
6997 ("r-rjson" ,r-rjson)
6998 ("r-rsamtools" ,r-rsamtools)
6999 ("r-shortread" ,r-shortread)
7000 ("r-summarizedexperiment" ,r-summarizedexperiment)
7002 ("r-variantannotation" ,r-variantannotation)))
7003 (home-page "https://github.com/tgirke/systemPipeR")
7004 (synopsis "Next generation sequencing workflow and reporting environment")
7006 "This R package provides tools for building and running automated
7007 end-to-end analysis workflows for a wide range of @dfn{next generation
7008 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7009 Important features include a uniform workflow interface across different NGS
7010 applications, automated report generation, and support for running both R and
7011 command-line software, such as NGS aligners or peak/variant callers, on local
7012 computers or compute clusters. Efficient handling of complex sample sets and
7013 experimental designs is facilitated by a consistently implemented sample
7014 annotation infrastructure.")
7015 (license license:artistic2.0)))
7017 (define-public r-grohmm
7024 (uri (bioconductor-uri "groHMM" version))
7027 "1p368qf8ab1vy8gl2j7rx0l7bvva4m7w06i364rqzs0sdyzlbm3y"))))
7028 (properties `((upstream-name . "groHMM")))
7029 (build-system r-build-system)
7031 `(("r-genomeinfodb" ,r-genomeinfodb)
7032 ("r-genomicalignments" ,r-genomicalignments)
7033 ("r-genomicranges" ,r-genomicranges)
7034 ("r-iranges" ,r-iranges)
7036 ("r-rtracklayer" ,r-rtracklayer)
7037 ("r-s4vectors" ,r-s4vectors)))
7038 (home-page "https://github.com/Kraus-Lab/groHMM")
7039 (synopsis "GRO-seq analysis pipeline")
7041 "This package provides a pipeline for the analysis of GRO-seq data.")
7042 (license license:gpl3+)))
7044 (define-public vsearch
7052 (url "https://github.com/torognes/vsearch.git")
7053 (commit (string-append "v" version))))
7054 (file-name (git-file-name name version))
7057 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7058 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7061 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7062 ;; for this in the patch.
7063 (delete-file "src/city.h")
7064 (delete-file "src/citycrc.h")
7065 (delete-file "src/city.cc")
7067 (build-system gnu-build-system)
7071 ("cityhash" ,cityhash)))
7073 `(("autoconf" ,autoconf)
7074 ("automake" ,automake)))
7075 (synopsis "Sequence search tools for metagenomics")
7077 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7078 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7079 masking. The tool takes advantage of parallelism in the form of SIMD
7080 vectorization as well as multiple threads to perform accurate alignments at
7081 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7082 Needleman-Wunsch).")
7083 (home-page "https://github.com/torognes/vsearch")
7084 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7086 (supported-systems '("x86_64-linux"))
7087 ;; Dual licensed; also includes public domain source.
7088 (license (list license:gpl3 license:bsd-2))))
7090 (define-public pardre
7093 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7098 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7102 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7103 (build-system gnu-build-system)
7105 `(#:tests? #f ; no tests included
7107 (modify-phases %standard-phases
7110 (lambda* (#:key outputs #:allow-other-keys)
7111 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7112 (install-file "ParDRe" bin)
7115 `(("openmpi" ,openmpi)
7117 (synopsis "Parallel tool to remove duplicate DNA reads")
7119 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7120 Duplicate reads can be seen as identical or nearly identical sequences with
7121 some mismatches. This tool lets users avoid the analysis of unnecessary
7122 reads, reducing the time of subsequent procedures with the
7123 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7124 in order to exploit the parallel capabilities of multicore clusters. It is
7125 faster than multithreaded counterparts (end of 2015) for the same number of
7126 cores and, thanks to the message-passing technology, it can be executed on
7128 (home-page "https://sourceforge.net/projects/pardre/")
7129 (license license:gpl3+)))
7131 (define-public ruby-bio-kseq
7133 (name "ruby-bio-kseq")
7138 (uri (rubygems-uri "bio-kseq" version))
7141 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7142 (build-system ruby-build-system)
7144 `(#:test-target "spec"))
7146 `(("bundler" ,bundler)
7147 ("ruby-rspec" ,ruby-rspec)
7148 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7151 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7153 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7154 FASTQ parsing code. It provides a fast iterator over sequences and their
7156 (home-page "https://github.com/gusevfe/bio-kseq")
7157 (license license:expat)))
7159 (define-public bio-locus
7166 (uri (rubygems-uri "bio-locus" version))
7169 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7170 (build-system ruby-build-system)
7172 `(("ruby-rspec" ,ruby-rspec)))
7173 (synopsis "Tool for fast querying of genome locations")
7175 "Bio-locus is a tabix-like tool for fast querying of genome
7176 locations. Many file formats in bioinformatics contain records that
7177 start with a chromosome name and a position for a SNP, or a start-end
7178 position for indels. Bio-locus allows users to store this chr+pos or
7179 chr+pos+alt information in a database.")
7180 (home-page "https://github.com/pjotrp/bio-locus")
7181 (license license:expat)))
7183 (define-public bio-blastxmlparser
7185 (name "bio-blastxmlparser")
7189 (uri (rubygems-uri "bio-blastxmlparser" version))
7192 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7193 (build-system ruby-build-system)
7195 `(("ruby-bio-logger" ,ruby-bio-logger)
7196 ("ruby-nokogiri" ,ruby-nokogiri)))
7198 `(("ruby-rspec" ,ruby-rspec)))
7199 (synopsis "Fast big data BLAST XML parser and library")
7201 "Very fast parallel big-data BLAST XML file parser which can be used as
7202 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7203 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7204 (home-page "https://github.com/pjotrp/blastxmlparser")
7205 (license license:expat)))
7207 (define-public bioruby
7214 (uri (rubygems-uri "bio" version))
7217 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7218 (build-system ruby-build-system)
7220 `(("ruby-libxml" ,ruby-libxml)))
7222 `(("which" ,which))) ; required for test phase
7225 (modify-phases %standard-phases
7226 (add-before 'build 'patch-test-command
7228 (substitute* '("test/functional/bio/test_command.rb")
7229 (("/bin/sh") (which "sh")))
7230 (substitute* '("test/functional/bio/test_command.rb")
7231 (("/bin/ls") (which "ls")))
7232 (substitute* '("test/functional/bio/test_command.rb")
7233 (("which") (which "which")))
7234 (substitute* '("test/functional/bio/test_command.rb",
7235 "test/data/command/echoarg2.sh")
7236 (("/bin/echo") (which "echo")))
7238 (synopsis "Ruby library, shell and utilities for bioinformatics")
7239 (description "BioRuby comes with a comprehensive set of Ruby development
7240 tools and libraries for bioinformatics and molecular biology. BioRuby has
7241 components for sequence analysis, pathway analysis, protein modelling and
7242 phylogenetic analysis; it supports many widely used data formats and provides
7243 easy access to databases, external programs and public web services, including
7244 BLAST, KEGG, GenBank, MEDLINE and GO.")
7245 (home-page "http://bioruby.org/")
7246 ;; Code is released under Ruby license, except for setup
7247 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7248 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7250 (define-public r-biocviews
7252 (name "r-biocviews")
7256 (uri (bioconductor-uri "biocViews" version))
7259 "0qwrsd9fcpkv7hhzy1scnj7ahdxi6cjary28kqk6b36gkzmnrw4r"))))
7261 `((upstream-name . "biocViews")))
7262 (build-system r-build-system)
7264 `(("r-biobase" ,r-biobase)
7265 ("r-biocmanager" ,r-biocmanager)
7266 ("r-graph" ,r-graph)
7268 ("r-rcurl" ,r-rcurl)
7270 ("r-runit" ,r-runit)))
7271 (home-page "https://bioconductor.org/packages/biocViews")
7272 (synopsis "Bioconductor package categorization helper")
7273 (description "The purpose of biocViews is to create HTML pages that
7274 categorize packages in a Bioconductor package repository according to keywords,
7275 also known as views, in a controlled vocabulary.")
7276 (license license:artistic2.0)))
7278 (define-public r-biocstyle
7280 (name "r-biocstyle")
7284 (uri (bioconductor-uri "BiocStyle" version))
7287 "029x8r9rcx6zy0xixdpwxai4jv4ynb161821fzac6z4r8k418398"))))
7289 `((upstream-name . "BiocStyle")))
7290 (build-system r-build-system)
7292 `(("r-biocmanager" ,r-biocmanager)
7293 ("r-bookdown" ,r-bookdown)
7294 ("r-knitr" ,r-knitr)
7295 ("r-rmarkdown" ,r-rmarkdown)
7296 ("r-yaml" ,r-yaml)))
7297 (home-page "https://bioconductor.org/packages/BiocStyle")
7298 (synopsis "Bioconductor formatting styles")
7299 (description "This package provides standard formatting styles for
7300 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7302 (license license:artistic2.0)))
7304 (define-public r-bioccheck
7306 (name "r-bioccheck")
7310 (uri (bioconductor-uri "BiocCheck" version))
7313 "1gkw9s6dhdryga9ap5yhvcqg9jsy4cn417ayqk1qiv6fy91fd124"))))
7315 `((upstream-name . "BiocCheck")))
7316 (build-system r-build-system)
7319 (modify-phases %standard-phases
7320 ;; This package can be used by calling BiocCheck(<package>) from
7321 ;; within R, or by running R CMD BiocCheck <package>. This phase
7322 ;; makes sure the latter works. For this to work, the BiocCheck
7323 ;; script must be somewhere on the PATH (not the R bin directory).
7324 (add-after 'install 'install-bioccheck-subcommand
7325 (lambda* (#:key outputs #:allow-other-keys)
7326 (let* ((out (assoc-ref outputs "out"))
7327 (dest-dir (string-append out "/bin"))
7329 (string-append out "/site-library/BiocCheck/script/")))
7331 (symlink (string-append script-dir "/checkBadDeps.R")
7332 (string-append dest-dir "/checkBadDeps.R"))
7333 (symlink (string-append script-dir "/BiocCheck")
7334 (string-append dest-dir "/BiocCheck")))
7337 `(("r-codetools" ,r-codetools)
7338 ("r-graph" ,r-graph)
7340 ("r-knitr" ,r-knitr)
7341 ("r-optparse" ,r-optparse)
7342 ("r-biocmanager" ,r-biocmanager)
7343 ("r-biocviews" ,r-biocviews)
7344 ("r-stringdist" ,r-stringdist)))
7345 (home-page "https://bioconductor.org/packages/BiocCheck")
7346 (synopsis "Executes Bioconductor-specific package checks")
7347 (description "This package contains tools to perform additional quality
7348 checks on R packages that are to be submitted to the Bioconductor repository.")
7349 (license license:artistic2.0)))
7351 (define-public r-s4vectors
7353 (name "r-s4vectors")
7357 (uri (bioconductor-uri "S4Vectors" version))
7360 "1wkqmpy0d0fab9bjfc7i5wh2zng75pg9rn9c1z1lkki7fpwaw2jb"))))
7362 `((upstream-name . "S4Vectors")))
7363 (build-system r-build-system)
7365 `(("r-biocgenerics" ,r-biocgenerics)))
7366 (home-page "https://bioconductor.org/packages/S4Vectors")
7367 (synopsis "S4 implementation of vectors and lists")
7369 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7370 classes and a set of generic functions that extend the semantic of ordinary
7371 vectors and lists in R. Package developers can easily implement vector-like
7372 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7373 In addition, a few low-level concrete subclasses of general interest (e.g.
7374 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7375 S4Vectors package itself.")
7376 (license license:artistic2.0)))
7378 (define-public r-iranges
7384 (uri (bioconductor-uri "IRanges" version))
7387 "1d64sh43pfc9vj2l7y7x6sb44l67wlnn3dzygp7ws0smn06mardq"))))
7389 `((upstream-name . "IRanges")))
7390 (build-system r-build-system)
7392 `(("r-biocgenerics" ,r-biocgenerics)
7393 ("r-s4vectors" ,r-s4vectors)))
7394 (home-page "https://bioconductor.org/packages/IRanges")
7395 (synopsis "Infrastructure for manipulating intervals on sequences")
7397 "This package provides efficient low-level and highly reusable S4 classes
7398 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7399 generally, data that can be organized sequentially (formally defined as
7400 @code{Vector} objects), as well as views on these @code{Vector} objects.
7401 Efficient list-like classes are also provided for storing big collections of
7402 instances of the basic classes. All classes in the package use consistent
7403 naming and share the same rich and consistent \"Vector API\" as much as
7405 (license license:artistic2.0)))
7407 (define-public r-genomeinfodbdata
7409 (name "r-genomeinfodbdata")
7413 ;; We cannot use bioconductor-uri here because this tarball is
7414 ;; located under "data/annotation/" instead of "bioc/".
7415 (uri (string-append "https://bioconductor.org/packages/release/"
7416 "data/annotation/src/contrib/GenomeInfoDbData_"
7420 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7422 `((upstream-name . "GenomeInfoDbData")))
7423 (build-system r-build-system)
7424 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7425 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7426 (description "This package contains data for mapping between NCBI taxonomy
7427 ID and species. It is used by functions in the GenomeInfoDb package.")
7428 (license license:artistic2.0)))
7430 (define-public r-genomeinfodb
7432 (name "r-genomeinfodb")
7436 (uri (bioconductor-uri "GenomeInfoDb" version))
7439 "0zkhms81b3jz30q7ag81a1mq1rgqg4izyfdvcni68gvn8gm7kdyk"))))
7441 `((upstream-name . "GenomeInfoDb")))
7442 (build-system r-build-system)
7444 `(("r-biocgenerics" ,r-biocgenerics)
7445 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7446 ("r-iranges" ,r-iranges)
7447 ("r-rcurl" ,r-rcurl)
7448 ("r-s4vectors" ,r-s4vectors)))
7449 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7450 (synopsis "Utilities for manipulating chromosome identifiers")
7452 "This package contains data and functions that define and allow
7453 translation between different chromosome sequence naming conventions (e.g.,
7454 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7455 names in their natural, rather than lexicographic, order.")
7456 (license license:artistic2.0)))
7458 (define-public r-edger
7464 (uri (bioconductor-uri "edgeR" version))
7467 "17vadhamjv4x0l4qqq2p2fi6j2bkllz5zd8dq761vgd5ic23zizm"))))
7468 (properties `((upstream-name . "edgeR")))
7469 (build-system r-build-system)
7471 `(("r-limma" ,r-limma)
7472 ("r-locfit" ,r-locfit)
7474 ("r-statmod" ,r-statmod))) ;for estimateDisp
7475 (home-page "http://bioinf.wehi.edu.au/edgeR")
7476 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7477 (description "This package can do differential expression analysis of
7478 RNA-seq expression profiles with biological replication. It implements a range
7479 of statistical methodology based on the negative binomial distributions,
7480 including empirical Bayes estimation, exact tests, generalized linear models
7481 and quasi-likelihood tests. It be applied to differential signal analysis of
7482 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7484 (license license:gpl2+)))
7486 (define-public r-variantannotation
7488 (name "r-variantannotation")
7492 (uri (bioconductor-uri "VariantAnnotation" version))
7495 "144x3d3b9a3q5jy4aqrk1nf2yavwjhwlf71s7qyr4x3ms3wmvf8i"))))
7497 `((upstream-name . "VariantAnnotation")))
7501 `(("r-annotationdbi" ,r-annotationdbi)
7502 ("r-biobase" ,r-biobase)
7503 ("r-biocgenerics" ,r-biocgenerics)
7504 ("r-biostrings" ,r-biostrings)
7505 ("r-bsgenome" ,r-bsgenome)
7507 ("r-genomeinfodb" ,r-genomeinfodb)
7508 ("r-genomicfeatures" ,r-genomicfeatures)
7509 ("r-genomicranges" ,r-genomicranges)
7510 ("r-iranges" ,r-iranges)
7511 ("r-summarizedexperiment" ,r-summarizedexperiment)
7512 ("r-rhtslib" ,r-rhtslib)
7513 ("r-rsamtools" ,r-rsamtools)
7514 ("r-rtracklayer" ,r-rtracklayer)
7515 ("r-s4vectors" ,r-s4vectors)
7516 ("r-xvector" ,r-xvector)
7517 ("r-zlibbioc" ,r-zlibbioc)))
7518 (build-system r-build-system)
7519 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7520 (synopsis "Package for annotation of genetic variants")
7521 (description "This R package can annotate variants, compute amino acid
7522 coding changes and predict coding outcomes.")
7523 (license license:artistic2.0)))
7525 (define-public r-limma
7531 (uri (bioconductor-uri "limma" version))
7534 "166z8cdh6w90rldqqaar7hyaskwiy4smawjfbn4sn58clv6q3mp8"))))
7535 (build-system r-build-system)
7536 (home-page "http://bioinf.wehi.edu.au/limma")
7537 (synopsis "Package for linear models for microarray and RNA-seq data")
7538 (description "This package can be used for the analysis of gene expression
7539 studies, especially the use of linear models for analysing designed experiments
7540 and the assessment of differential expression. The analysis methods apply to
7541 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7542 (license license:gpl2+)))
7544 (define-public r-xvector
7550 (uri (bioconductor-uri "XVector" version))
7553 "12y09pwy86h1za6cmaxs960r7fs0vjzhl0li8jn59vqq9liza1ap"))))
7555 `((upstream-name . "XVector")))
7556 (build-system r-build-system)
7559 (modify-phases %standard-phases
7560 (add-after 'unpack 'use-system-zlib
7562 (substitute* "DESCRIPTION"
7563 (("zlibbioc, ") ""))
7564 (substitute* "NAMESPACE"
7565 (("import\\(zlibbioc\\)") ""))
7570 `(("r-biocgenerics" ,r-biocgenerics)
7571 ("r-iranges" ,r-iranges)
7572 ("r-s4vectors" ,r-s4vectors)))
7573 (home-page "https://bioconductor.org/packages/XVector")
7574 (synopsis "Representation and manpulation of external sequences")
7576 "This package provides memory efficient S4 classes for storing sequences
7577 \"externally\" (behind an R external pointer, or on disk).")
7578 (license license:artistic2.0)))
7580 (define-public r-genomicranges
7582 (name "r-genomicranges")
7586 (uri (bioconductor-uri "GenomicRanges" version))
7589 "1285fr8qjd7d0ixpv7d5imi0n6wzc4k6yia1rkmig71qd2gg556k"))))
7591 `((upstream-name . "GenomicRanges")))
7592 (build-system r-build-system)
7594 `(("r-biocgenerics" ,r-biocgenerics)
7595 ("r-genomeinfodb" ,r-genomeinfodb)
7596 ("r-iranges" ,r-iranges)
7597 ("r-s4vectors" ,r-s4vectors)
7598 ("r-xvector" ,r-xvector)))
7599 (home-page "https://bioconductor.org/packages/GenomicRanges")
7600 (synopsis "Representation and manipulation of genomic intervals")
7602 "This package provides tools to efficiently represent and manipulate
7603 genomic annotations and alignments is playing a central role when it comes to
7604 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7605 GenomicRanges package defines general purpose containers for storing and
7606 manipulating genomic intervals and variables defined along a genome.")
7607 (license license:artistic2.0)))
7609 (define-public r-biobase
7615 (uri (bioconductor-uri "Biobase" version))
7618 "15yl92niqamx3lmwd11zlk0xniibqnh1gi280iadxicmchi83npc"))))
7620 `((upstream-name . "Biobase")))
7621 (build-system r-build-system)
7623 `(("r-biocgenerics" ,r-biocgenerics)))
7624 (home-page "https://bioconductor.org/packages/Biobase")
7625 (synopsis "Base functions for Bioconductor")
7627 "This package provides functions that are needed by many other packages
7628 on Bioconductor or which replace R functions.")
7629 (license license:artistic2.0)))
7631 (define-public r-annotationdbi
7633 (name "r-annotationdbi")
7637 (uri (bioconductor-uri "AnnotationDbi" version))
7640 "0lfq5668a6sq4kqhxx78hl3jcaqdsaaliiybl9xyya2scdk8c29c"))))
7642 `((upstream-name . "AnnotationDbi")))
7643 (build-system r-build-system)
7645 `(("r-biobase" ,r-biobase)
7646 ("r-biocgenerics" ,r-biocgenerics)
7648 ("r-iranges" ,r-iranges)
7649 ("r-rsqlite" ,r-rsqlite)
7650 ("r-s4vectors" ,r-s4vectors)))
7651 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7652 (synopsis "Annotation database interface")
7654 "This package provides user interface and database connection code for
7655 annotation data packages using SQLite data storage.")
7656 (license license:artistic2.0)))
7658 (define-public r-biomart
7664 (uri (bioconductor-uri "biomaRt" version))
7667 "022m1r44s00c5k9bmv0lr22lcn662nhc91aazvv0yyysxjamyf60"))))
7669 `((upstream-name . "biomaRt")))
7670 (build-system r-build-system)
7672 `(("r-annotationdbi" ,r-annotationdbi)
7674 ("r-progress" ,r-progress)
7675 ("r-rcurl" ,r-rcurl)
7676 ("r-stringr" ,r-stringr)
7678 (home-page "https://bioconductor.org/packages/biomaRt")
7679 (synopsis "Interface to BioMart databases")
7681 "biomaRt provides an interface to a growing collection of databases
7682 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7683 package enables retrieval of large amounts of data in a uniform way without
7684 the need to know the underlying database schemas or write complex SQL queries.
7685 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7686 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7687 users direct access to a diverse set of data and enable a wide range of
7688 powerful online queries from gene annotation to database mining.")
7689 (license license:artistic2.0)))
7691 (define-public r-biocparallel
7693 (name "r-biocparallel")
7697 (uri (bioconductor-uri "BiocParallel" version))
7700 "0v8rhf3hbgb3v32h2pmsv1y6q2x4airmpp50fk7z6ardcn4aza7x"))))
7702 `((upstream-name . "BiocParallel")))
7703 (build-system r-build-system)
7705 `(("r-futile-logger" ,r-futile-logger)
7708 (home-page "https://bioconductor.org/packages/BiocParallel")
7709 (synopsis "Bioconductor facilities for parallel evaluation")
7711 "This package provides modified versions and novel implementation of
7712 functions for parallel evaluation, tailored to use with Bioconductor
7714 (license (list license:gpl2+ license:gpl3+))))
7716 (define-public r-biostrings
7718 (name "r-biostrings")
7722 (uri (bioconductor-uri "Biostrings" version))
7725 "0inrl97hli3qz6cfxcikc4picmbrqc8phdgqi18ynlvxy5ql64h4"))))
7727 `((upstream-name . "Biostrings")))
7728 (build-system r-build-system)
7730 `(("r-biocgenerics" ,r-biocgenerics)
7731 ("r-iranges" ,r-iranges)
7732 ("r-s4vectors" ,r-s4vectors)
7733 ("r-xvector" ,r-xvector)))
7734 (home-page "https://bioconductor.org/packages/Biostrings")
7735 (synopsis "String objects and algorithms for biological sequences")
7737 "This package provides memory efficient string containers, string
7738 matching algorithms, and other utilities, for fast manipulation of large
7739 biological sequences or sets of sequences.")
7740 (license license:artistic2.0)))
7742 (define-public r-rsamtools
7744 (name "r-rsamtools")
7748 (uri (bioconductor-uri "Rsamtools" version))
7751 "1nv5idyjk75mvl4np5sig0xa6qygm1ivj33k041ffyj19q8jf7ij"))))
7753 `((upstream-name . "Rsamtools")))
7754 (build-system r-build-system)
7757 (modify-phases %standard-phases
7758 (add-after 'unpack 'use-system-zlib
7760 (substitute* "DESCRIPTION"
7761 (("zlibbioc, ") ""))
7762 (substitute* "NAMESPACE"
7763 (("import\\(zlibbioc\\)") ""))
7768 `(("r-biocgenerics" ,r-biocgenerics)
7769 ("r-biocparallel" ,r-biocparallel)
7770 ("r-biostrings" ,r-biostrings)
7771 ("r-bitops" ,r-bitops)
7772 ("r-genomeinfodb" ,r-genomeinfodb)
7773 ("r-genomicranges" ,r-genomicranges)
7774 ("r-iranges" ,r-iranges)
7775 ("r-rhtslib" ,r-rhtslib)
7776 ("r-s4vectors" ,r-s4vectors)
7777 ("r-xvector" ,r-xvector)))
7778 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7779 (synopsis "Interface to samtools, bcftools, and tabix")
7781 "This package provides an interface to the @code{samtools},
7782 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7783 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7784 tab-delimited (tabix) files.")
7785 (license license:expat)))
7787 (define-public r-delayedarray
7789 (name "r-delayedarray")
7793 (uri (bioconductor-uri "DelayedArray" version))
7796 "0l907ggxndn3f29zvsd5pppmp4c31rb22r6zkhvgph7xdxahyy6z"))))
7798 `((upstream-name . "DelayedArray")))
7799 (build-system r-build-system)
7801 `(("r-biocgenerics" ,r-biocgenerics)
7802 ("r-biocparallel" ,r-biocparallel)
7803 ("r-s4vectors" ,r-s4vectors)
7804 ("r-iranges" ,r-iranges)
7805 ("r-matrix" ,r-matrix)
7806 ("r-matrixstats" ,r-matrixstats)))
7807 (home-page "https://bioconductor.org/packages/DelayedArray")
7808 (synopsis "Delayed operations on array-like objects")
7810 "Wrapping an array-like object (typically an on-disk object) in a
7811 @code{DelayedArray} object allows one to perform common array operations on it
7812 without loading the object in memory. In order to reduce memory usage and
7813 optimize performance, operations on the object are either delayed or executed
7814 using a block processing mechanism. Note that this also works on in-memory
7815 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7816 @code{Matrix} objects, and ordinary arrays and data frames.")
7817 (license license:artistic2.0)))
7819 (define-public r-summarizedexperiment
7821 (name "r-summarizedexperiment")
7825 (uri (bioconductor-uri "SummarizedExperiment" version))
7828 "0bhwgzrdipr0qjzc4j0qspqprx3v1rvshmx4j6506dv43pqlgp3f"))))
7830 `((upstream-name . "SummarizedExperiment")))
7831 (build-system r-build-system)
7833 `(("r-biobase" ,r-biobase)
7834 ("r-biocgenerics" ,r-biocgenerics)
7835 ("r-delayedarray" ,r-delayedarray)
7836 ("r-genomeinfodb" ,r-genomeinfodb)
7837 ("r-genomicranges" ,r-genomicranges)
7838 ("r-iranges" ,r-iranges)
7839 ("r-matrix" ,r-matrix)
7840 ("r-s4vectors" ,r-s4vectors)))
7841 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7842 (synopsis "Container for representing genomic ranges by sample")
7844 "The SummarizedExperiment container contains one or more assays, each
7845 represented by a matrix-like object of numeric or other mode. The rows
7846 typically represent genomic ranges of interest and the columns represent
7848 (license license:artistic2.0)))
7850 (define-public r-genomicalignments
7852 (name "r-genomicalignments")
7856 (uri (bioconductor-uri "GenomicAlignments" version))
7859 "0s3q97q4pgj5jwn4g95al44rahrwsncsf45v01v4071msx3xmjxq"))))
7861 `((upstream-name . "GenomicAlignments")))
7862 (build-system r-build-system)
7864 `(("r-biocgenerics" ,r-biocgenerics)
7865 ("r-biocparallel" ,r-biocparallel)
7866 ("r-biostrings" ,r-biostrings)
7867 ("r-genomeinfodb" ,r-genomeinfodb)
7868 ("r-genomicranges" ,r-genomicranges)
7869 ("r-iranges" ,r-iranges)
7870 ("r-rsamtools" ,r-rsamtools)
7871 ("r-s4vectors" ,r-s4vectors)
7872 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7873 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7874 (synopsis "Representation and manipulation of short genomic alignments")
7876 "This package provides efficient containers for storing and manipulating
7877 short genomic alignments (typically obtained by aligning short reads to a
7878 reference genome). This includes read counting, computing the coverage,
7879 junction detection, and working with the nucleotide content of the
7881 (license license:artistic2.0)))
7883 (define-public r-rtracklayer
7885 (name "r-rtracklayer")
7889 (uri (bioconductor-uri "rtracklayer" version))
7892 "03b4rfsbzjjf5kxcsjv7kq8hrsgcvz9rfzcn2v7fx3nr818pbb8s"))))
7893 (build-system r-build-system)
7896 (modify-phases %standard-phases
7897 (add-after 'unpack 'use-system-zlib
7899 (substitute* "DESCRIPTION"
7900 ((" zlibbioc,") ""))
7901 (substitute* "NAMESPACE"
7902 (("import\\(zlibbioc\\)") ""))
7905 `(("pkg-config" ,pkg-config)))
7909 `(("r-biocgenerics" ,r-biocgenerics)
7910 ("r-biostrings" ,r-biostrings)
7911 ("r-genomeinfodb" ,r-genomeinfodb)
7912 ("r-genomicalignments" ,r-genomicalignments)
7913 ("r-genomicranges" ,r-genomicranges)
7914 ("r-iranges" ,r-iranges)
7915 ("r-rcurl" ,r-rcurl)
7916 ("r-rsamtools" ,r-rsamtools)
7917 ("r-s4vectors" ,r-s4vectors)
7919 ("r-xvector" ,r-xvector)))
7920 (home-page "https://bioconductor.org/packages/rtracklayer")
7921 (synopsis "R interface to genome browsers and their annotation tracks")
7923 "rtracklayer is an extensible framework for interacting with multiple
7924 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7925 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7926 built-in). The user may export/import tracks to/from the supported browsers,
7927 as well as query and modify the browser state, such as the current viewport.")
7928 (license license:artistic2.0)))
7930 (define-public r-genomicfeatures
7932 (name "r-genomicfeatures")
7936 (uri (bioconductor-uri "GenomicFeatures" version))
7939 "0zkd57i5qjxsravv0gbyckc0wrnqzgxd61ibh3jmhmrccrr9ihn3"))))
7941 `((upstream-name . "GenomicFeatures")))
7942 (build-system r-build-system)
7944 `(("r-annotationdbi" ,r-annotationdbi)
7945 ("r-biobase" ,r-biobase)
7946 ("r-biocgenerics" ,r-biocgenerics)
7947 ("r-biomart" ,r-biomart)
7948 ("r-biostrings" ,r-biostrings)
7950 ("r-genomeinfodb" ,r-genomeinfodb)
7951 ("r-genomicranges" ,r-genomicranges)
7952 ("r-iranges" ,r-iranges)
7953 ("r-rcurl" ,r-rcurl)
7954 ("r-rsqlite" ,r-rsqlite)
7955 ("r-rtracklayer" ,r-rtracklayer)
7956 ("r-s4vectors" ,r-s4vectors)
7957 ("r-xvector" ,r-xvector)))
7958 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7959 (synopsis "Tools for working with transcript centric annotations")
7961 "This package provides a set of tools and methods for making and
7962 manipulating transcript centric annotations. With these tools the user can
7963 easily download the genomic locations of the transcripts, exons and cds of a
7964 given organism, from either the UCSC Genome Browser or a BioMart
7965 database (more sources will be supported in the future). This information is
7966 then stored in a local database that keeps track of the relationship between
7967 transcripts, exons, cds and genes. Flexible methods are provided for
7968 extracting the desired features in a convenient format.")
7969 (license license:artistic2.0)))
7971 (define-public r-go-db
7977 (uri (string-append "https://www.bioconductor.org/packages/"
7978 "release/data/annotation/src/contrib/GO.db_"
7982 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7984 `((upstream-name . "GO.db")))
7985 (build-system r-build-system)
7987 `(("r-annotationdbi" ,r-annotationdbi)))
7988 (home-page "https://bioconductor.org/packages/GO.db")
7989 (synopsis "Annotation maps describing the entire Gene Ontology")
7991 "The purpose of this GO.db annotation package is to provide detailed
7992 information about the latest version of the Gene Ontologies.")
7993 (license license:artistic2.0)))
7995 (define-public r-topgo
8001 (uri (bioconductor-uri "topGO" version))
8004 "09z42jwz5vh289ijz3x68zv5vmgkgcbhlp73vvmna1gld5lh5kz1"))))
8006 `((upstream-name . "topGO")))
8007 (build-system r-build-system)
8009 `(("r-annotationdbi" ,r-annotationdbi)
8011 ("r-biobase" ,r-biobase)
8012 ("r-biocgenerics" ,r-biocgenerics)
8013 ("r-go-db" ,r-go-db)
8014 ("r-graph" ,r-graph)
8015 ("r-lattice" ,r-lattice)
8016 ("r-matrixstats" ,r-matrixstats)
8017 ("r-sparsem" ,r-sparsem)))
8018 (home-page "https://bioconductor.org/packages/topGO")
8019 (synopsis "Enrichment analysis for gene ontology")
8021 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8022 terms while accounting for the topology of the GO graph. Different test
8023 statistics and different methods for eliminating local similarities and
8024 dependencies between GO terms can be implemented and applied.")
8025 ;; Any version of the LGPL applies.
8026 (license license:lgpl2.1+)))
8028 (define-public r-bsgenome
8034 (uri (bioconductor-uri "BSgenome" version))
8037 "0zwx42s73hc1vhn0v82i67mcixdwwc6n6q5h5vpnhpxlm4qwgqzp"))))
8039 `((upstream-name . "BSgenome")))
8040 (build-system r-build-system)
8042 `(("r-biocgenerics" ,r-biocgenerics)
8043 ("r-biostrings" ,r-biostrings)
8044 ("r-genomeinfodb" ,r-genomeinfodb)
8045 ("r-genomicranges" ,r-genomicranges)
8046 ("r-iranges" ,r-iranges)
8047 ("r-rsamtools" ,r-rsamtools)
8048 ("r-rtracklayer" ,r-rtracklayer)
8049 ("r-s4vectors" ,r-s4vectors)
8050 ("r-xvector" ,r-xvector)))
8051 (home-page "https://bioconductor.org/packages/BSgenome")
8052 (synopsis "Infrastructure for Biostrings-based genome data packages")
8054 "This package provides infrastructure shared by all Biostrings-based
8055 genome data packages and support for efficient SNP representation.")
8056 (license license:artistic2.0)))
8058 (define-public r-impute
8064 (uri (bioconductor-uri "impute" version))
8067 "144jb889979cv3il2zxqk724v3sj1wnzjm3lkspxcvk29dbb9q8j"))))
8069 `(("gfortran" ,gfortran)))
8070 (build-system r-build-system)
8071 (home-page "https://bioconductor.org/packages/impute")
8072 (synopsis "Imputation for microarray data")
8074 "This package provides a function to impute missing gene expression
8075 microarray data, using nearest neighbor averaging.")
8076 (license license:gpl2+)))
8078 (define-public r-seqpattern
8080 (name "r-seqpattern")
8084 (uri (bioconductor-uri "seqPattern" version))
8087 "1ljqscbmrmi5d4lzzvg2d86sqzch26yxw57d33qyid300wm60db2"))))
8089 `((upstream-name . "seqPattern")))
8090 (build-system r-build-system)
8092 `(("r-biostrings" ,r-biostrings)
8093 ("r-genomicranges" ,r-genomicranges)
8094 ("r-iranges" ,r-iranges)
8095 ("r-kernsmooth" ,r-kernsmooth)
8096 ("r-plotrix" ,r-plotrix)))
8097 (home-page "https://bioconductor.org/packages/seqPattern")
8098 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8100 "This package provides tools to visualize oligonucleotide patterns and
8101 sequence motif occurrences across a large set of sequences centred at a common
8102 reference point and sorted by a user defined feature.")
8103 (license license:gpl3+)))
8105 (define-public r-genomation
8107 (name "r-genomation")
8111 (uri (bioconductor-uri "genomation" version))
8114 "06i711pwq9znd7plh0p25skxnnh5dyl61c33k9gma243wvlzmlkj"))))
8115 (build-system r-build-system)
8117 `(("r-biostrings" ,r-biostrings)
8118 ("r-bsgenome" ,r-bsgenome)
8119 ("r-data-table" ,r-data-table)
8120 ("r-genomeinfodb" ,r-genomeinfodb)
8121 ("r-genomicalignments" ,r-genomicalignments)
8122 ("r-genomicranges" ,r-genomicranges)
8123 ("r-ggplot2" ,r-ggplot2)
8124 ("r-gridbase" ,r-gridbase)
8125 ("r-impute" ,r-impute)
8126 ("r-iranges" ,r-iranges)
8127 ("r-matrixstats" ,r-matrixstats)
8128 ("r-plotrix" ,r-plotrix)
8131 ("r-readr" ,r-readr)
8132 ("r-reshape2" ,r-reshape2)
8133 ("r-rsamtools" ,r-rsamtools)
8134 ("r-rtracklayer" ,r-rtracklayer)
8135 ("r-runit" ,r-runit)
8136 ("r-s4vectors" ,r-s4vectors)
8137 ("r-seqpattern" ,r-seqpattern)))
8138 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8139 (synopsis "Summary, annotation and visualization of genomic data")
8141 "This package provides a package for summary and annotation of genomic
8142 intervals. Users can visualize and quantify genomic intervals over
8143 pre-defined functional regions, such as promoters, exons, introns, etc. The
8144 genomic intervals represent regions with a defined chromosome position, which
8145 may be associated with a score, such as aligned reads from HT-seq experiments,
8146 TF binding sites, methylation scores, etc. The package can use any tabular
8147 genomic feature data as long as it has minimal information on the locations of
8148 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8149 (license license:artistic2.0)))
8151 (define-public r-genomationdata
8153 (name "r-genomationdata")
8157 ;; We cannot use bioconductor-uri here because this tarball is
8158 ;; located under "data/annotation/" instead of "bioc/".
8159 (uri (string-append "https://bioconductor.org/packages/"
8160 "release/data/experiment/src/contrib/"
8161 "genomationData_" version ".tar.gz"))
8164 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8165 (build-system r-build-system)
8166 ;; As this package provides little more than large data files, it doesn't
8167 ;; make sense to build substitutes.
8168 (arguments `(#:substitutable? #f))
8170 `(("r-knitr" ,r-knitr)))
8171 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8172 (synopsis "Experimental data for use with the genomation package")
8174 "This package contains experimental genetic data for use with the
8175 genomation package. Included are Chip Seq, Methylation and Cage data,
8176 downloaded from Encode.")
8177 (license license:gpl3+)))
8179 (define-public r-seqlogo
8186 (uri (bioconductor-uri "seqLogo" version))
8189 "1z63imr1a24nqijpvxaxlakykcsadfqyxl2b3vlllncxnjjvb52b"))))
8190 (properties `((upstream-name . "seqLogo")))
8191 (build-system r-build-system)
8192 (home-page "https://bioconductor.org/packages/seqLogo")
8193 (synopsis "Sequence logos for DNA sequence alignments")
8195 "seqLogo takes the position weight matrix of a DNA sequence motif and
8196 plots the corresponding sequence logo as introduced by Schneider and
8198 (license license:lgpl2.0+)))
8200 (define-public r-motifrg
8207 (uri (bioconductor-uri "motifRG" version))
8210 "02c7fbjwdq7pk96bd2rn07l9r2hqy00s3hfpli5ybmwgvc9h9z4z"))))
8211 (properties `((upstream-name . "motifRG")))
8212 (build-system r-build-system)
8214 `(("r-biostrings" ,r-biostrings)
8215 ("r-bsgenome" ,r-bsgenome)
8216 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8217 ("r-iranges" ,r-iranges)
8218 ("r-seqlogo" ,r-seqlogo)
8219 ("r-xvector" ,r-xvector)))
8220 (home-page "https://bioconductor.org/packages/motifRG")
8221 (synopsis "Discover motifs in high throughput sequencing data")
8223 "This package provides tools for discriminative motif discovery in high
8224 throughput genetic sequencing data sets using regression methods.")
8225 (license license:artistic2.0)))
8227 (define-public r-qtl
8234 (uri (string-append "mirror://cran/src/contrib/qtl_"
8238 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8239 (build-system r-build-system)
8240 (home-page "http://rqtl.org/")
8241 (synopsis "R package for analyzing QTL experiments in genetics")
8242 (description "R/qtl is an extension library for the R statistics
8243 system. It is used to analyze experimental crosses for identifying
8244 genes contributing to variation in quantitative traits (so-called
8245 quantitative trait loci, QTLs).
8247 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8248 identify genotyping errors, and to perform single-QTL and two-QTL,
8249 two-dimensional genome scans.")
8250 (license license:gpl3)))
8252 (define-public r-zlibbioc
8258 (uri (bioconductor-uri "zlibbioc" version))
8261 "1h0a2ps2rfk9azzps7p23sxj5z1giv8gcx0ypzgyz7fkr4xi9z7k"))))
8263 `((upstream-name . "zlibbioc")))
8264 (build-system r-build-system)
8265 (home-page "https://bioconductor.org/packages/zlibbioc")
8266 (synopsis "Provider for zlib-1.2.5 to R packages")
8267 (description "This package uses the source code of zlib-1.2.5 to create
8268 libraries for systems that do not have these available via other means.")
8269 (license license:artistic2.0)))
8271 (define-public r-r4rna
8278 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8282 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8283 (build-system r-build-system)
8285 `(("r-optparse" ,r-optparse)
8286 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8287 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8288 (synopsis "Analysis framework for RNA secondary structure")
8290 "The R4RNA package aims to be a general framework for the analysis of RNA
8291 secondary structure and comparative analysis in R.")
8292 (license license:gpl3+)))
8294 (define-public r-rhtslib
8301 (uri (bioconductor-uri "Rhtslib" version))
8304 "178zbrm221rwhbjk7j2v9g5ra44k0xg7c5abhd810m3g7snma8k8"))))
8305 (properties `((upstream-name . "Rhtslib")))
8306 (build-system r-build-system)
8307 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8308 ;; which makes R abort the build.
8309 (arguments '(#:configure-flags '("--no-staged-install")))
8311 `(("r-zlibbioc" ,r-zlibbioc)))
8315 `(("pkg-config" ,pkg-config)))
8316 (home-page "https://github.com/nhayden/Rhtslib")
8317 (synopsis "High-throughput sequencing library as an R package")
8319 "This package provides the HTSlib C library for high-throughput
8320 nucleotide sequence analysis. The package is primarily useful to developers
8321 of other R packages who wish to make use of HTSlib.")
8322 (license license:lgpl2.0+)))
8324 (define-public r-bamsignals
8326 (name "r-bamsignals")
8331 (uri (bioconductor-uri "bamsignals" version))
8334 "15q1q51dwl9qxfkf10yppw4m194ba03nq9plsrbj8fqj00v4729i"))))
8335 (build-system r-build-system)
8337 `(("r-biocgenerics" ,r-biocgenerics)
8338 ("r-genomicranges" ,r-genomicranges)
8339 ("r-iranges" ,r-iranges)
8341 ("r-rhtslib" ,r-rhtslib)
8342 ("r-zlibbioc" ,r-zlibbioc)))
8345 (home-page "https://bioconductor.org/packages/bamsignals")
8346 (synopsis "Extract read count signals from bam files")
8348 "This package allows to efficiently obtain count vectors from indexed bam
8349 files. It counts the number of nucleotide sequence reads in given genomic
8350 ranges and it computes reads profiles and coverage profiles. It also handles
8352 (license license:gpl2+)))
8354 (define-public r-rcas
8360 (uri (bioconductor-uri "RCAS" version))
8363 "1h4vf5gzilqbdrd8m9l3zc2m4sca8cir8366a7njgd558k7ld5kl"))))
8364 (properties `((upstream-name . "RCAS")))
8365 (build-system r-build-system)
8367 `(("r-annotationdbi" ,r-annotationdbi)
8368 ("r-biocgenerics" ,r-biocgenerics)
8369 ("r-biomart" ,r-biomart)
8370 ("r-biostrings" ,r-biostrings)
8371 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8372 ("r-cowplot" ,r-cowplot)
8373 ("r-data-table" ,r-data-table)
8376 ("r-genomation" ,r-genomation)
8377 ("r-genomeinfodb" ,r-genomeinfodb)
8378 ("r-genomicfeatures" ,r-genomicfeatures)
8379 ("r-genomicranges" ,r-genomicranges)
8380 ("r-ggplot2" ,r-ggplot2)
8381 ("r-ggseqlogo" ,r-ggseqlogo)
8382 ("r-knitr" ,r-knitr)
8383 ("r-motifrg" ,r-motifrg)
8384 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8385 ("r-pbapply" ,r-pbapply)
8386 ("r-pheatmap" ,r-pheatmap)
8387 ("r-plotly" ,r-plotly)
8388 ("r-plotrix" ,r-plotrix)
8389 ("r-proxy" ,r-proxy)
8390 ("r-rsqlite" ,r-rsqlite)
8391 ("r-rtracklayer" ,r-rtracklayer)
8392 ("r-rmarkdown" ,r-rmarkdown)
8393 ("r-s4vectors" ,r-s4vectors)
8394 ("r-topgo" ,r-topgo)
8395 ("pandoc" ,ghc-pandoc)))
8396 (synopsis "RNA-centric annotation system")
8398 "RCAS aims to be a standalone RNA-centric annotation system that provides
8399 intuitive reports and publication-ready graphics. This package provides the R
8400 library implementing most of the pipeline's features.")
8401 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8402 (license license:artistic2.0)))
8404 (define-public rcas-web
8411 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8412 "releases/download/v" version
8413 "/rcas-web-" version ".tar.gz"))
8416 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8417 (build-system gnu-build-system)
8420 (modify-phases %standard-phases
8421 (add-after 'install 'wrap-executable
8422 (lambda* (#:key inputs outputs #:allow-other-keys)
8423 (let* ((out (assoc-ref outputs "out"))
8424 (json (assoc-ref inputs "guile-json"))
8425 (redis (assoc-ref inputs "guile-redis"))
8426 (path (string-append
8427 json "/share/guile/site/2.2:"
8428 redis "/share/guile/site/2.2")))
8429 (wrap-program (string-append out "/bin/rcas-web")
8430 `("GUILE_LOAD_PATH" ":" = (,path))
8431 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8432 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8435 `(("r-minimal" ,r-minimal)
8437 ("guile-next" ,guile-2.2)
8438 ("guile-json" ,guile-json-1)
8439 ("guile-redis" ,guile-redis)))
8441 `(("pkg-config" ,pkg-config)))
8442 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8443 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8444 (description "This package provides a simple web interface for the
8445 @dfn{RNA-centric annotation system} (RCAS).")
8446 (license license:agpl3+)))
8448 (define-public r-mutationalpatterns
8450 (name "r-mutationalpatterns")
8455 (uri (bioconductor-uri "MutationalPatterns" version))
8458 "1k3r06xj1nim1s8as1i7fykfa6fbb4x456kslbzdvbf83ppx34z3"))))
8459 (build-system r-build-system)
8461 `(("r-biocgenerics" ,r-biocgenerics)
8462 ("r-biostrings" ,r-biostrings)
8463 ;; These two packages are suggested packages
8464 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8465 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8466 ("r-genomicranges" ,r-genomicranges)
8467 ("r-genomeinfodb" ,r-genomeinfodb)
8468 ("r-ggplot2" ,r-ggplot2)
8469 ("r-iranges" ,r-iranges)
8472 ("r-pracma" ,r-pracma)
8473 ("r-reshape2" ,r-reshape2)
8474 ("r-cowplot" ,r-cowplot)
8475 ("r-ggdendro" ,r-ggdendro)
8476 ("r-s4vectors" ,r-s4vectors)
8477 ("r-summarizedexperiment" ,r-summarizedexperiment)
8478 ("r-variantannotation" ,r-variantannotation)))
8479 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8480 (synopsis "Extract and visualize mutational patterns in genomic data")
8481 (description "This package provides an extensive toolset for the
8482 characterization and visualization of a wide range of mutational patterns
8483 in SNV base substitution data.")
8484 (license license:expat)))
8486 (define-public r-chipkernels
8487 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8490 (name "r-chipkernels")
8491 (version (string-append "1.1-" revision "." (string-take commit 9)))
8496 (url "https://github.com/ManuSetty/ChIPKernels.git")
8498 (file-name (string-append name "-" version))
8501 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8502 (build-system r-build-system)
8504 `(("r-iranges" ,r-iranges)
8505 ("r-xvector" ,r-xvector)
8506 ("r-biostrings" ,r-biostrings)
8507 ("r-bsgenome" ,r-bsgenome)
8508 ("r-gtools" ,r-gtools)
8509 ("r-genomicranges" ,r-genomicranges)
8510 ("r-sfsmisc" ,r-sfsmisc)
8511 ("r-kernlab" ,r-kernlab)
8512 ("r-s4vectors" ,r-s4vectors)
8513 ("r-biocgenerics" ,r-biocgenerics)))
8514 (home-page "https://github.com/ManuSetty/ChIPKernels")
8515 (synopsis "Build string kernels for DNA Sequence analysis")
8516 (description "ChIPKernels is an R package for building different string
8517 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8518 must be built and this dictionary can be used for determining kernels for DNA
8520 (license license:gpl2+))))
8522 (define-public r-seqgl
8530 (url "https://github.com/ManuSetty/SeqGL.git")
8532 (file-name (git-file-name name version))
8535 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8536 (build-system r-build-system)
8538 `(("r-biostrings" ,r-biostrings)
8539 ("r-chipkernels" ,r-chipkernels)
8540 ("r-genomicranges" ,r-genomicranges)
8541 ("r-spams" ,r-spams)
8542 ("r-wgcna" ,r-wgcna)
8543 ("r-fastcluster" ,r-fastcluster)))
8544 (home-page "https://github.com/ManuSetty/SeqGL")
8545 (synopsis "Group lasso for Dnase/ChIP-seq data")
8546 (description "SeqGL is a group lasso based algorithm to extract
8547 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8548 This package presents a method which uses group lasso to discriminate between
8549 bound and non bound genomic regions to accurately identify transcription
8550 factors bound at the specific regions.")
8551 (license license:gpl2+)))
8553 (define-public r-tximport
8559 (uri (bioconductor-uri "tximport" version))
8562 "070nx0blvvfhsnkbb5j899wy7dgalrh4xfcciir9l2xl67lna1zf"))))
8563 (build-system r-build-system)
8564 (home-page "https://bioconductor.org/packages/tximport")
8565 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8567 "This package provides tools to import transcript-level abundance,
8568 estimated counts and transcript lengths, and to summarize them into matrices
8569 for use with downstream gene-level analysis packages. Average transcript
8570 length, weighted by sample-specific transcript abundance estimates, is
8571 provided as a matrix which can be used as an offset for different expression
8572 of gene-level counts.")
8573 (license license:gpl2+)))
8575 (define-public r-rhdf5
8581 (uri (bioconductor-uri "rhdf5" version))
8584 "0y1w3cs7wg2b3jlkd6wyyz6626xg011nrg36si8gg371iqck9a1i"))))
8585 (build-system r-build-system)
8587 `(("r-rhdf5lib" ,r-rhdf5lib)))
8590 (home-page "https://bioconductor.org/packages/rhdf5")
8591 (synopsis "HDF5 interface to R")
8593 "This R/Bioconductor package provides an interface between HDF5 and R.
8594 HDF5's main features are the ability to store and access very large and/or
8595 complex datasets and a wide variety of metadata on mass storage (disk) through
8596 a completely portable file format. The rhdf5 package is thus suited for the
8597 exchange of large and/or complex datasets between R and other software
8598 package, and for letting R applications work on datasets that are larger than
8599 the available RAM.")
8600 (license license:artistic2.0)))
8602 (define-public r-annotationfilter
8604 (name "r-annotationfilter")
8608 (uri (bioconductor-uri "AnnotationFilter" version))
8611 "15qh4jwxxqsnb308nxzj99gckfk18rhp8g26q1xwgkr57zc5kcrx"))))
8613 `((upstream-name . "AnnotationFilter")))
8614 (build-system r-build-system)
8616 `(("r-genomicranges" ,r-genomicranges)
8617 ("r-lazyeval" ,r-lazyeval)))
8618 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8619 (synopsis "Facilities for filtering Bioconductor annotation resources")
8621 "This package provides classes and other infrastructure to implement
8622 filters for manipulating Bioconductor annotation resources. The filters are
8623 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8624 (license license:artistic2.0)))
8626 (define-public emboss
8632 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8633 (version-major+minor version) ".0/"
8634 "EMBOSS-" version ".tar.gz"))
8637 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8638 (build-system gnu-build-system)
8641 (list (string-append "--with-hpdf="
8642 (assoc-ref %build-inputs "libharu")))
8644 (modify-phases %standard-phases
8645 (add-after 'unpack 'fix-checks
8647 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8648 ;; and zlib, but assume that they are all found at the same
8650 (substitute* "configure.in"
8651 (("CHECK_PNGDRIVER")
8652 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8653 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8654 AM_CONDITIONAL(AMPNG, true)"))
8656 (add-after 'fix-checks 'disable-update-check
8658 ;; At build time there is no connection to the Internet, so
8659 ;; looking for updates will not work.
8660 (substitute* "Makefile.am"
8661 (("\\$\\(bindir\\)/embossupdate") ""))
8663 (add-after 'disable-update-check 'autogen
8664 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8670 ("libharu" ,libharu)
8673 `(("autoconf" ,autoconf)
8674 ("automake" ,automake)
8675 ("libtool" ,libtool)
8676 ("pkg-config" ,pkg-config)))
8677 (home-page "http://emboss.sourceforge.net")
8678 (synopsis "Molecular biology analysis suite")
8679 (description "EMBOSS is the \"European Molecular Biology Open Software
8680 Suite\". EMBOSS is an analysis package specially developed for the needs of
8681 the molecular biology (e.g. EMBnet) user community. The software
8682 automatically copes with data in a variety of formats and even allows
8683 transparent retrieval of sequence data from the web. It also provides a
8684 number of libraries for the development of software in the field of molecular
8685 biology. EMBOSS also integrates a range of currently available packages and
8686 tools for sequence analysis into a seamless whole.")
8687 (license license:gpl2+)))
8690 (let ((revision "1")
8691 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8694 ;; The version is 2.13.0 even though no release archives have been
8695 ;; published as yet.
8696 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8700 (url "https://github.com/arq5x/bits.git")
8702 (file-name (string-append name "-" version "-checkout"))
8705 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8706 (build-system gnu-build-system)
8708 `(#:tests? #f ;no tests included
8710 (modify-phases %standard-phases
8712 (add-after 'unpack 'remove-cuda
8714 (substitute* "Makefile"
8716 (("(bits_test_intersections) \\\\" _ match) match))
8719 (lambda* (#:key outputs #:allow-other-keys)
8721 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8726 (home-page "https://github.com/arq5x/bits")
8727 (synopsis "Implementation of binary interval search algorithm")
8728 (description "This package provides an implementation of the
8729 BITS (Binary Interval Search) algorithm, an approach to interval set
8730 intersection. It is especially suited for the comparison of diverse genomic
8731 datasets and the exploration of large datasets of genome
8732 intervals (e.g. genes, sequence alignments).")
8733 (license license:gpl2))))
8735 (define-public piranha
8736 ;; There is no release tarball for the latest version. The latest commit is
8737 ;; older than one year at the time of this writing.
8738 (let ((revision "1")
8739 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8742 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8746 (url "https://github.com/smithlabcode/piranha.git")
8748 (file-name (git-file-name name version))
8751 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8752 (build-system gnu-build-system)
8754 `(#:test-target "test"
8756 (modify-phases %standard-phases
8757 (add-after 'unpack 'copy-smithlab-cpp
8758 (lambda* (#:key inputs #:allow-other-keys)
8759 (for-each (lambda (file)
8760 (install-file file "./src/smithlab_cpp/"))
8761 (find-files (assoc-ref inputs "smithlab-cpp")))
8763 (add-after 'install 'install-to-store
8764 (lambda* (#:key outputs #:allow-other-keys)
8765 (let* ((out (assoc-ref outputs "out"))
8766 (bin (string-append out "/bin")))
8767 (for-each (lambda (file)
8768 (install-file file bin))
8769 (find-files "bin" ".*")))
8772 (list (string-append "--with-bam_tools_headers="
8773 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8774 (string-append "--with-bam_tools_library="
8775 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8777 `(("bamtools" ,bamtools)
8778 ("samtools" ,samtools-0.1)
8781 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8785 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8787 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8790 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8792 `(("python" ,python-2)))
8793 (home-page "https://github.com/smithlabcode/piranha")
8794 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8796 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8797 RIP-seq experiments. It takes input in BED or BAM format and identifies
8798 regions of statistically significant read enrichment. Additional covariates
8799 may optionally be provided to further inform the peak-calling process.")
8800 (license license:gpl3+))))
8808 (uri (pypi-uri "PePr" version))
8811 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8812 (build-system python-build-system)
8814 `(#:python ,python-2 ; python2 only
8815 #:tests? #f)) ; no tests included
8817 `(("python2-numpy" ,python2-numpy)
8818 ("python2-scipy" ,python2-scipy)
8819 ("python2-pysam" ,python2-pysam)))
8820 (home-page "https://github.com/shawnzhangyx/PePr")
8821 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8823 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8824 that is primarily designed for data with biological replicates. It uses a
8825 negative binomial distribution to model the read counts among the samples in
8826 the same group, and look for consistent differences between ChIP and control
8827 group or two ChIP groups run under different conditions.")
8828 (license license:gpl3+)))
8830 (define-public filevercmp
8831 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8834 (version (string-append "0-1." (string-take commit 7)))
8838 (url "https://github.com/ekg/filevercmp.git")
8840 (file-name (git-file-name name commit))
8843 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8844 (build-system gnu-build-system)
8846 `(#:tests? #f ; There are no tests to run.
8848 (modify-phases %standard-phases
8849 (delete 'configure) ; There is no configure phase.
8851 (lambda* (#:key outputs #:allow-other-keys)
8852 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8853 (install-file "filevercmp" bin)
8855 (home-page "https://github.com/ekg/filevercmp")
8856 (synopsis "This program compares version strings")
8857 (description "This program compares version strings. It intends to be a
8858 replacement for strverscmp.")
8859 (license license:gpl3+))))
8861 (define-public multiqc
8868 (uri (pypi-uri "multiqc" version))
8871 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8872 (build-system python-build-system)
8874 `(("python-jinja2" ,python-jinja2)
8875 ("python-simplejson" ,python-simplejson)
8876 ("python-pyyaml" ,python-pyyaml)
8877 ("python-click" ,python-click)
8878 ("python-spectra" ,python-spectra)
8879 ("python-requests" ,python-requests)
8880 ("python-markdown" ,python-markdown)
8881 ("python-lzstring" ,python-lzstring)
8882 ("python-matplotlib" ,python-matplotlib)
8883 ("python-numpy" ,python-numpy)
8884 ;; MultQC checks for the presence of nose at runtime.
8885 ("python-nose" ,python-nose)))
8888 (modify-phases %standard-phases
8889 (add-after 'unpack 'relax-requirements
8891 (substitute* "setup.py"
8892 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8893 ;; than the one in Guix, but should work fine with 2.2.2.
8894 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8895 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8896 (("['\"]matplotlib.*?['\"]")
8899 (home-page "http://multiqc.info")
8900 (synopsis "Aggregate bioinformatics analysis reports")
8902 "MultiQC is a tool to aggregate bioinformatics results across many
8903 samples into a single report. It contains modules for a large number of
8904 common bioinformatics tools.")
8905 (license license:gpl3+)))
8907 (define-public r-chipseq
8914 (uri (bioconductor-uri "chipseq" version))
8917 "1835nhrxcaqpqf1kxrsk1js8bf7x33z1n3bqjvm8404091acqyma"))))
8918 (build-system r-build-system)
8920 `(("r-biocgenerics" ,r-biocgenerics)
8921 ("r-genomicranges" ,r-genomicranges)
8922 ("r-iranges" ,r-iranges)
8923 ("r-lattice" ,r-lattice)
8924 ("r-s4vectors" ,r-s4vectors)
8925 ("r-shortread" ,r-shortread)))
8926 (home-page "https://bioconductor.org/packages/chipseq")
8927 (synopsis "Package for analyzing ChIPseq data")
8929 "This package provides tools for processing short read data from ChIPseq
8931 (license license:artistic2.0)))
8933 (define-public r-copyhelper
8935 (name "r-copyhelper")
8940 (uri (string-append "https://bioconductor.org/packages/release/"
8941 "data/experiment/src/contrib/CopyhelpeR_"
8945 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8946 (properties `((upstream-name . "CopyhelpeR")))
8947 (build-system r-build-system)
8948 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8949 (synopsis "Helper files for CopywriteR")
8951 "This package contains the helper files that are required to run the
8952 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8953 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8954 mm10. In addition, it contains a blacklist filter to remove regions that
8955 display copy number variation. Files are stored as GRanges objects from the
8956 GenomicRanges Bioconductor package.")
8957 (license license:gpl2)))
8959 (define-public r-copywriter
8961 (name "r-copywriter")
8966 (uri (bioconductor-uri "CopywriteR" version))
8969 "0kv3k58wyyicq1hhq7bddh0v3b2ksz6fa47skvnp8f193csza9g6"))))
8970 (properties `((upstream-name . "CopywriteR")))
8971 (build-system r-build-system)
8973 `(("r-biocparallel" ,r-biocparallel)
8974 ("r-chipseq" ,r-chipseq)
8975 ("r-copyhelper" ,r-copyhelper)
8976 ("r-data-table" ,r-data-table)
8977 ("r-dnacopy" ,r-dnacopy)
8978 ("r-futile-logger" ,r-futile-logger)
8979 ("r-genomeinfodb" ,r-genomeinfodb)
8980 ("r-genomicalignments" ,r-genomicalignments)
8981 ("r-genomicranges" ,r-genomicranges)
8982 ("r-gtools" ,r-gtools)
8983 ("r-iranges" ,r-iranges)
8984 ("r-matrixstats" ,r-matrixstats)
8985 ("r-rsamtools" ,r-rsamtools)
8986 ("r-s4vectors" ,r-s4vectors)))
8987 (home-page "https://github.com/PeeperLab/CopywriteR")
8988 (synopsis "Copy number information from targeted sequencing")
8990 "CopywriteR extracts DNA copy number information from targeted sequencing
8991 by utilizing off-target reads. It allows for extracting uniformly distributed
8992 copy number information, can be used without reference, and can be applied to
8993 sequencing data obtained from various techniques including chromatin
8994 immunoprecipitation and target enrichment on small gene panels. Thereby,
8995 CopywriteR constitutes a widely applicable alternative to available copy
8996 number detection tools.")
8997 (license license:gpl2)))
8999 (define-public r-methylkit
9001 (name "r-methylkit")
9005 (uri (bioconductor-uri "methylKit" version))
9008 "1z687vpi5kwcqpnd6r74c5y72hcsbqlwg0bk95kksgpi81q710qj"))))
9009 (properties `((upstream-name . "methylKit")))
9010 (build-system r-build-system)
9012 `(("r-data-table" ,r-data-table)
9013 ("r-emdbook" ,r-emdbook)
9014 ("r-fastseg" ,r-fastseg)
9015 ("r-genomeinfodb" ,r-genomeinfodb)
9016 ("r-genomicranges" ,r-genomicranges)
9017 ("r-gtools" ,r-gtools)
9018 ("r-iranges" ,r-iranges)
9019 ("r-kernsmooth" ,r-kernsmooth)
9020 ("r-limma" ,r-limma)
9021 ("r-mclust" ,r-mclust)
9023 ("r-qvalue" ,r-qvalue)
9024 ("r-r-utils" ,r-r-utils)
9026 ("r-rhtslib" ,r-rhtslib)
9027 ("r-rsamtools" ,r-rsamtools)
9028 ("r-rtracklayer" ,r-rtracklayer)
9029 ("r-s4vectors" ,r-s4vectors)
9030 ("r-zlibbioc" ,r-zlibbioc)))
9033 (home-page "https://github.com/al2na/methylKit")
9035 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9037 "MethylKit is an R package for DNA methylation analysis and annotation
9038 from high-throughput bisulfite sequencing. The package is designed to deal
9039 with sequencing data from @dfn{Reduced representation bisulfite
9040 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9041 genome bisulfite sequencing. It also has functions to analyze base-pair
9042 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9044 (license license:artistic2.0)))
9046 (define-public r-sva
9053 (uri (bioconductor-uri "sva" version))
9056 "0jj6klfha5v5qmx2sjblf1an6s2zqd7mmgsp7sfmh4k2jpqi3jm9"))))
9057 (build-system r-build-system)
9059 `(("r-genefilter" ,r-genefilter)
9061 ("r-biocparallel" ,r-biocparallel)
9062 ("r-matrixstats" ,r-matrixstats)
9063 ("r-limma" ,r-limma)))
9064 (home-page "https://bioconductor.org/packages/sva")
9065 (synopsis "Surrogate variable analysis")
9067 "This package contains functions for removing batch effects and other
9068 unwanted variation in high-throughput experiment. It also contains functions
9069 for identifying and building surrogate variables for high-dimensional data
9070 sets. Surrogate variables are covariates constructed directly from
9071 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9072 imaging data that can be used in subsequent analyses to adjust for unknown,
9073 unmodeled, or latent sources of noise.")
9074 (license license:artistic2.0)))
9076 (define-public r-seqminer
9083 (uri (cran-uri "seqminer" version))
9086 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9087 (build-system r-build-system)
9090 (home-page "http://seqminer.genomic.codes")
9091 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9093 "This package provides tools to integrate nucleotide sequencing
9094 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9095 ;; Any version of the GPL is acceptable
9096 (license (list license:gpl2+ license:gpl3+))))
9098 (define-public r-raremetals2
9100 (name "r-raremetals2")
9105 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9106 "b/b7/RareMETALS2_" version ".tar.gz"))
9109 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9110 (properties `((upstream-name . "RareMETALS2")))
9111 (build-system r-build-system)
9113 `(("r-seqminer" ,r-seqminer)
9114 ("r-mvtnorm" ,r-mvtnorm)
9116 ("r-compquadform" ,r-compquadform)
9117 ("r-getopt" ,r-getopt)))
9118 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9119 (synopsis "Analyze gene-level association tests for binary trait")
9121 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9122 It was designed to meta-analyze gene-level association tests for binary trait.
9123 While rareMETALS offers a near-complete solution for meta-analysis of
9124 gene-level tests for quantitative trait, it does not offer the optimal
9125 solution for binary trait. The package rareMETALS2 offers improved features
9126 for analyzing gene-level association tests in meta-analyses for binary
9128 (license license:gpl3)))
9130 (define-public r-maldiquant
9132 (name "r-maldiquant")
9137 (uri (cran-uri "MALDIquant" version))
9140 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9141 (properties `((upstream-name . "MALDIquant")))
9142 (build-system r-build-system)
9143 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9144 (synopsis "Quantitative analysis of mass spectrometry data")
9146 "This package provides a complete analysis pipeline for matrix-assisted
9147 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9148 two-dimensional mass spectrometry data. In addition to commonly used plotting
9149 and processing methods it includes distinctive features, namely baseline
9150 subtraction methods such as morphological filters (TopHat) or the
9151 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9152 alignment using warping functions, handling of replicated measurements as well
9153 as allowing spectra with different resolutions.")
9154 (license license:gpl3+)))
9156 (define-public r-protgenerics
9158 (name "r-protgenerics")
9163 (uri (bioconductor-uri "ProtGenerics" version))
9166 "12jjwmg58b4xbivxlw4pffq0qfi2c1c5hyrci0sfyphrc99fvx0i"))))
9167 (properties `((upstream-name . "ProtGenerics")))
9168 (build-system r-build-system)
9169 (home-page "https://github.com/lgatto/ProtGenerics")
9170 (synopsis "S4 generic functions for proteomics infrastructure")
9172 "This package provides S4 generic functions needed by Bioconductor
9173 proteomics packages.")
9174 (license license:artistic2.0)))
9176 (define-public r-mzr
9183 (uri (bioconductor-uri "mzR" version))
9186 "0g5r6yk4gyz0xdwlmrcij4zv7apdgsgygr043095l33hard6nsl5"))
9187 (modules '((guix build utils)))
9190 (delete-file-recursively "src/boost")
9192 (properties `((upstream-name . "mzR")))
9193 (build-system r-build-system)
9196 (modify-phases %standard-phases
9197 (add-after 'unpack 'use-system-boost
9199 (substitute* "src/Makevars"
9200 (("\\./boost/libs.*") "")
9201 (("ARCH_OBJS=" line)
9203 "\nARCH_LIBS=-lboost_system -lboost_regex \
9204 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9207 `(;; XXX Boost 1.69 will not work here.
9208 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9211 `(("r-biobase" ,r-biobase)
9212 ("r-biocgenerics" ,r-biocgenerics)
9213 ("r-ncdf4" ,r-ncdf4)
9214 ("r-protgenerics" ,r-protgenerics)
9216 ("r-rhdf5lib" ,r-rhdf5lib)
9217 ("r-zlibbioc" ,r-zlibbioc)))
9218 (home-page "https://github.com/sneumann/mzR/")
9219 (synopsis "Parser for mass spectrometry data files")
9221 "The mzR package provides a unified API to the common file formats and
9222 parsers available for mass spectrometry data. It comes with a wrapper for the
9223 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9224 The package contains the original code written by the ISB, and a subset of the
9225 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9226 previously been used in XCMS.")
9227 (license license:artistic2.0)))
9229 (define-public r-affyio
9236 (uri (bioconductor-uri "affyio" version))
9239 "1s78hm51fgac3i2j4bbdy0z6g14370154s6km8lldc9zpahx8b6p"))))
9240 (build-system r-build-system)
9242 `(("r-zlibbioc" ,r-zlibbioc)))
9245 (home-page "https://github.com/bmbolstad/affyio")
9246 (synopsis "Tools for parsing Affymetrix data files")
9248 "This package provides routines for parsing Affymetrix data files based
9249 upon file format information. The primary focus is on accessing the CEL and
9251 (license license:lgpl2.0+)))
9253 (define-public r-affy
9260 (uri (bioconductor-uri "affy" version))
9263 "05vz0vf3472s1ivfhc0gc8yz98y4rvvp7cf6kfbxhy1b23im1bgk"))))
9264 (build-system r-build-system)
9266 `(("r-affyio" ,r-affyio)
9267 ("r-biobase" ,r-biobase)
9268 ("r-biocgenerics" ,r-biocgenerics)
9269 ("r-biocmanager" ,r-biocmanager)
9270 ("r-preprocesscore" ,r-preprocesscore)
9271 ("r-zlibbioc" ,r-zlibbioc)))
9274 (home-page "https://bioconductor.org/packages/affy")
9275 (synopsis "Methods for affymetrix oligonucleotide arrays")
9277 "This package contains functions for exploratory oligonucleotide array
9279 (license license:lgpl2.0+)))
9281 (define-public r-vsn
9288 (uri (bioconductor-uri "vsn" version))
9291 "1vqmyxg06kgq9m3w6n0jykqm4jgsjw879r4s216wlcq4xc94dh1r"))))
9292 (build-system r-build-system)
9294 `(("r-affy" ,r-affy)
9295 ("r-biobase" ,r-biobase)
9296 ("r-ggplot2" ,r-ggplot2)
9297 ("r-lattice" ,r-lattice)
9298 ("r-limma" ,r-limma)))
9299 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9300 (synopsis "Variance stabilization and calibration for microarray data")
9302 "The package implements a method for normalising microarray intensities,
9303 and works for single- and multiple-color arrays. It can also be used for data
9304 from other technologies, as long as they have similar format. The method uses
9305 a robust variant of the maximum-likelihood estimator for an
9306 additive-multiplicative error model and affine calibration. The model
9307 incorporates data calibration step (a.k.a. normalization), a model for the
9308 dependence of the variance on the mean intensity and a variance stabilizing
9309 data transformation. Differences between transformed intensities are
9310 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9311 their variance is independent of the mean, and they are usually more sensitive
9312 and specific in detecting differential transcription.")
9313 (license license:artistic2.0)))
9315 (define-public r-mzid
9322 (uri (bioconductor-uri "mzID" version))
9325 "0vnyg7jlmy7ain7gmjwhqyqr664znrvrdlh7zd63563vhb87qarn"))))
9326 (properties `((upstream-name . "mzID")))
9327 (build-system r-build-system)
9329 `(("r-doparallel" ,r-doparallel)
9330 ("r-foreach" ,r-foreach)
9331 ("r-iterators" ,r-iterators)
9333 ("r-protgenerics" ,r-protgenerics)
9336 (home-page "https://bioconductor.org/packages/mzID")
9337 (synopsis "Parser for mzIdentML files")
9339 "This package provides a parser for mzIdentML files implemented using the
9340 XML package. The parser tries to be general and able to handle all types of
9341 mzIdentML files with the drawback of having less pretty output than a vendor
9343 (license license:gpl2+)))
9345 (define-public r-pcamethods
9347 (name "r-pcamethods")
9352 (uri (bioconductor-uri "pcaMethods" version))
9355 "0svf4n7l0afy4wwgs6x8x4dm330r3311l5vmsxw2f0r4axkh3bzk"))))
9356 (properties `((upstream-name . "pcaMethods")))
9357 (build-system r-build-system)
9359 `(("r-biobase" ,r-biobase)
9360 ("r-biocgenerics" ,r-biocgenerics)
9362 ("r-rcpp" ,r-rcpp)))
9363 (home-page "https://github.com/hredestig/pcamethods")
9364 (synopsis "Collection of PCA methods")
9366 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9367 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9368 for missing value estimation is included for comparison. BPCA, PPCA and
9369 NipalsPCA may be used to perform PCA on incomplete data as well as for
9370 accurate missing value estimation. A set of methods for printing and plotting
9371 the results is also provided. All PCA methods make use of the same data
9372 structure (pcaRes) to provide a common interface to the PCA results.")
9373 (license license:gpl3+)))
9375 (define-public r-msnbase
9382 (uri (bioconductor-uri "MSnbase" version))
9385 "0z63yqazkycq0zbbarq9ida6al35hv3g7g9g7s7bss4gh0hk7lhd"))))
9386 (properties `((upstream-name . "MSnbase")))
9387 (build-system r-build-system)
9389 `(("r-affy" ,r-affy)
9390 ("r-biobase" ,r-biobase)
9391 ("r-biocgenerics" ,r-biocgenerics)
9392 ("r-biocparallel" ,r-biocparallel)
9393 ("r-digest" ,r-digest)
9394 ("r-ggplot2" ,r-ggplot2)
9395 ("r-impute" ,r-impute)
9396 ("r-iranges" ,r-iranges)
9397 ("r-lattice" ,r-lattice)
9398 ("r-maldiquant" ,r-maldiquant)
9402 ("r-pcamethods" ,r-pcamethods)
9404 ("r-preprocesscore" ,r-preprocesscore)
9405 ("r-protgenerics" ,r-protgenerics)
9407 ("r-s4vectors" ,r-s4vectors)
9408 ("r-scales" ,r-scales)
9411 (home-page "https://github.com/lgatto/MSnbase")
9412 (synopsis "Base functions and classes for MS-based proteomics")
9414 "This package provides basic plotting, data manipulation and processing
9415 of mass spectrometry based proteomics data.")
9416 (license license:artistic2.0)))
9418 (define-public r-msnid
9425 (uri (bioconductor-uri "MSnID" version))
9428 "18mp8zacawhfapfwpq8czbswxix2ykvqhwjga54v0a99zg3k87h3"))))
9429 (properties `((upstream-name . "MSnID")))
9430 (build-system r-build-system)
9432 `(("r-biobase" ,r-biobase)
9433 ("r-data-table" ,r-data-table)
9434 ("r-doparallel" ,r-doparallel)
9435 ("r-dplyr" ,r-dplyr)
9436 ("r-foreach" ,r-foreach)
9437 ("r-iterators" ,r-iterators)
9438 ("r-msnbase" ,r-msnbase)
9441 ("r-protgenerics" ,r-protgenerics)
9442 ("r-r-cache" ,r-r-cache)
9444 ("r-reshape2" ,r-reshape2)))
9445 (home-page "https://bioconductor.org/packages/MSnID")
9446 (synopsis "Utilities for LC-MSn proteomics identifications")
9448 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9449 from mzIdentML (leveraging the mzID package) or text files. After collating
9450 the search results from multiple datasets it assesses their identification
9451 quality and optimize filtering criteria to achieve the maximum number of
9452 identifications while not exceeding a specified false discovery rate. It also
9453 contains a number of utilities to explore the MS/MS results and assess missed
9454 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9455 (license license:artistic2.0)))
9457 (define-public r-seurat
9463 (uri (cran-uri "Seurat" version))
9466 "016fgcmjz3sjfxdvam5hd7mdxpmpnc7f6p5zqlh97m21dgn5vpqn"))))
9467 (properties `((upstream-name . "Seurat")))
9468 (build-system r-build-system)
9471 ("r-cluster" ,r-cluster)
9472 ("r-cowplot" ,r-cowplot)
9473 ("r-fitdistrplus" ,r-fitdistrplus)
9474 ("r-future" ,r-future)
9475 ("r-future-apply" ,r-future-apply)
9476 ("r-ggplot2" ,r-ggplot2)
9477 ("r-ggrepel" ,r-ggrepel)
9478 ("r-ggridges" ,r-ggridges)
9480 ("r-igraph" ,r-igraph)
9481 ("r-irlba" ,r-irlba)
9482 ("r-kernsmooth" ,r-kernsmooth)
9483 ("r-lmtest" ,r-lmtest)
9485 ("r-matrix" ,r-matrix)
9486 ("r-metap" ,r-metap)
9487 ("r-pbapply" ,r-pbapply)
9488 ("r-plotly" ,r-plotly)
9491 ("r-rcolorbrewer" ,r-rcolorbrewer)
9493 ("r-rcppeigen" ,r-rcppeigen)
9494 ("r-rcppprogress" ,r-rcppprogress)
9495 ("r-reticulate" ,r-reticulate)
9496 ("r-rlang" ,r-rlang)
9499 ("r-rtsne" ,r-rtsne)
9500 ("r-scales" ,r-scales)
9501 ("r-sctransform" ,r-sctransform)
9502 ("r-sdmtools" ,r-sdmtools)
9503 ("r-tsne" ,r-tsne)))
9504 (home-page "http://www.satijalab.org/seurat")
9505 (synopsis "Seurat is an R toolkit for single cell genomics")
9507 "This package is an R package designed for QC, analysis, and
9508 exploration of single cell RNA-seq data. It easily enables widely-used
9509 analytical techniques, including the identification of highly variable genes,
9510 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9511 algorithms; density clustering, hierarchical clustering, k-means, and the
9512 discovery of differentially expressed genes and markers.")
9513 (license license:gpl3)))
9515 (define-public r-aroma-light
9517 (name "r-aroma-light")
9522 (uri (bioconductor-uri "aroma.light" version))
9525 "0a1prl4jhbqpa85i2vyia1ks9iippzl8np50fvm9wx8kbjxna5l6"))))
9526 (properties `((upstream-name . "aroma.light")))
9527 (build-system r-build-system)
9529 `(("r-matrixstats" ,r-matrixstats)
9530 ("r-r-methodss3" ,r-r-methodss3)
9532 ("r-r-utils" ,r-r-utils)))
9533 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9534 (synopsis "Methods for normalization and visualization of microarray data")
9536 "This package provides methods for microarray analysis that take basic
9537 data types such as matrices and lists of vectors. These methods can be used
9538 standalone, be utilized in other packages, or be wrapped up in higher-level
9540 (license license:gpl2+)))
9542 (define-public r-deseq
9549 (uri (bioconductor-uri "DESeq" version))
9552 "0jppqrikg9qfqcfw5qd3m5c7bag9g23bc0kcpk5zfkk1wv09mnlm"))))
9553 (properties `((upstream-name . "DESeq")))
9554 (build-system r-build-system)
9556 `(("r-biobase" ,r-biobase)
9557 ("r-biocgenerics" ,r-biocgenerics)
9558 ("r-genefilter" ,r-genefilter)
9559 ("r-geneplotter" ,r-geneplotter)
9560 ("r-lattice" ,r-lattice)
9561 ("r-locfit" ,r-locfit)
9563 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9564 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9565 (synopsis "Differential gene expression analysis")
9567 "This package provides tools for estimating variance-mean dependence in
9568 count data from high-throughput genetic sequencing assays and for testing for
9569 differential expression based on a model using the negative binomial
9571 (license license:gpl3+)))
9573 (define-public r-edaseq
9580 (uri (bioconductor-uri "EDASeq" version))
9583 "0mmc9bij17w4mfwcc566zbj5fvqgl8gfqs0qvj6ri4mbcql9jxb3"))))
9584 (properties `((upstream-name . "EDASeq")))
9585 (build-system r-build-system)
9587 `(("r-annotationdbi" ,r-annotationdbi)
9588 ("r-aroma-light" ,r-aroma-light)
9589 ("r-biobase" ,r-biobase)
9590 ("r-biocgenerics" ,r-biocgenerics)
9591 ("r-biocmanager" ,r-biocmanager)
9592 ("r-biomart" ,r-biomart)
9593 ("r-biostrings" ,r-biostrings)
9594 ("r-deseq" ,r-deseq)
9595 ("r-genomicfeatures" ,r-genomicfeatures)
9596 ("r-genomicranges" ,r-genomicranges)
9597 ("r-iranges" ,r-iranges)
9598 ("r-rsamtools" ,r-rsamtools)
9599 ("r-shortread" ,r-shortread)))
9600 (home-page "https://github.com/drisso/EDASeq")
9601 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9603 "This package provides support for numerical and graphical summaries of
9604 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9605 adjust for GC-content effect (or other gene-level effects) on read counts:
9606 loess robust local regression, global-scaling, and full-quantile
9607 normalization. Between-lane normalization procedures to adjust for
9608 distributional differences between lanes (e.g., sequencing depth):
9609 global-scaling and full-quantile normalization.")
9610 (license license:artistic2.0)))
9612 (define-public r-interactivedisplaybase
9614 (name "r-interactivedisplaybase")
9619 (uri (bioconductor-uri "interactiveDisplayBase" version))
9622 "1kkyv7hkygacmksvld9gs3ycf6wlblqcwi11nny0hq3l0ha265v5"))))
9624 `((upstream-name . "interactiveDisplayBase")))
9625 (build-system r-build-system)
9627 `(("r-biocgenerics" ,r-biocgenerics)
9628 ("r-shiny" ,r-shiny)))
9629 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9630 (synopsis "Base package for web displays of Bioconductor objects")
9632 "This package contains the basic methods needed to generate interactive
9633 Shiny-based display methods for Bioconductor objects.")
9634 (license license:artistic2.0)))
9636 (define-public r-annotationhub
9638 (name "r-annotationhub")
9643 (uri (bioconductor-uri "AnnotationHub" version))
9646 "1rpzl4x5mrwxrrf1jzm4zni6li6x34fjfyybsdvplb0ixa48zhn4"))))
9647 (properties `((upstream-name . "AnnotationHub")))
9648 (build-system r-build-system)
9650 `(("r-annotationdbi" ,r-annotationdbi)
9651 ("r-biocfilecache" ,r-biocfilecache)
9652 ("r-biocgenerics" ,r-biocgenerics)
9653 ("r-biocmanager" ,r-biocmanager)
9655 ("r-dplyr" ,r-dplyr)
9657 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9658 ("r-rappdirs" ,r-rappdirs)
9659 ("r-rsqlite" ,r-rsqlite)
9660 ("r-s4vectors" ,r-s4vectors)
9661 ("r-yaml" ,r-yaml)))
9662 (home-page "https://bioconductor.org/packages/AnnotationHub")
9663 (synopsis "Client to access AnnotationHub resources")
9665 "This package provides a client for the Bioconductor AnnotationHub web
9666 resource. The AnnotationHub web resource provides a central location where
9667 genomic files (e.g. VCF, bed, wig) and other resources from standard
9668 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9669 metadata about each resource, e.g., a textual description, tags, and date of
9670 modification. The client creates and manages a local cache of files retrieved
9671 by the user, helping with quick and reproducible access.")
9672 (license license:artistic2.0)))
9674 (define-public r-fastseg
9681 (uri (bioconductor-uri "fastseg" version))
9684 "03gggz29nf8kyy9clkifqr0xm8v0yb0kl0gjfb5c0vrjmwkfqvdf"))))
9685 (build-system r-build-system)
9687 `(("r-biobase" ,r-biobase)
9688 ("r-biocgenerics" ,r-biocgenerics)
9689 ("r-genomicranges" ,r-genomicranges)
9690 ("r-iranges" ,r-iranges)
9691 ("r-s4vectors" ,r-s4vectors)))
9692 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9693 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9695 "Fastseg implements a very fast and efficient segmentation algorithm.
9696 It can segment data from DNA microarrays and data from next generation
9697 sequencing for example to detect copy number segments. Further it can segment
9698 data from RNA microarrays like tiling arrays to identify transcripts. Most
9699 generally, it can segment data given as a matrix or as a vector. Various data
9700 formats can be used as input to fastseg like expression set objects for
9701 microarrays or GRanges for sequencing data.")
9702 (license license:lgpl2.0+)))
9704 (define-public r-keggrest
9711 (uri (bioconductor-uri "KEGGREST" version))
9714 "1yjrpbm5zfg0h3nb5gg06q2f19ydbhjqwi0jb6q3p8dyrgww9mqp"))))
9715 (properties `((upstream-name . "KEGGREST")))
9716 (build-system r-build-system)
9718 `(("r-biostrings" ,r-biostrings)
9721 (home-page "https://bioconductor.org/packages/KEGGREST")
9722 (synopsis "Client-side REST access to KEGG")
9724 "This package provides a package that provides a client interface to the
9725 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9726 (license license:artistic2.0)))
9728 (define-public r-gage
9735 (uri (bioconductor-uri "gage" version))
9738 "08d5yg7n4rx4xsginc8bx0sycpj06pi1k7i44ff757444p20srwq"))))
9739 (build-system r-build-system)
9741 `(("r-annotationdbi" ,r-annotationdbi)
9742 ("r-graph" ,r-graph)
9743 ("r-keggrest" ,r-keggrest)))
9744 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9745 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9747 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9748 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9749 data attributes including sample sizes, experimental designs, assay platforms,
9750 and other types of heterogeneity. The gage package provides functions for
9751 basic GAGE analysis, result processing and presentation. In addition, it
9752 provides demo microarray data and commonly used gene set data based on KEGG
9753 pathways and GO terms. These functions and data are also useful for gene set
9754 analysis using other methods.")
9755 (license license:gpl2+)))
9757 (define-public r-genomicfiles
9759 (name "r-genomicfiles")
9764 (uri (bioconductor-uri "GenomicFiles" version))
9767 "122g0yhpsm6fyvv38agp57clagl13h324rk06mlgb2xz104a1j4i"))))
9768 (properties `((upstream-name . "GenomicFiles")))
9769 (build-system r-build-system)
9771 `(("r-biocgenerics" ,r-biocgenerics)
9772 ("r-biocparallel" ,r-biocparallel)
9773 ("r-genomeinfodb" ,r-genomeinfodb)
9774 ("r-genomicalignments" ,r-genomicalignments)
9775 ("r-genomicranges" ,r-genomicranges)
9776 ("r-iranges" ,r-iranges)
9777 ("r-rsamtools" ,r-rsamtools)
9778 ("r-rtracklayer" ,r-rtracklayer)
9779 ("r-s4vectors" ,r-s4vectors)
9780 ("r-summarizedexperiment" ,r-summarizedexperiment)
9781 ("r-variantannotation" ,r-variantannotation)))
9782 (home-page "https://bioconductor.org/packages/GenomicFiles")
9783 (synopsis "Distributed computing by file or by range")
9785 "This package provides infrastructure for parallel computations
9786 distributed by file or by range. User defined mapper and reducer functions
9787 provide added flexibility for data combination and manipulation.")
9788 (license license:artistic2.0)))
9790 (define-public r-complexheatmap
9792 (name "r-complexheatmap")
9797 (uri (bioconductor-uri "ComplexHeatmap" version))
9800 "1imnb72r10csl2h12sckic7hcsb8v2z0y3dyw1ax2fpykmsmq776"))))
9802 `((upstream-name . "ComplexHeatmap")))
9803 (build-system r-build-system)
9805 `(("r-circlize" ,r-circlize)
9807 ("r-colorspace" ,r-colorspace)
9808 ("r-getoptlong" ,r-getoptlong)
9809 ("r-globaloptions" ,r-globaloptions)
9811 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9813 "https://github.com/jokergoo/ComplexHeatmap")
9814 (synopsis "Making Complex Heatmaps")
9816 "Complex heatmaps are efficient to visualize associations between
9817 different sources of data sets and reveal potential structures. This package
9818 provides a highly flexible way to arrange multiple heatmaps and supports
9819 self-defined annotation graphics.")
9820 (license license:gpl2+)))
9822 (define-public r-dirichletmultinomial
9824 (name "r-dirichletmultinomial")
9829 (uri (bioconductor-uri "DirichletMultinomial" version))
9832 "0qirvhnbv4wd50ln4pqbk4dj6h2935ipf9p4sw1x62qqhwxidqk4"))))
9834 `((upstream-name . "DirichletMultinomial")))
9835 (build-system r-build-system)
9839 `(("r-biocgenerics" ,r-biocgenerics)
9840 ("r-iranges" ,r-iranges)
9841 ("r-s4vectors" ,r-s4vectors)))
9842 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9843 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9845 "Dirichlet-multinomial mixture models can be used to describe variability
9846 in microbial metagenomic data. This package is an interface to code
9847 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9849 (license license:lgpl3)))
9851 (define-public r-ensembldb
9853 (name "r-ensembldb")
9858 (uri (bioconductor-uri "ensembldb" version))
9861 "09s5g9xm9m8mqvzk6pkp9fyhx3zyb4p8yziz49mhfji5n35nydjr"))))
9862 (build-system r-build-system)
9864 `(("r-annotationdbi" ,r-annotationdbi)
9865 ("r-annotationfilter" ,r-annotationfilter)
9866 ("r-biobase" ,r-biobase)
9867 ("r-biocgenerics" ,r-biocgenerics)
9868 ("r-biostrings" ,r-biostrings)
9871 ("r-genomeinfodb" ,r-genomeinfodb)
9872 ("r-genomicfeatures" ,r-genomicfeatures)
9873 ("r-genomicranges" ,r-genomicranges)
9874 ("r-iranges" ,r-iranges)
9875 ("r-protgenerics" ,r-protgenerics)
9876 ("r-rsamtools" ,r-rsamtools)
9877 ("r-rsqlite" ,r-rsqlite)
9878 ("r-rtracklayer" ,r-rtracklayer)
9879 ("r-s4vectors" ,r-s4vectors)))
9880 (home-page "https://github.com/jotsetung/ensembldb")
9881 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9883 "The package provides functions to create and use transcript-centric
9884 annotation databases/packages. The annotation for the databases are directly
9885 fetched from Ensembl using their Perl API. The functionality and data is
9886 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9887 but, in addition to retrieve all gene/transcript models and annotations from
9888 the database, the @code{ensembldb} package also provides a filter framework
9889 allowing to retrieve annotations for specific entries like genes encoded on a
9890 chromosome region or transcript models of lincRNA genes.")
9891 ;; No version specified
9892 (license license:lgpl3+)))
9894 (define-public r-organismdbi
9896 (name "r-organismdbi")
9901 (uri (bioconductor-uri "OrganismDbi" version))
9904 "14azk69pmwlhza0mhsxigsg127w3mgsx9hhrbdcdqmy3vzfbfaqq"))))
9905 (properties `((upstream-name . "OrganismDbi")))
9906 (build-system r-build-system)
9908 `(("r-annotationdbi" ,r-annotationdbi)
9909 ("r-biobase" ,r-biobase)
9910 ("r-biocgenerics" ,r-biocgenerics)
9911 ("r-biocmanager" ,r-biocmanager)
9913 ("r-genomicfeatures" ,r-genomicfeatures)
9914 ("r-genomicranges" ,r-genomicranges)
9915 ("r-graph" ,r-graph)
9916 ("r-iranges" ,r-iranges)
9918 ("r-s4vectors" ,r-s4vectors)))
9919 (home-page "https://bioconductor.org/packages/OrganismDbi")
9920 (synopsis "Software to enable the smooth interfacing of database packages")
9921 (description "The package enables a simple unified interface to several
9922 annotation packages each of which has its own schema by taking advantage of
9923 the fact that each of these packages implements a select methods.")
9924 (license license:artistic2.0)))
9926 (define-public r-biovizbase
9928 (name "r-biovizbase")
9933 (uri (bioconductor-uri "biovizBase" version))
9936 "1lba1801ak0a4vz6f8jffp9d525q27p0dhi2bp4f68mvdwwl2994"))))
9937 (properties `((upstream-name . "biovizBase")))
9938 (build-system r-build-system)
9940 `(("r-annotationdbi" ,r-annotationdbi)
9941 ("r-annotationfilter" ,r-annotationfilter)
9942 ("r-biocgenerics" ,r-biocgenerics)
9943 ("r-biostrings" ,r-biostrings)
9944 ("r-dichromat" ,r-dichromat)
9945 ("r-ensembldb" ,r-ensembldb)
9946 ("r-genomeinfodb" ,r-genomeinfodb)
9947 ("r-genomicalignments" ,r-genomicalignments)
9948 ("r-genomicfeatures" ,r-genomicfeatures)
9949 ("r-genomicranges" ,r-genomicranges)
9950 ("r-hmisc" ,r-hmisc)
9951 ("r-iranges" ,r-iranges)
9952 ("r-rcolorbrewer" ,r-rcolorbrewer)
9953 ("r-rlang" ,r-rlang)
9954 ("r-rsamtools" ,r-rsamtools)
9955 ("r-s4vectors" ,r-s4vectors)
9956 ("r-scales" ,r-scales)
9957 ("r-summarizedexperiment" ,r-summarizedexperiment)
9958 ("r-variantannotation" ,r-variantannotation)))
9959 (home-page "https://bioconductor.org/packages/biovizBase")
9960 (synopsis "Basic graphic utilities for visualization of genomic data")
9962 "The biovizBase package is designed to provide a set of utilities, color
9963 schemes and conventions for genomic data. It serves as the base for various
9964 high-level packages for biological data visualization. This saves development
9965 effort and encourages consistency.")
9966 (license license:artistic2.0)))
9968 (define-public r-ggbio
9975 (uri (bioconductor-uri "ggbio" version))
9978 "10s6hnffnrrsx3896adqdc5g55fzd5y6qhnp1mq0c641nw833rwd"))))
9979 (build-system r-build-system)
9982 (modify-phases %standard-phases
9983 ;; See https://github.com/tengfei/ggbio/issues/117
9984 ;; This fix will be included in the next release.
9985 (add-after 'unpack 'fix-typo
9987 (substitute* "R/GGbio-class.R"
9988 (("fechable") "fetchable"))
9991 `(("r-annotationdbi" ,r-annotationdbi)
9992 ("r-annotationfilter" ,r-annotationfilter)
9993 ("r-biobase" ,r-biobase)
9994 ("r-biocgenerics" ,r-biocgenerics)
9995 ("r-biostrings" ,r-biostrings)
9996 ("r-biovizbase" ,r-biovizbase)
9997 ("r-bsgenome" ,r-bsgenome)
9998 ("r-ensembldb" ,r-ensembldb)
9999 ("r-genomeinfodb" ,r-genomeinfodb)
10000 ("r-genomicalignments" ,r-genomicalignments)
10001 ("r-genomicfeatures" ,r-genomicfeatures)
10002 ("r-genomicranges" ,r-genomicranges)
10003 ("r-ggally" ,r-ggally)
10004 ("r-ggplot2" ,r-ggplot2)
10005 ("r-gridextra" ,r-gridextra)
10006 ("r-gtable" ,r-gtable)
10007 ("r-hmisc" ,r-hmisc)
10008 ("r-iranges" ,r-iranges)
10009 ("r-organismdbi" ,r-organismdbi)
10010 ("r-reshape2" ,r-reshape2)
10011 ("r-rlang" ,r-rlang)
10012 ("r-rsamtools" ,r-rsamtools)
10013 ("r-rtracklayer" ,r-rtracklayer)
10014 ("r-s4vectors" ,r-s4vectors)
10015 ("r-scales" ,r-scales)
10016 ("r-summarizedexperiment" ,r-summarizedexperiment)
10017 ("r-variantannotation" ,r-variantannotation)))
10018 (home-page "http://www.tengfei.name/ggbio/")
10019 (synopsis "Visualization tools for genomic data")
10021 "The ggbio package extends and specializes the grammar of graphics for
10022 biological data. The graphics are designed to answer common scientific
10023 questions, in particular those often asked of high throughput genomics data.
10024 All core Bioconductor data structures are supported, where appropriate. The
10025 package supports detailed views of particular genomic regions, as well as
10026 genome-wide overviews. Supported overviews include ideograms and grand linear
10027 views. High-level plots include sequence fragment length, edge-linked
10028 interval to data view, mismatch pileup, and several splicing summaries.")
10029 (license license:artistic2.0)))
10031 (define-public r-gprofiler
10033 (name "r-gprofiler")
10038 (uri (cran-uri "gProfileR" version))
10041 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10042 (properties `((upstream-name . "gProfileR")))
10043 (build-system r-build-system)
10045 `(("r-plyr" ,r-plyr)
10046 ("r-rcurl" ,r-rcurl)))
10047 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10048 (synopsis "Interface to the g:Profiler toolkit")
10050 "This package provides tools for functional enrichment analysis,
10051 gene identifier conversion and mapping homologous genes across related
10052 organisms via the @code{g:Profiler} toolkit.")
10053 (license license:gpl2+)))
10055 (define-public r-gqtlbase
10057 (name "r-gqtlbase")
10062 (uri (bioconductor-uri "gQTLBase" version))
10065 "1n2cizb88g2ankngvhxv377gizg80y3fhlx67sgm0z4ilm6a30ql"))))
10066 (properties `((upstream-name . "gQTLBase")))
10067 (build-system r-build-system)
10069 `(("r-batchjobs" ,r-batchjobs)
10070 ("r-bbmisc" ,r-bbmisc)
10071 ("r-biocgenerics" ,r-biocgenerics)
10073 ("r-doparallel" ,r-doparallel)
10075 ("r-ffbase" ,r-ffbase)
10076 ("r-foreach" ,r-foreach)
10077 ("r-genomicfiles" ,r-genomicfiles)
10078 ("r-genomicranges" ,r-genomicranges)
10079 ("r-rtracklayer" ,r-rtracklayer)
10080 ("r-s4vectors" ,r-s4vectors)
10081 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10082 (home-page "https://bioconductor.org/packages/gQTLBase")
10083 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10085 "The purpose of this package is to simplify the storage and interrogation
10086 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10088 (license license:artistic2.0)))
10090 (define-public r-snpstats
10092 (name "r-snpstats")
10097 (uri (bioconductor-uri "snpStats" version))
10100 "0drfd24a5pkrhzmpidlh717bgh2dm68mpn6vj1vlpkilfbkifl34"))))
10101 (properties `((upstream-name . "snpStats")))
10102 (build-system r-build-system)
10103 (inputs `(("zlib" ,zlib)))
10105 `(("r-biocgenerics" ,r-biocgenerics)
10106 ("r-matrix" ,r-matrix)
10107 ("r-survival" ,r-survival)
10108 ("r-zlibbioc" ,r-zlibbioc)))
10109 (home-page "https://bioconductor.org/packages/snpStats")
10110 (synopsis "Methods for SNP association studies")
10112 "This package provides classes and statistical methods for large
10113 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10114 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10115 (license license:gpl3)))
10117 (define-public r-homo-sapiens
10119 (name "r-homo-sapiens")
10123 ;; We cannot use bioconductor-uri here because this tarball is
10124 ;; located under "data/annotation/" instead of "bioc/".
10125 (uri (string-append "http://www.bioconductor.org/packages/"
10126 "release/data/annotation/src/contrib/"
10128 version ".tar.gz"))
10131 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10133 `((upstream-name . "Homo.sapiens")))
10134 (build-system r-build-system)
10136 `(("r-genomicfeatures" ,r-genomicfeatures)
10137 ("r-go-db" ,r-go-db)
10138 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10139 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10140 ("r-organismdbi" ,r-organismdbi)
10141 ("r-annotationdbi" ,r-annotationdbi)))
10142 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10143 (synopsis "Annotation package for the Homo.sapiens object")
10145 "This package contains the Homo.sapiens object to access data from
10146 several related annotation packages.")
10147 (license license:artistic2.0)))
10149 (define-public r-erma
10156 (uri (bioconductor-uri "erma" version))
10159 "0j7ggp63m5y88cxgi49vcql1s1avzifwvvd2hydj4lj3yrmzib48"))))
10160 (build-system r-build-system)
10162 `(("r-annotationdbi" ,r-annotationdbi)
10163 ("r-biobase" ,r-biobase)
10164 ("r-biocgenerics" ,r-biocgenerics)
10165 ("r-biocparallel" ,r-biocparallel)
10166 ("r-genomeinfodb" ,r-genomeinfodb)
10167 ("r-genomicfiles" ,r-genomicfiles)
10168 ("r-genomicranges" ,r-genomicranges)
10169 ("r-ggplot2" ,r-ggplot2)
10170 ("r-homo-sapiens" ,r-homo-sapiens)
10171 ("r-iranges" ,r-iranges)
10172 ("r-rtracklayer" ,r-rtracklayer)
10173 ("r-s4vectors" ,r-s4vectors)
10174 ("r-shiny" ,r-shiny)
10175 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10176 (home-page "https://bioconductor.org/packages/erma")
10177 (synopsis "Epigenomic road map adventures")
10179 "The epigenomics road map describes locations of epigenetic marks in DNA
10180 from a variety of cell types. Of interest are locations of histone
10181 modifications, sites of DNA methylation, and regions of accessible chromatin.
10182 This package presents a selection of elements of the road map including
10183 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10184 by Ernst and Kellis.")
10185 (license license:artistic2.0)))
10187 (define-public r-ldblock
10194 (uri (bioconductor-uri "ldblock" version))
10197 "0lraxhq9ny3468534klrl64nx0dpaf9cbd5bir6m5qma8j7kfnyd"))))
10198 (build-system r-build-system)
10200 `(("r-biocgenerics" ,r-biocgenerics)
10202 ("r-genomeinfodb" ,r-genomeinfodb)
10203 ("r-genomicfiles" ,r-genomicfiles)
10204 ("r-go-db" ,r-go-db)
10205 ("r-homo-sapiens" ,r-homo-sapiens)
10206 ("r-matrix" ,r-matrix)
10207 ("r-rsamtools" ,r-rsamtools)
10208 ("r-snpstats" ,r-snpstats)
10209 ("r-variantannotation" ,r-variantannotation)))
10210 (home-page "https://bioconductor.org/packages/ldblock")
10211 (synopsis "Data structures for linkage disequilibrium measures in populations")
10213 "This package defines data structures for @dfn{linkage
10214 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10215 handling of existing population-level data for the purpose of flexibly
10216 defining LD blocks.")
10217 (license license:artistic2.0)))
10219 (define-public r-gqtlstats
10221 (name "r-gqtlstats")
10226 (uri (bioconductor-uri "gQTLstats" version))
10229 "17xadfn8qh1pwzlpcbds5wrjr9bzhsnmv90wffxmp02hq20qkrh5"))))
10230 (properties `((upstream-name . "gQTLstats")))
10231 (build-system r-build-system)
10233 `(("r-annotationdbi" ,r-annotationdbi)
10234 ("r-batchjobs" ,r-batchjobs)
10235 ("r-bbmisc" ,r-bbmisc)
10236 ("r-beeswarm" ,r-beeswarm)
10237 ("r-biobase" ,r-biobase)
10238 ("r-biocgenerics" ,r-biocgenerics)
10239 ("r-doparallel" ,r-doparallel)
10240 ("r-dplyr" ,r-dplyr)
10242 ("r-ffbase" ,r-ffbase)
10243 ("r-foreach" ,r-foreach)
10244 ("r-genomeinfodb" ,r-genomeinfodb)
10245 ("r-genomicfeatures" ,r-genomicfeatures)
10246 ("r-genomicfiles" ,r-genomicfiles)
10247 ("r-genomicranges" ,r-genomicranges)
10248 ("r-ggbeeswarm" ,r-ggbeeswarm)
10249 ("r-ggplot2" ,r-ggplot2)
10250 ("r-gqtlbase" ,r-gqtlbase)
10251 ("r-hardyweinberg" ,r-hardyweinberg)
10252 ("r-homo-sapiens" ,r-homo-sapiens)
10253 ("r-iranges" ,r-iranges)
10254 ("r-limma" ,r-limma)
10256 ("r-plotly" ,r-plotly)
10257 ("r-reshape2" ,r-reshape2)
10258 ("r-s4vectors" ,r-s4vectors)
10259 ("r-shiny" ,r-shiny)
10260 ("r-snpstats" ,r-snpstats)
10261 ("r-summarizedexperiment" ,r-summarizedexperiment)
10262 ("r-variantannotation" ,r-variantannotation)))
10263 (home-page "https://bioconductor.org/packages/gQTLstats")
10264 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10266 "This package provides tools for the computationally efficient analysis
10267 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10268 The software in this package aims to support refinements and functional
10269 interpretation of members of a collection of association statistics on a
10270 family of feature/genome hypotheses.")
10271 (license license:artistic2.0)))
10273 (define-public r-gviz
10280 (uri (bioconductor-uri "Gviz" version))
10283 "02alz27w8fnnm2ga71g3jg2b94f95ccv6r1fyszj4yb1k2g7rkxk"))))
10284 (properties `((upstream-name . "Gviz")))
10285 (build-system r-build-system)
10287 `(("r-annotationdbi" ,r-annotationdbi)
10288 ("r-biobase" ,r-biobase)
10289 ("r-biocgenerics" ,r-biocgenerics)
10290 ("r-biomart" ,r-biomart)
10291 ("r-biostrings" ,r-biostrings)
10292 ("r-biovizbase" ,r-biovizbase)
10293 ("r-bsgenome" ,r-bsgenome)
10294 ("r-digest" ,r-digest)
10295 ("r-genomeinfodb" ,r-genomeinfodb)
10296 ("r-genomicalignments" ,r-genomicalignments)
10297 ("r-genomicfeatures" ,r-genomicfeatures)
10298 ("r-genomicranges" ,r-genomicranges)
10299 ("r-iranges" ,r-iranges)
10300 ("r-lattice" ,r-lattice)
10301 ("r-latticeextra" ,r-latticeextra)
10302 ("r-matrixstats" ,r-matrixstats)
10303 ("r-rcolorbrewer" ,r-rcolorbrewer)
10304 ("r-rsamtools" ,r-rsamtools)
10305 ("r-rtracklayer" ,r-rtracklayer)
10306 ("r-s4vectors" ,r-s4vectors)
10307 ("r-xvector" ,r-xvector)))
10308 (home-page "https://bioconductor.org/packages/Gviz")
10309 (synopsis "Plotting data and annotation information along genomic coordinates")
10311 "Genomic data analyses requires integrated visualization of known genomic
10312 information and new experimental data. Gviz uses the biomaRt and the
10313 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10314 and translates this to e.g. gene/transcript structures in viewports of the
10315 grid graphics package. This results in genomic information plotted together
10317 (license license:artistic2.0)))
10319 (define-public r-gwascat
10326 (uri (bioconductor-uri "gwascat" version))
10329 "0akb36mrybmxbb1bc9kgxbnj3cdypfylj3yzrmhjwqxml03mg61i"))))
10330 (build-system r-build-system)
10332 `(("r-annotationdbi" ,r-annotationdbi)
10333 ("r-biocgenerics" ,r-biocgenerics)
10334 ("r-biostrings" ,r-biostrings)
10335 ("r-genomeinfodb" ,r-genomeinfodb)
10336 ("r-genomicfeatures" ,r-genomicfeatures)
10337 ("r-genomicranges" ,r-genomicranges)
10338 ("r-homo-sapiens" ,r-homo-sapiens)
10339 ("r-iranges" ,r-iranges)
10340 ("r-rsamtools" ,r-rsamtools)
10341 ("r-rtracklayer" ,r-rtracklayer)
10342 ("r-s4vectors" ,r-s4vectors)))
10343 (home-page "https://bioconductor.org/packages/gwascat")
10344 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10346 "This package provides tools for representing and modeling data in the
10347 EMBL-EBI GWAS catalog.")
10348 (license license:artistic2.0)))
10350 (define-public r-sushi
10356 (uri (bioconductor-uri "Sushi" version))
10359 "1hgh3jfcx0bh3fyvp85v7435hvsk3ah1hxx5117ss93v03iwjf1g"))))
10360 (properties `((upstream-name . "Sushi")))
10361 (build-system r-build-system)
10363 `(("r-biomart" ,r-biomart)
10365 (home-page "https://bioconductor.org/packages/Sushi")
10366 (synopsis "Tools for visualizing genomics data")
10368 "This package provides flexible, quantitative, and integrative genomic
10369 visualizations for publication-quality multi-panel figures.")
10370 (license license:gpl2+)))
10372 (define-public r-fithic
10378 (uri (bioconductor-uri "FitHiC" version))
10381 "1qrxy4v8vmykrk8y6g3bs5wh5xhbs6pxyydbxy3vnj2mjirnxr6d"))))
10382 (properties `((upstream-name . "FitHiC")))
10383 (build-system r-build-system)
10385 `(("r-data-table" ,r-data-table)
10386 ("r-fdrtool" ,r-fdrtool)
10387 ("r-rcpp" ,r-rcpp)))
10388 (home-page "https://bioconductor.org/packages/FitHiC")
10389 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10391 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10392 intra-chromosomal contact maps produced by genome-wide genome architecture
10393 assays such as Hi-C.")
10394 (license license:gpl2+)))
10396 (define-public r-hitc
10402 (uri (bioconductor-uri "HiTC" version))
10405 "059a1xxv2kb0bb32flymg2s8ylhavnv3j8l4125rfidagcgxgzjq"))))
10406 (properties `((upstream-name . "HiTC")))
10407 (build-system r-build-system)
10409 `(("r-biostrings" ,r-biostrings)
10410 ("r-genomeinfodb" ,r-genomeinfodb)
10411 ("r-genomicranges" ,r-genomicranges)
10412 ("r-iranges" ,r-iranges)
10413 ("r-matrix" ,r-matrix)
10414 ("r-rcolorbrewer" ,r-rcolorbrewer)
10415 ("r-rtracklayer" ,r-rtracklayer)))
10416 (home-page "https://bioconductor.org/packages/HiTC")
10417 (synopsis "High throughput chromosome conformation capture analysis")
10419 "The HiTC package was developed to explore high-throughput \"C\" data
10420 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10421 quality controls, normalization, visualization, and further analysis are also
10423 (license license:artistic2.0)))
10425 (define-public r-hdf5array
10427 (name "r-hdf5array")
10432 (uri (bioconductor-uri "HDF5Array" version))
10435 "0n8zc1x582vwb0zfhrjmnqbnpqky9zbhjc2j836i0a4yisklwdcp"))))
10436 (properties `((upstream-name . "HDF5Array")))
10437 (build-system r-build-system)
10441 `(("r-biocgenerics" ,r-biocgenerics)
10442 ("r-delayedarray" ,r-delayedarray)
10443 ("r-iranges" ,r-iranges)
10444 ("r-rhdf5" ,r-rhdf5)
10445 ("r-rhdf5lib" ,r-rhdf5lib)
10446 ("r-s4vectors" ,r-s4vectors)))
10447 (home-page "https://bioconductor.org/packages/HDF5Array")
10448 (synopsis "HDF5 back end for DelayedArray objects")
10449 (description "This package provides an array-like container for convenient
10450 access and manipulation of HDF5 datasets. It supports delayed operations and
10451 block processing.")
10452 (license license:artistic2.0)))
10454 (define-public r-rhdf5lib
10456 (name "r-rhdf5lib")
10461 (uri (bioconductor-uri "Rhdf5lib" version))
10464 "1lpmyxlwwcy92hyxqag321ssc5z6yw3a0ws9r058jwgzyjg7i2gm"))
10465 (modules '((guix build utils)))
10468 ;; Delete bundled binaries
10469 (delete-file-recursively "src/winlib/")
10471 (properties `((upstream-name . "Rhdf5lib")))
10472 (build-system r-build-system)
10475 (modify-phases %standard-phases
10476 (add-after 'unpack 'do-not-use-bundled-hdf5
10477 (lambda* (#:key inputs #:allow-other-keys)
10478 (for-each delete-file '("configure" "configure.ac"))
10479 ;; Do not make other packages link with the proprietary libsz.
10480 (substitute* "R/zzz.R"
10481 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10482 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10483 (("'%s/libhdf5.a %s/libsz.a -lz'")
10484 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10485 (with-directory-excursion "src"
10486 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10487 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10489 ;; Remove timestamp and host system information to make
10490 ;; the build reproducible.
10491 (substitute* "hdf5/src/libhdf5.settings.in"
10492 (("Configured on: @CONFIG_DATE@")
10493 "Configured on: Guix")
10494 (("Uname information:.*")
10495 "Uname information: Linux\n")
10496 ;; Remove unnecessary store reference.
10498 "C Compiler: GCC\n"))
10499 (rename-file "Makevars.in" "Makevars")
10500 (substitute* "Makevars"
10501 (("HDF5_CXX_LIB=.*")
10502 (string-append "HDF5_CXX_LIB="
10503 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10505 (string-append "HDF5_LIB="
10506 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10507 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10508 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10509 ;; szip is non-free software
10510 (("cp \\$\\{SZIP_LIB\\}.*") "")
10511 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10516 `(("hdf5" ,hdf5-1.10)))
10518 `(("hdf5-source" ,(package-source hdf5-1.10))))
10519 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10520 (synopsis "HDF5 library as an R package")
10521 (description "This package provides C and C++ HDF5 libraries for use in R
10523 (license license:artistic2.0)))
10525 (define-public r-beachmat
10527 (name "r-beachmat")
10532 (uri (bioconductor-uri "beachmat" version))
10535 "14cz19fw97s8mhm9r2n5li44vckx069k8nqsyy64c3lkfm4vy4zx"))))
10536 (build-system r-build-system)
10538 `(("r-biocgenerics" ,r-biocgenerics)
10539 ("r-delayedarray" ,r-delayedarray)))
10540 (home-page "https://bioconductor.org/packages/beachmat")
10541 (synopsis "Compiling Bioconductor to handle each matrix type")
10542 (description "This package provides a consistent C++ class interface for a
10543 variety of commonly used matrix types, including sparse and HDF5-backed
10545 (license license:gpl3)))
10547 (define-public r-singlecellexperiment
10549 (name "r-singlecellexperiment")
10554 (uri (bioconductor-uri "SingleCellExperiment" version))
10557 "0m3yjnv1njb4gyzcjfk7a0lz2vgggp2wjz382gqrb0qhhwcgfkj5"))))
10559 `((upstream-name . "SingleCellExperiment")))
10560 (build-system r-build-system)
10562 `(("r-biocgenerics" ,r-biocgenerics)
10563 ("r-s4vectors" ,r-s4vectors)
10564 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10565 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10566 (synopsis "S4 classes for single cell data")
10567 (description "This package defines an S4 class for storing data from
10568 single-cell experiments. This includes specialized methods to store and
10569 retrieve spike-in information, dimensionality reduction coordinates and size
10570 factors for each cell, along with the usual metadata for genes and
10572 (license license:gpl3)))
10574 (define-public r-scater
10580 (uri (bioconductor-uri "scater" version))
10583 "16a17161xlhh6qpna9qxph3anlc7ydgyrczmy4alfiw8si7pzmxa"))))
10584 (build-system r-build-system)
10586 `(("r-beachmat" ,r-beachmat)
10587 ("r-biocgenerics" ,r-biocgenerics)
10588 ("r-biocneighbors" ,r-biocneighbors)
10589 ("r-biocparallel" ,r-biocparallel)
10590 ("r-biocsingular" ,r-biocsingular)
10591 ("r-delayedarray" ,r-delayedarray)
10592 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10593 ("r-dplyr" ,r-dplyr)
10594 ("r-ggbeeswarm" ,r-ggbeeswarm)
10595 ("r-ggplot2" ,r-ggplot2)
10596 ("r-matrix" ,r-matrix)
10598 ("r-s4vectors" ,r-s4vectors)
10599 ("r-singlecellexperiment" ,r-singlecellexperiment)
10600 ("r-summarizedexperiment" ,r-summarizedexperiment)
10601 ("r-viridis" ,r-viridis)))
10602 (home-page "https://github.com/davismcc/scater")
10603 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10604 (description "This package provides a collection of tools for doing
10605 various analyses of single-cell RNA-seq gene expression data, with a focus on
10607 (license license:gpl2+)))
10609 (define-public r-scran
10616 (uri (bioconductor-uri "scran" version))
10619 "17mknpkvs7mgnlbf2hv9k7rwbx2vlg60yrwfyb8nn3nxsb6vm7yn"))))
10620 (build-system r-build-system)
10622 `(("r-beachmat" ,r-beachmat)
10624 ("r-biocgenerics" ,r-biocgenerics)
10625 ("r-biocneighbors" ,r-biocneighbors)
10626 ("r-biocparallel" ,r-biocparallel)
10627 ("r-biocsingular" ,r-biocsingular)
10628 ("r-delayedarray" ,r-delayedarray)
10629 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10630 ("r-dqrng" ,r-dqrng)
10631 ("r-dynamictreecut" ,r-dynamictreecut)
10632 ("r-edger" ,r-edger)
10633 ("r-igraph" ,r-igraph)
10634 ("r-limma" ,r-limma)
10635 ("r-matrix" ,r-matrix)
10637 ("r-s4vectors" ,r-s4vectors)
10638 ("r-scater" ,r-scater)
10639 ("r-singlecellexperiment" ,r-singlecellexperiment)
10640 ("r-statmod" ,r-statmod)
10641 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10642 (home-page "https://bioconductor.org/packages/scran")
10643 (synopsis "Methods for single-cell RNA-Seq data analysis")
10644 (description "This package implements a variety of low-level analyses of
10645 single-cell RNA-seq data. Methods are provided for normalization of
10646 cell-specific biases, assignment of cell cycle phase, and detection of highly
10647 variable and significantly correlated genes.")
10648 (license license:gpl3)))
10650 (define-public r-delayedmatrixstats
10652 (name "r-delayedmatrixstats")
10657 (uri (bioconductor-uri "DelayedMatrixStats" version))
10660 "0632ypndblrgzfk8k98rr8c6m2r0zwzf02pzvlrhcp9bj1pvqbrz"))))
10662 `((upstream-name . "DelayedMatrixStats")))
10663 (build-system r-build-system)
10665 `(("r-biocparallel" ,r-biocparallel)
10666 ("r-delayedarray" ,r-delayedarray)
10667 ("r-hdf5array" ,r-hdf5array)
10668 ("r-iranges" ,r-iranges)
10669 ("r-matrix" ,r-matrix)
10670 ("r-matrixstats" ,r-matrixstats)
10671 ("r-s4vectors" ,r-s4vectors)))
10672 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10673 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10675 "This package provides a port of the @code{matrixStats} API for use with
10676 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10677 contains high-performing functions operating on rows and columns of
10678 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10679 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10680 are optimized per data type and for subsetted calculations such that both
10681 memory usage and processing time is minimized.")
10682 (license license:expat)))
10684 (define-public r-phangorn
10686 (name "r-phangorn")
10691 (uri (cran-uri "phangorn" version))
10694 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
10695 (build-system r-build-system)
10698 ("r-fastmatch" ,r-fastmatch)
10699 ("r-igraph" ,r-igraph)
10700 ("r-magrittr" ,r-magrittr)
10701 ("r-matrix" ,r-matrix)
10702 ("r-quadprog" ,r-quadprog)
10703 ("r-rcpp" ,r-rcpp)))
10704 (home-page "https://github.com/KlausVigo/phangorn")
10705 (synopsis "Phylogenetic analysis in R")
10707 "Phangorn is a package for phylogenetic analysis in R. It supports
10708 estimation of phylogenetic trees and networks using Maximum Likelihood,
10709 Maximum Parsimony, distance methods and Hadamard conjugation.")
10710 (license license:gpl2+)))
10712 (define-public r-dropbead
10713 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10716 (name "r-dropbead")
10717 (version (string-append "0-" revision "." (string-take commit 7)))
10721 (uri (git-reference
10722 (url "https://github.com/rajewsky-lab/dropbead.git")
10724 (file-name (git-file-name name version))
10727 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10728 (build-system r-build-system)
10730 `(("r-ggplot2" ,r-ggplot2)
10731 ("r-rcolorbrewer" ,r-rcolorbrewer)
10732 ("r-gridextra" ,r-gridextra)
10733 ("r-gplots" ,r-gplots)
10734 ("r-plyr" ,r-plyr)))
10735 (home-page "https://github.com/rajewsky-lab/dropbead")
10736 (synopsis "Basic exploration and analysis of Drop-seq data")
10737 (description "This package offers a quick and straight-forward way to
10738 explore and perform basic analysis of single cell sequencing data coming from
10739 droplet sequencing. It has been particularly tailored for Drop-seq.")
10740 (license license:gpl3))))
10742 (define htslib-for-sambamba
10743 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10746 (name "htslib-for-sambamba")
10747 (version (string-append "1.3.1-1." (string-take commit 9)))
10751 (uri (git-reference
10752 (url "https://github.com/lomereiter/htslib.git")
10754 (file-name (string-append "htslib-" version "-checkout"))
10757 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10759 `(("autoconf" ,autoconf)
10760 ("automake" ,automake)
10761 ,@(package-native-inputs htslib))))))
10763 (define-public sambamba
10770 (uri (git-reference
10771 (url "https://github.com/lomereiter/sambamba.git")
10772 (commit (string-append "v" version))))
10773 (file-name (string-append name "-" version "-checkout"))
10776 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10777 (build-system gnu-build-system)
10779 `(#:tests? #f ; there is no test target
10780 #:parallel-build? #f ; not supported
10782 (modify-phases %standard-phases
10783 (delete 'configure)
10784 (add-after 'unpack 'fix-ldc-version
10786 (substitute* "gen_ldc_version_info.py"
10787 (("/usr/bin/env.*") (which "python3")))
10788 (substitute* "Makefile"
10789 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10790 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10792 (add-after 'unpack 'place-biod-and-undead
10793 (lambda* (#:key inputs #:allow-other-keys)
10794 (copy-recursively (assoc-ref inputs "biod") "BioD")
10795 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10797 (add-after 'unpack 'unbundle-prerequisites
10799 (substitute* "Makefile"
10800 (("htslib/libhts.a lz4/lib/liblz4.a")
10802 ((" lz4-static htslib-static") ""))
10805 (lambda* (#:key outputs #:allow-other-keys)
10806 (let* ((out (assoc-ref outputs "out"))
10807 (bin (string-append out "/bin")))
10809 (install-file "bin/sambamba" bin)
10816 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10819 (uri (git-reference
10820 (url "https://github.com/biod/BioD.git")
10822 (file-name (string-append "biod-"
10823 (string-take commit 9)
10827 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10829 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10832 (uri (git-reference
10833 (url "https://github.com/biod/undeaD.git")
10835 (file-name (string-append "undead-"
10836 (string-take commit 9)
10840 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10843 ("htslib" ,htslib-for-sambamba)))
10844 (home-page "http://lomereiter.github.io/sambamba")
10845 (synopsis "Tools for working with SAM/BAM data")
10846 (description "Sambamba is a high performance modern robust and
10847 fast tool (and library), written in the D programming language, for
10848 working with SAM and BAM files. Current parallelised functionality is
10849 an important subset of samtools functionality, including view, index,
10850 sort, markdup, and depth.")
10851 (license license:gpl2+)))
10853 (define-public ritornello
10855 (name "ritornello")
10859 (uri (git-reference
10860 (url "https://github.com/KlugerLab/Ritornello.git")
10861 (commit (string-append "v" version))))
10862 (file-name (git-file-name name version))
10865 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10866 (build-system gnu-build-system)
10868 `(#:tests? #f ; there are no tests
10870 (modify-phases %standard-phases
10871 (add-after 'unpack 'patch-samtools-references
10872 (lambda* (#:key inputs #:allow-other-keys)
10873 (substitute* '("src/SamStream.h"
10875 (("<sam.h>") "<samtools/sam.h>"))
10877 (delete 'configure)
10879 (lambda* (#:key inputs outputs #:allow-other-keys)
10880 (let* ((out (assoc-ref outputs "out"))
10881 (bin (string-append out "/bin/")))
10883 (install-file "bin/Ritornello" bin)
10886 `(("samtools" ,samtools-0.1)
10890 (home-page "https://github.com/KlugerLab/Ritornello")
10891 (synopsis "Control-free peak caller for ChIP-seq data")
10892 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10893 signal processing that can accurately call binding events without the need to
10894 do a pair total DNA input or IgG control sample. It has been tested for use
10895 with narrow binding events such as transcription factor ChIP-seq.")
10896 (license license:gpl3+)))
10898 (define-public trim-galore
10900 (name "trim-galore")
10905 (uri (git-reference
10906 (url "https://github.com/FelixKrueger/TrimGalore.git")
10908 (file-name (git-file-name name version))
10911 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
10912 (build-system gnu-build-system)
10914 `(#:tests? #f ; no tests
10916 (modify-phases %standard-phases
10917 (replace 'configure
10919 ;; Trim Galore tries to figure out what version of Python
10920 ;; cutadapt is using by looking at the shebang. Of course that
10921 ;; doesn't work, because cutadapt is wrapped in a shell script.
10922 (substitute* "trim_galore"
10923 (("my \\$python_return.*")
10924 "my $python_return = \"Python 3.999\";\n"))
10927 (add-after 'unpack 'hardcode-tool-references
10928 (lambda* (#:key inputs #:allow-other-keys)
10929 (substitute* "trim_galore"
10930 (("\\$path_to_cutadapt = 'cutadapt'")
10931 (string-append "$path_to_cutadapt = '"
10932 (assoc-ref inputs "cutadapt")
10934 (("\\$compression_path = \"gzip\"")
10935 (string-append "$compression_path = \""
10936 (assoc-ref inputs "gzip")
10939 (string-append "\""
10940 (assoc-ref inputs "gzip")
10943 (string-append "\""
10944 (assoc-ref inputs "pigz")
10948 (lambda* (#:key outputs #:allow-other-keys)
10949 (let ((bin (string-append (assoc-ref outputs "out")
10952 (install-file "trim_galore" bin)
10958 ("cutadapt" ,cutadapt)))
10960 `(("unzip" ,unzip)))
10961 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10962 (synopsis "Wrapper around Cutadapt and FastQC")
10963 (description "Trim Galore! is a wrapper script to automate quality and
10964 adapter trimming as well as quality control, with some added functionality to
10965 remove biased methylation positions for RRBS sequence files.")
10966 (license license:gpl3+)))
10968 (define-public gess
10974 (uri (string-append "http://compbio.uthscsa.edu/"
10976 "gess-" version ".src.tar.gz"))
10979 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10980 (build-system gnu-build-system)
10982 `(#:tests? #f ; no tests
10984 (modify-phases %standard-phases
10985 (delete 'configure)
10988 (lambda* (#:key inputs outputs #:allow-other-keys)
10989 (let* ((python (assoc-ref inputs "python"))
10990 (out (assoc-ref outputs "out"))
10991 (bin (string-append out "/bin/"))
10992 (target (string-append
10994 ,(version-major+minor
10995 (package-version python))
10996 "/site-packages/gess/")))
10998 (copy-recursively "." target)
10999 ;; Make GESS.py executable
11000 (chmod (string-append target "GESS.py") #o555)
11001 ;; Add Python shebang to the top and make Matplotlib
11003 (substitute* (string-append target "GESS.py")
11004 (("\"\"\"Description:" line)
11005 (string-append "#!" (which "python") "
11007 matplotlib.use('Agg')
11009 ;; Make sure GESS has all modules in its path
11010 (wrap-program (string-append target "GESS.py")
11011 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11013 (symlink (string-append target "GESS.py")
11014 (string-append bin "GESS.py"))
11017 `(("python" ,python-2)
11018 ("python2-pysam" ,python2-pysam)
11019 ("python2-scipy" ,python2-scipy)
11020 ("python2-numpy" ,python2-numpy)
11021 ("python2-networkx" ,python2-networkx)
11022 ("python2-biopython" ,python2-biopython)))
11023 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11024 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11026 "GESS is an implementation of a novel computational method to detect de
11027 novo exon-skipping events directly from raw RNA-seq data without the prior
11028 knowledge of gene annotation information. GESS stands for the graph-based
11029 exon-skipping scanner detection scheme.")
11030 (license license:bsd-3)))
11032 (define-public phylip
11039 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11040 "download/phylip-" version ".tar.gz"))
11043 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11044 (build-system gnu-build-system)
11046 `(#:tests? #f ; no check target
11047 #:make-flags (list "-f" "Makefile.unx" "install")
11048 #:parallel-build? #f ; not supported
11050 (modify-phases %standard-phases
11051 (add-after 'unpack 'enter-dir
11052 (lambda _ (chdir "src") #t))
11053 (delete 'configure)
11055 (lambda* (#:key inputs outputs #:allow-other-keys)
11056 (let ((target (string-append (assoc-ref outputs "out")
11059 (for-each (lambda (file)
11060 (install-file file target))
11061 (find-files "../exe" ".*")))
11063 (home-page "http://evolution.genetics.washington.edu/phylip/")
11064 (synopsis "Tools for inferring phylogenies")
11065 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11066 programs for inferring phylogenies (evolutionary trees).")
11067 (license license:bsd-2)))
11076 (uri (string-append "https://integrativemodeling.org/"
11077 version "/download/imp-" version ".tar.gz"))
11080 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11081 (build-system cmake-build-system)
11083 `(;; FIXME: Some tests fail because they produce warnings, others fail
11084 ;; because the PYTHONPATH does not include the modeller's directory.
11092 ("python" ,python-2)))
11094 `(("python2-numpy" ,python2-numpy)
11095 ("python2-scipy" ,python2-scipy)
11096 ("python2-pandas" ,python2-pandas)
11097 ("python2-scikit-learn" ,python2-scikit-learn)
11098 ("python2-networkx" ,python2-networkx)))
11099 (home-page "https://integrativemodeling.org")
11100 (synopsis "Integrative modeling platform")
11101 (description "IMP's broad goal is to contribute to a comprehensive
11102 structural characterization of biomolecules ranging in size and complexity
11103 from small peptides to large macromolecular assemblies, by integrating data
11104 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11105 Python toolbox for solving complex modeling problems, and a number of
11106 applications for tackling some common problems in a user-friendly way.")
11107 ;; IMP is largely available under the GNU Lesser GPL; see the file
11108 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11109 ;; available under the GNU GPL (see the file COPYING.GPL).
11110 (license (list license:lgpl2.1+
11113 (define-public tadbit
11119 (uri (git-reference
11120 (url "https://github.com/3DGenomes/TADbit.git")
11121 (commit (string-append "v" version))))
11122 (file-name (git-file-name name version))
11125 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11126 (build-system python-build-system)
11128 `(;; Tests are included and must be run after installation, but
11129 ;; they are incomplete and thus cannot be run.
11133 (modify-phases %standard-phases
11134 (add-after 'unpack 'fix-problems-with-setup.py
11135 (lambda* (#:key outputs #:allow-other-keys)
11136 ;; setup.py opens these files for writing
11137 (chmod "_pytadbit/_version.py" #o664)
11138 (chmod "README.rst" #o664)
11140 ;; Don't attempt to install the bash completions to
11141 ;; the home directory.
11142 (rename-file "extras/.bash_completion"
11144 (substitute* "setup.py"
11145 (("\\(path.expanduser\\('~'\\)")
11146 (string-append "(\""
11147 (assoc-ref outputs "out")
11148 "/etc/bash_completion.d\""))
11149 (("extras/\\.bash_completion")
11153 ;; TODO: add Chimera for visualization
11156 ("python2-scipy" ,python2-scipy)
11157 ("python2-numpy" ,python2-numpy)
11158 ("python2-matplotlib" ,python2-matplotlib)
11159 ("python2-pysam" ,python2-pysam)))
11160 (home-page "https://3dgenomes.github.io/TADbit/")
11161 (synopsis "Analyze, model, and explore 3C-based data")
11163 "TADbit is a complete Python library to deal with all steps to analyze,
11164 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11165 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11166 correct interaction matrices, identify and compare the so-called
11167 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11168 interaction matrices, and finally, extract structural properties from the
11169 models. TADbit is complemented by TADkit for visualizing 3D models.")
11170 (license license:gpl3+)))
11172 (define-public kentutils
11175 ;; 302.1.0 is out, but the only difference is the inclusion of
11176 ;; pre-built binaries.
11177 (version "302.0.0")
11181 (uri (git-reference
11182 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11183 (commit (string-append "v" version))))
11184 (file-name (git-file-name name version))
11187 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11188 (modules '((guix build utils)
11193 ;; Only the contents of the specified directories are free
11194 ;; for all uses, so we remove the rest. "hg/autoSql" and
11195 ;; "hg/autoXml" are nominally free, but they depend on a
11196 ;; library that is built from the sources in "hg/lib",
11197 ;; which is nonfree.
11198 (let ((free (list "." ".."
11199 "utils" "lib" "inc" "tagStorm"
11200 "parasol" "htslib"))
11201 (directory? (lambda (file)
11202 (eq? 'directory (stat:type (stat file))))))
11203 (for-each (lambda (file)
11204 (and (directory? file)
11205 (delete-file-recursively file)))
11206 (map (cut string-append "src/" <>)
11209 (not (member file free)))))))
11210 ;; Only make the utils target, not the userApps target,
11211 ;; because that requires libraries we won't build.
11212 (substitute* "Makefile"
11213 ((" userApps") " utils"))
11214 ;; Only build libraries that are free.
11215 (substitute* "src/makefile"
11216 (("DIRS =.*") "DIRS =\n")
11217 (("cd jkOwnLib.*") "")
11220 (substitute* "src/utils/makefile"
11221 ;; These tools depend on "jkhgap.a", which is part of the
11222 ;; nonfree "src/hg/lib" directory.
11223 (("raSqlQuery") "")
11224 (("pslLiftSubrangeBlat") "")
11226 ;; Do not build UCSC tools, which may require nonfree
11228 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11230 (build-system gnu-build-system)
11232 `( ;; There is no global test target and the test target for
11233 ;; individual tools depends on input files that are not
11237 (modify-phases %standard-phases
11238 (add-after 'unpack 'fix-permissions
11239 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11240 (add-after 'unpack 'fix-paths
11242 (substitute* "Makefile"
11243 (("/bin/echo") (which "echo")))
11245 (add-after 'unpack 'prepare-samtabix
11246 (lambda* (#:key inputs #:allow-other-keys)
11247 (copy-recursively (assoc-ref inputs "samtabix")
11250 (delete 'configure)
11252 (lambda* (#:key outputs #:allow-other-keys)
11253 (let ((bin (string-append (assoc-ref outputs "out")
11255 (copy-recursively "bin" bin))
11261 (uri (git-reference
11262 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11263 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11266 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11272 ("mariadb" ,mariadb)
11273 ("openssl" ,openssl)))
11274 (home-page "http://genome.cse.ucsc.edu/index.html")
11275 (synopsis "Assorted bioinformatics utilities")
11276 (description "This package provides the kentUtils, a selection of
11277 bioinformatics utilities used in combination with the UCSC genome
11279 ;; Only a subset of the sources are released under a non-copyleft
11280 ;; free software license. All other sources are removed in a
11281 ;; snippet. See this bug report for an explanation of how the
11282 ;; license statements apply:
11283 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11284 (license (license:non-copyleft
11285 "http://genome.ucsc.edu/license/"
11286 "The contents of this package are free for all uses."))))
11288 (define-public f-seq
11289 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11293 (version (string-append "1.1-" revision "." (string-take commit 7)))
11296 (uri (git-reference
11297 (url "https://github.com/aboyle/F-seq.git")
11299 (file-name (string-append name "-" version))
11302 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11303 (modules '((guix build utils)))
11304 ;; Remove bundled Java library archives.
11307 (for-each delete-file (find-files "lib" ".*"))
11309 (build-system ant-build-system)
11311 `(#:tests? #f ; no tests included
11313 (modify-phases %standard-phases
11315 (lambda* (#:key inputs outputs #:allow-other-keys)
11316 (let* ((target (assoc-ref outputs "out"))
11317 (bin (string-append target "/bin"))
11318 (doc (string-append target "/share/doc/f-seq"))
11319 (lib (string-append target "/lib")))
11322 (substitute* "bin/linux/fseq"
11323 (("java") (which "java"))
11324 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11325 (string-append (assoc-ref inputs "java-commons-cli")
11326 "/share/java/commons-cli.jar"))
11328 (string-append "REALDIR=" bin "\n")))
11329 (install-file "README.txt" doc)
11330 (install-file "bin/linux/fseq" bin)
11331 (install-file "build~/fseq.jar" lib)
11332 (copy-recursively "lib" lib)
11336 ("java-commons-cli" ,java-commons-cli)))
11337 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11338 (synopsis "Feature density estimator for high-throughput sequence tags")
11340 "F-Seq is a software package that generates a continuous tag sequence
11341 density estimation allowing identification of biologically meaningful sites
11342 such as transcription factor binding sites (ChIP-seq) or regions of open
11343 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11345 (license license:gpl3+))))
11347 (define-public bismark
11354 (uri (git-reference
11355 (url "https://github.com/FelixKrueger/Bismark.git")
11357 (file-name (string-append name "-" version "-checkout"))
11360 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11361 (build-system perl-build-system)
11363 `(#:tests? #f ; there are no tests
11364 #:modules ((guix build utils)
11367 (guix build perl-build-system))
11369 (modify-phases %standard-phases
11370 ;; The bundled plotly.js is minified.
11371 (add-after 'unpack 'replace-plotly.js
11372 (lambda* (#:key inputs #:allow-other-keys)
11373 (let* ((file (assoc-ref inputs "plotly.js"))
11374 (installed "plotly/plotly.js"))
11375 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11376 (call-with-output-file installed
11377 (cut dump-port minified <>))))
11379 (delete 'configure)
11382 (lambda* (#:key inputs outputs #:allow-other-keys)
11383 (let* ((out (assoc-ref outputs "out"))
11384 (bin (string-append out "/bin"))
11385 (share (string-append out "/share/bismark"))
11386 (docdir (string-append out "/share/doc/bismark"))
11387 (docs '("Docs/Bismark_User_Guide.html"))
11388 (scripts '("bismark"
11389 "bismark_genome_preparation"
11390 "bismark_methylation_extractor"
11393 "coverage2cytosine"
11394 "deduplicate_bismark"
11395 "filter_non_conversion"
11398 "NOMe_filtering")))
11399 (substitute* "bismark2report"
11400 (("\\$RealBin/plotly")
11401 (string-append share "/plotly")))
11405 (for-each (lambda (file) (install-file file bin))
11407 (for-each (lambda (file) (install-file file docdir))
11409 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11410 (copy-recursively "plotly"
11411 (string-append share "/plotly"))
11413 ;; Fix references to gunzip
11414 (substitute* (map (lambda (file)
11415 (string-append bin "/" file))
11418 (string-append "\"" (assoc-ref inputs "gzip")
11419 "/bin/gunzip -c")))
11423 ("perl-carp" ,perl-carp)
11424 ("perl-getopt-long" ,perl-getopt-long)))
11429 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11430 "v1.39.4/dist/plotly.js"))
11432 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11433 ("uglify-js" ,uglify-js)))
11434 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11435 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11436 (description "Bismark is a program to map bisulfite treated sequencing
11437 reads to a genome of interest and perform methylation calls in a single step.
11438 The output can be easily imported into a genome viewer, such as SeqMonk, and
11439 enables a researcher to analyse the methylation levels of their samples
11440 straight away. Its main features are:
11443 @item Bisulfite mapping and methylation calling in one single step
11444 @item Supports single-end and paired-end read alignments
11445 @item Supports ungapped and gapped alignments
11446 @item Alignment seed length, number of mismatches etc are adjustable
11447 @item Output discriminates between cytosine methylation in CpG, CHG
11450 (license license:gpl3+)))
11452 (define-public paml
11458 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11459 "paml" version ".tgz"))
11462 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11463 (modules '((guix build utils)))
11464 ;; Remove Windows binaries
11467 (for-each delete-file (find-files "." "\\.exe$"))
11469 (build-system gnu-build-system)
11471 `(#:tests? #f ; there are no tests
11472 #:make-flags '("CC=gcc")
11474 (modify-phases %standard-phases
11475 (replace 'configure
11477 (substitute* "src/BFdriver.c"
11478 (("/bin/bash") (which "bash")))
11482 (lambda* (#:key outputs #:allow-other-keys)
11483 (let ((tools '("baseml" "basemlg" "codeml"
11484 "pamp" "evolver" "yn00" "chi2"))
11485 (bin (string-append (assoc-ref outputs "out") "/bin"))
11486 (docdir (string-append (assoc-ref outputs "out")
11487 "/share/doc/paml")))
11489 (for-each (lambda (file) (install-file file bin)) tools)
11490 (copy-recursively "../doc" docdir)
11492 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11493 (synopsis "Phylogentic analysis by maximum likelihood")
11494 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11495 contains a few programs for model fitting and phylogenetic tree reconstruction
11496 using nucleotide or amino-acid sequence data.")
11498 (license license:gpl3)))
11500 (define-public kallisto
11506 (uri (git-reference
11507 (url "https://github.com/pachterlab/kallisto.git")
11508 (commit (string-append "v" version))))
11509 (file-name (git-file-name name version))
11512 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11513 (build-system cmake-build-system)
11515 `(#:tests? #f ; no "check" target
11517 (modify-phases %standard-phases
11518 (add-after 'unpack 'do-not-use-bundled-htslib
11520 (substitute* "CMakeLists.txt"
11521 (("^ExternalProject_Add" m)
11522 (string-append "if (NEVER)\n" m))
11524 (string-append ")\nendif(NEVER)"))
11525 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11526 (string-append "# " m)))
11527 (substitute* "src/CMakeLists.txt"
11528 (("target_link_libraries\\(kallisto kallisto_core pthread \
11529 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11530 "target_link_libraries(kallisto kallisto_core pthread hts)")
11531 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11537 (home-page "http://pachterlab.github.io/kallisto/")
11538 (synopsis "Near-optimal RNA-Seq quantification")
11540 "Kallisto is a program for quantifying abundances of transcripts from
11541 RNA-Seq data, or more generally of target sequences using high-throughput
11542 sequencing reads. It is based on the novel idea of pseudoalignment for
11543 rapidly determining the compatibility of reads with targets, without the need
11544 for alignment. Pseudoalignment of reads preserves the key information needed
11545 for quantification, and kallisto is therefore not only fast, but also as
11546 accurate as existing quantification tools.")
11547 (license license:bsd-2)))
11549 (define-public libgff
11555 (uri (git-reference
11556 (url "https://github.com/Kingsford-Group/libgff.git")
11557 (commit (string-append "v" version))))
11558 (file-name (git-file-name name version))
11561 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11562 (build-system cmake-build-system)
11563 (arguments `(#:tests? #f)) ; no tests included
11564 (home-page "https://github.com/Kingsford-Group/libgff")
11565 (synopsis "Parser library for reading/writing GFF files")
11566 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11567 code that is used in the Cufflinks codebase. The goal of this library is to
11568 provide this functionality without the necessity of drawing in a heavy-weight
11569 dependency like SeqAn.")
11570 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11572 (define-public libdivsufsort
11574 (name "libdivsufsort")
11578 (uri (git-reference
11579 (url "https://github.com/y-256/libdivsufsort.git")
11581 (file-name (git-file-name name version))
11584 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11585 (build-system cmake-build-system)
11587 '(#:tests? #f ; there are no tests
11589 ;; Needed for rapmap and sailfish.
11590 '("-DBUILD_DIVSUFSORT64=ON")))
11591 (home-page "https://github.com/y-256/libdivsufsort")
11592 (synopsis "Lightweight suffix-sorting library")
11593 (description "libdivsufsort is a software library that implements a
11594 lightweight suffix array construction algorithm. This library provides a
11595 simple and an efficient C API to construct a suffix array and a
11596 Burrows-Wheeler transformed string from a given string over a constant-size
11597 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11598 bytes of memory space, where n is the length of the string.")
11599 (license license:expat)))
11601 (define-public sailfish
11607 (uri (git-reference
11608 (url "https://github.com/kingsfordgroup/sailfish.git")
11609 (commit (string-append "v" version))))
11610 (file-name (git-file-name name version))
11613 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11614 (modules '((guix build utils)))
11617 ;; Delete bundled headers for eigen3.
11618 (delete-file-recursively "include/eigen3/")
11620 (build-system cmake-build-system)
11622 `(#:configure-flags
11623 (list (string-append "-DBOOST_INCLUDEDIR="
11624 (assoc-ref %build-inputs "boost")
11626 (string-append "-DBOOST_LIBRARYDIR="
11627 (assoc-ref %build-inputs "boost")
11629 (string-append "-DBoost_LIBRARIES="
11630 "-lboost_iostreams "
11631 "-lboost_filesystem "
11636 "-lboost_program_options")
11637 "-DBoost_FOUND=TRUE"
11638 ;; Don't download RapMap---we already have it!
11639 "-DFETCHED_RAPMAP=1")
11640 ;; Tests must be run after installation and the location of the test
11641 ;; data file must be overridden. But the tests fail. It looks like
11642 ;; they are not really meant to be run.
11645 (modify-phases %standard-phases
11646 ;; Boost cannot be found, even though it's right there.
11647 (add-after 'unpack 'do-not-look-for-boost
11648 (lambda* (#:key inputs #:allow-other-keys)
11649 (substitute* "CMakeLists.txt"
11650 (("find_package\\(Boost 1\\.53\\.0") "#"))
11652 (add-after 'unpack 'do-not-assign-to-macro
11654 (substitute* "include/spdlog/details/format.cc"
11655 (("const unsigned CHAR_WIDTH = 1;") ""))
11657 (add-after 'unpack 'prepare-rapmap
11658 (lambda* (#:key inputs #:allow-other-keys)
11659 (let ((src "external/install/src/rapmap/")
11660 (include "external/install/include/rapmap/")
11661 (rapmap (assoc-ref inputs "rapmap")))
11662 (mkdir-p "/tmp/rapmap")
11664 (assoc-ref inputs "rapmap")
11666 "--strip-components=1")
11669 (for-each (lambda (file)
11670 (install-file file src))
11671 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11672 (copy-recursively "/tmp/rapmap/include" include))
11674 (add-after 'unpack 'use-system-libraries
11675 (lambda* (#:key inputs #:allow-other-keys)
11676 (substitute* '("src/SailfishIndexer.cpp"
11677 "src/SailfishUtils.cpp"
11678 "src/SailfishQuantify.cpp"
11679 "src/FASTAParser.cpp"
11681 "include/SailfishUtils.hpp"
11682 "include/SailfishIndex.hpp"
11683 "include/CollapsedEMOptimizer.hpp"
11684 "src/CollapsedEMOptimizer.cpp")
11685 (("#include \"jellyfish/config.h\"") ""))
11686 (substitute* "src/CMakeLists.txt"
11687 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11688 (string-append (assoc-ref inputs "jellyfish")
11689 "/include/jellyfish-" ,(package-version jellyfish)))
11690 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11691 (string-append (assoc-ref inputs "jellyfish")
11692 "/lib/libjellyfish-2.0.a"))
11693 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11694 (string-append (assoc-ref inputs "libdivsufsort")
11695 "/lib/libdivsufsort.so"))
11696 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11697 (string-append (assoc-ref inputs "libdivsufsort")
11698 "/lib/libdivsufsort64.so")))
11699 (substitute* "CMakeLists.txt"
11700 ;; Don't prefer static libs
11701 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11702 (("find_package\\(Jellyfish.*") "")
11703 (("ExternalProject_Add\\(libjellyfish") "message(")
11704 (("ExternalProject_Add\\(libgff") "message(")
11705 (("ExternalProject_Add\\(libsparsehash") "message(")
11706 (("ExternalProject_Add\\(libdivsufsort") "message("))
11708 ;; Ensure that Eigen headers can be found
11709 (setenv "CPLUS_INCLUDE_PATH"
11710 (string-append (getenv "CPLUS_INCLUDE_PATH")
11712 (assoc-ref inputs "eigen")
11713 "/include/eigen3"))
11718 ("jemalloc" ,jemalloc)
11719 ("jellyfish" ,jellyfish)
11720 ("sparsehash" ,sparsehash)
11723 (uri (git-reference
11724 (url "https://github.com/COMBINE-lab/RapMap.git")
11725 (commit (string-append "sf-v" version))))
11726 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11729 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11730 (modules '((guix build utils)))
11731 ;; These files are expected to be excluded.
11733 '(begin (delete-file-recursively "include/spdlog")
11734 (for-each delete-file '("include/xxhash.h"
11737 ("libdivsufsort" ,libdivsufsort)
11742 `(("pkg-config" ,pkg-config)))
11743 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11744 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11745 (description "Sailfish is a tool for genomic transcript quantification
11746 from RNA-seq data. It requires a set of target transcripts (either from a
11747 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11748 fasta file containing your reference transcripts and a (set of) fasta/fastq
11749 file(s) containing your reads.")
11750 (license license:gpl3+)))
11752 (define libstadenio-for-salmon
11754 (name "libstadenio")
11758 (uri (git-reference
11759 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11760 (commit (string-append "v" version))))
11761 (file-name (string-append name "-" version "-checkout"))
11764 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11765 (build-system gnu-build-system)
11766 (arguments '(#:parallel-tests? #f)) ; not supported
11770 `(("perl" ,perl))) ; for tests
11771 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11772 (synopsis "General purpose trace and experiment file library")
11773 (description "This package provides a library of file reading and writing
11774 code to provide a general purpose Trace file (and Experiment File) reading
11777 The following file formats are supported:
11780 @item SCF trace files
11781 @item ABI trace files
11782 @item ALF trace files
11783 @item ZTR trace files
11784 @item SFF trace archives
11785 @item SRF trace archives
11786 @item Experiment files
11787 @item Plain text files
11788 @item SAM/BAM sequence files
11789 @item CRAM sequence files
11791 (license license:bsd-3)))
11793 (define-public salmon
11799 (uri (git-reference
11800 (url "https://github.com/COMBINE-lab/salmon.git")
11801 (commit (string-append "v" version))))
11802 (file-name (git-file-name name version))
11805 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11806 (modules '((guix build utils)))
11809 ;; Delete bundled headers for eigen3.
11810 (delete-file-recursively "include/eigen3/")
11812 (build-system cmake-build-system)
11814 `(#:configure-flags
11815 (list (string-append "-DBOOST_INCLUDEDIR="
11816 (assoc-ref %build-inputs "boost")
11818 (string-append "-DBOOST_LIBRARYDIR="
11819 (assoc-ref %build-inputs "boost")
11821 (string-append "-DBoost_LIBRARIES="
11822 "-lboost_iostreams "
11823 "-lboost_filesystem "
11828 "-lboost_program_options")
11829 "-DBoost_FOUND=TRUE"
11830 "-DTBB_LIBRARIES=tbb tbbmalloc"
11831 ;; Don't download RapMap---we already have it!
11832 "-DFETCHED_RAPMAP=1")
11834 (modify-phases %standard-phases
11835 ;; Boost cannot be found, even though it's right there.
11836 (add-after 'unpack 'do-not-look-for-boost
11837 (lambda* (#:key inputs #:allow-other-keys)
11838 (substitute* "CMakeLists.txt"
11839 (("find_package\\(Boost 1\\.59\\.0") "#"))
11841 (add-after 'unpack 'do-not-phone-home
11843 (substitute* "src/Salmon.cpp"
11844 (("getVersionMessage\\(\\)") "\"\""))
11846 (add-after 'unpack 'prepare-rapmap
11847 (lambda* (#:key inputs #:allow-other-keys)
11848 (let ((src "external/install/src/rapmap/")
11849 (include "external/install/include/rapmap/")
11850 (rapmap (assoc-ref inputs "rapmap")))
11853 (copy-recursively (string-append rapmap "/src") src)
11854 (copy-recursively (string-append rapmap "/include") include)
11855 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11856 "external/install/include/rapmap/FastxParser.hpp"
11857 "external/install/include/rapmap/concurrentqueue.h"
11858 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11859 "external/install/src/rapmap/FastxParser.cpp"
11860 "external/install/src/rapmap/xxhash.c"))
11861 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11863 (add-after 'unpack 'use-system-libraries
11864 (lambda* (#:key inputs #:allow-other-keys)
11865 (substitute* "CMakeLists.txt"
11866 ;; Don't prefer static libs
11867 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11868 (("set\\(TBB_LIBRARIES") "message(")
11869 ;; Don't download anything
11870 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11871 (("externalproject_add\\(libcereal") "message(")
11872 (("externalproject_add\\(libgff") "message(")
11873 (("externalproject_add\\(libtbb") "message(")
11874 (("externalproject_add\\(libdivsufsort") "message(")
11875 (("externalproject_add\\(libstadenio") "message(")
11876 (("externalproject_add_step\\(") "message("))
11877 (substitute* "src/CMakeLists.txt"
11878 (("add_dependencies") "#")
11879 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11880 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11881 "/lib/libstaden-read.so"))
11882 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11883 (string-append (assoc-ref inputs "libdivsufsort")
11884 "/lib/libdivsufsort.so"))
11885 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11886 (string-append (assoc-ref inputs "libdivsufsort")
11887 "/lib/libdivsufsort64.so"))
11888 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11890 ;; Ensure that all headers can be found
11891 (setenv "CPLUS_INCLUDE_PATH"
11892 (string-append (getenv "CPLUS_INCLUDE_PATH")
11894 (assoc-ref inputs "eigen")
11895 "/include/eigen3"))
11897 (string-append (assoc-ref inputs "eigen")
11898 "/include/eigen3"))
11900 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11901 ;; run. It only exists after the install phase.
11902 (add-after 'unpack 'fix-tests
11904 (substitute* "src/CMakeLists.txt"
11905 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11906 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11915 (uri (git-reference
11916 (url "https://github.com/COMBINE-lab/RapMap.git")
11917 (commit (string-append "salmon-v" version))))
11918 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11921 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
11922 ("jemalloc" ,jemalloc)
11925 ("libdivsufsort" ,libdivsufsort)
11926 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11930 `(("pkg-config" ,pkg-config)))
11931 (home-page "https://github.com/COMBINE-lab/salmon")
11932 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11933 (description "Salmon is a program to produce highly-accurate,
11934 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11935 its accuracy and speed via a number of different innovations, including the
11936 use of lightweight alignments (accurate but fast-to-compute proxies for
11937 traditional read alignments) and massively-parallel stochastic collapsed
11938 variational inference.")
11939 (license license:gpl3+)))
11941 (define-public python-loompy
11943 (name "python-loompy")
11945 ;; The tarball on Pypi does not include the tests.
11948 (uri (git-reference
11949 (url "https://github.com/linnarsson-lab/loompy.git")
11951 (file-name (git-file-name name version))
11954 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
11955 (build-system python-build-system)
11958 (modify-phases %standard-phases
11961 (setenv "PYTHONPATH"
11962 (string-append (getcwd) ":"
11963 (getenv "PYTHONPATH")))
11964 (invoke "pytest" "tests")
11967 `(("python-h5py" ,python-h5py)
11968 ("python-numpy" ,python-numpy)
11969 ("python-pandas" ,python-pandas)
11970 ("python-scipy" ,python-scipy)))
11972 `(("python-pytest" ,python-pytest)))
11973 (home-page "https://github.com/linnarsson-lab/loompy")
11974 (synopsis "Work with .loom files for single-cell RNA-seq data")
11975 (description "The loom file format is an efficient format for very large
11976 omics datasets, consisting of a main matrix, optional additional layers, a
11977 variable number of row and column annotations. Loom also supports sparse
11978 graphs. This library makes it easy to work with @file{.loom} files for
11979 single-cell RNA-seq data.")
11980 (license license:bsd-3)))
11982 ;; pigx-scrnaseq does not work with the latest version of loompy.
11983 (define-public python-loompy-for-pigx-scrnaseq
11984 (package (inherit python-loompy)
11985 (name "python-loompy")
11989 (uri (git-reference
11990 (url "https://github.com/linnarsson-lab/loompy.git")
11991 (commit (string-append "v" version))))
11992 (file-name (git-file-name name version))
11995 "0pjyl532pl8sbv71yci6h0agchn0naw2qjcwj50n6afrsahbsag3"))))
11997 (arguments '(#:tests? #f))))
11999 ;; We cannot use the latest commit because it requires Java 9.
12000 (define-public java-forester
12001 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12004 (name "java-forester")
12005 (version (string-append "0-" revision "." (string-take commit 7)))
12008 (uri (git-reference
12009 (url "https://github.com/cmzmasek/forester.git")
12011 (file-name (string-append name "-" version "-checkout"))
12014 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12015 (modules '((guix build utils)))
12018 ;; Delete bundled jars and pre-built classes
12019 (delete-file-recursively "forester/java/resources")
12020 (delete-file-recursively "forester/java/classes")
12021 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12022 ;; Delete bundled applications
12023 (delete-file-recursively "forester_applications")
12025 (build-system ant-build-system)
12027 `(#:tests? #f ; there are none
12029 #:modules ((guix build ant-build-system)
12031 (guix build java-utils)
12035 (modify-phases %standard-phases
12036 (add-after 'unpack 'chdir
12037 (lambda _ (chdir "forester/java") #t))
12038 (add-after 'chdir 'fix-dependencies
12040 (chmod "build.xml" #o664)
12041 (call-with-output-file "build.xml.new"
12045 (with-input-from-file "build.xml"
12046 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12047 `(;; Remove all unjar tags to avoid repacking classes.
12048 (unjar . ,(lambda _ '()))
12049 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12050 (*text* . ,(lambda (_ txt) txt))))
12052 (rename-file "build.xml.new" "build.xml")
12054 ;; FIXME: itext is difficult to package as it depends on a few
12055 ;; unpackaged libraries.
12056 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12058 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12059 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12060 (("pdf_written_to = PdfExporter.*")
12061 "throw new IOException(\"PDF export is not available.\");"))
12063 ;; There is no install target
12064 (replace 'install (install-jars ".")))))
12066 `(("java-commons-codec" ,java-commons-codec)
12067 ("java-openchart2" ,java-openchart2)))
12068 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12069 (synopsis "Phylogenomics libraries for Java")
12070 (description "Forester is a collection of Java libraries for
12071 phylogenomics and evolutionary biology research. It includes support for
12072 reading, writing, and exporting phylogenetic trees.")
12073 (license license:lgpl2.1+))))
12075 (define-public java-forester-1.005
12077 (name "java-forester")
12081 (uri (string-append "http://search.maven.org/remotecontent?"
12082 "filepath=org/biojava/thirdparty/forester/"
12083 version "/forester-" version "-sources.jar"))
12084 (file-name (string-append name "-" version ".jar"))
12087 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12088 (build-system ant-build-system)
12090 `(#:tests? #f ; there are none
12092 #:modules ((guix build ant-build-system)
12094 (guix build java-utils)
12098 (modify-phases %standard-phases
12099 (add-after 'unpack 'fix-dependencies
12100 (lambda* (#:key inputs #:allow-other-keys)
12101 (call-with-output-file "build.xml"
12105 (with-input-from-file "src/build.xml"
12106 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12107 `(;; Remove all unjar tags to avoid repacking classes.
12108 (unjar . ,(lambda _ '()))
12109 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12110 (*text* . ,(lambda (_ txt) txt))))
12112 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12113 "synth_look_and_feel_1.xml")
12114 (copy-file (assoc-ref inputs "phyloxml.xsd")
12116 (substitute* "build.xml"
12117 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12118 "synth_look_and_feel_1.xml")
12119 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12122 ;; FIXME: itext is difficult to package as it depends on a few
12123 ;; unpackaged libraries.
12124 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12126 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12127 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12128 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12129 (("pdf_written_to = PdfExporter.*")
12130 "throw new IOException(\"PDF export is not available.\"); /*")
12131 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12132 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12134 (add-after 'unpack 'delete-pre-built-classes
12135 (lambda _ (delete-file-recursively "src/classes") #t))
12136 ;; There is no install target
12137 (replace 'install (install-jars ".")))))
12139 `(("java-commons-codec" ,java-commons-codec)
12140 ("java-openchart2" ,java-openchart2)))
12141 ;; The source archive does not contain the resources.
12146 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12147 "b61cc2dcede0bede317db362472333115756b8c6/"
12148 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12149 (file-name (string-append name "-phyloxml-" version ".xsd"))
12152 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12153 ("synth_look_and_feel_1.xml"
12156 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12157 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12158 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12159 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12162 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12163 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12164 (synopsis "Phylogenomics libraries for Java")
12165 (description "Forester is a collection of Java libraries for
12166 phylogenomics and evolutionary biology research. It includes support for
12167 reading, writing, and exporting phylogenetic trees.")
12168 (license license:lgpl2.1+)))
12170 (define-public java-biojava-core
12172 (name "java-biojava-core")
12176 (uri (git-reference
12177 (url "https://github.com/biojava/biojava")
12178 (commit (string-append "biojava-" version))))
12179 (file-name (string-append name "-" version "-checkout"))
12182 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12183 (build-system ant-build-system)
12186 #:jar-name "biojava-core.jar"
12187 #:source-dir "biojava-core/src/main/java/"
12188 #:test-dir "biojava-core/src/test"
12189 ;; These tests seem to require internet access.
12190 #:test-exclude (list "**/SearchIOTest.java"
12191 "**/BlastXMLParserTest.java"
12192 "**/GenbankCookbookTest.java"
12193 "**/GenbankProxySequenceReaderTest.java")
12195 (modify-phases %standard-phases
12196 (add-before 'build 'copy-resources
12198 (copy-recursively "biojava-core/src/main/resources"
12201 (add-before 'check 'copy-test-resources
12203 (copy-recursively "biojava-core/src/test/resources"
12204 "build/test-classes")
12207 `(("java-log4j-api" ,java-log4j-api)
12208 ("java-log4j-core" ,java-log4j-core)
12209 ("java-slf4j-api" ,java-slf4j-api)
12210 ("java-slf4j-simple" ,java-slf4j-simple)))
12212 `(("java-junit" ,java-junit)
12213 ("java-hamcrest-core" ,java-hamcrest-core)))
12214 (home-page "http://biojava.org")
12215 (synopsis "Core libraries of Java framework for processing biological data")
12216 (description "BioJava is a project dedicated to providing a Java framework
12217 for processing biological data. It provides analytical and statistical
12218 routines, parsers for common file formats, reference implementations of
12219 popular algorithms, and allows the manipulation of sequences and 3D
12220 structures. The goal of the biojava project is to facilitate rapid
12221 application development for bioinformatics.
12223 This package provides the core libraries.")
12224 (license license:lgpl2.1+)))
12226 (define-public java-biojava-phylo
12227 (package (inherit java-biojava-core)
12228 (name "java-biojava-phylo")
12229 (build-system ant-build-system)
12232 #:jar-name "biojava-phylo.jar"
12233 #:source-dir "biojava-phylo/src/main/java/"
12234 #:test-dir "biojava-phylo/src/test"
12236 (modify-phases %standard-phases
12237 (add-before 'build 'copy-resources
12239 (copy-recursively "biojava-phylo/src/main/resources"
12242 (add-before 'check 'copy-test-resources
12244 (copy-recursively "biojava-phylo/src/test/resources"
12245 "build/test-classes")
12248 `(("java-log4j-api" ,java-log4j-api)
12249 ("java-log4j-core" ,java-log4j-core)
12250 ("java-slf4j-api" ,java-slf4j-api)
12251 ("java-slf4j-simple" ,java-slf4j-simple)
12252 ("java-biojava-core" ,java-biojava-core)
12253 ("java-forester" ,java-forester)))
12255 `(("java-junit" ,java-junit)
12256 ("java-hamcrest-core" ,java-hamcrest-core)))
12257 (home-page "http://biojava.org")
12258 (synopsis "Biojava interface to the forester phylogenomics library")
12259 (description "The phylo module provides a biojava interface layer to the
12260 forester phylogenomics library for constructing phylogenetic trees.")))
12262 (define-public java-biojava-alignment
12263 (package (inherit java-biojava-core)
12264 (name "java-biojava-alignment")
12265 (build-system ant-build-system)
12268 #:jar-name "biojava-alignment.jar"
12269 #:source-dir "biojava-alignment/src/main/java/"
12270 #:test-dir "biojava-alignment/src/test"
12272 (modify-phases %standard-phases
12273 (add-before 'build 'copy-resources
12275 (copy-recursively "biojava-alignment/src/main/resources"
12278 (add-before 'check 'copy-test-resources
12280 (copy-recursively "biojava-alignment/src/test/resources"
12281 "build/test-classes")
12284 `(("java-log4j-api" ,java-log4j-api)
12285 ("java-log4j-core" ,java-log4j-core)
12286 ("java-slf4j-api" ,java-slf4j-api)
12287 ("java-slf4j-simple" ,java-slf4j-simple)
12288 ("java-biojava-core" ,java-biojava-core)
12289 ("java-biojava-phylo" ,java-biojava-phylo)
12290 ("java-forester" ,java-forester)))
12292 `(("java-junit" ,java-junit)
12293 ("java-hamcrest-core" ,java-hamcrest-core)))
12294 (home-page "http://biojava.org")
12295 (synopsis "Biojava API for genetic sequence alignment")
12296 (description "The alignment module of BioJava provides an API that
12300 @item implementations of dynamic programming algorithms for sequence
12302 @item reading and writing of popular alignment file formats;
12303 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12306 (define-public java-biojava-core-4.0
12307 (package (inherit java-biojava-core)
12308 (name "java-biojava-core")
12312 (uri (git-reference
12313 (url "https://github.com/biojava/biojava")
12314 (commit (string-append "biojava-" version))))
12315 (file-name (string-append name "-" version "-checkout"))
12318 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12320 (define-public java-biojava-phylo-4.0
12321 (package (inherit java-biojava-core-4.0)
12322 (name "java-biojava-phylo")
12323 (build-system ant-build-system)
12326 #:jar-name "biojava-phylo.jar"
12327 #:source-dir "biojava-phylo/src/main/java/"
12328 #:test-dir "biojava-phylo/src/test"
12330 (modify-phases %standard-phases
12331 (add-before 'build 'copy-resources
12333 (copy-recursively "biojava-phylo/src/main/resources"
12336 (add-before 'check 'copy-test-resources
12338 (copy-recursively "biojava-phylo/src/test/resources"
12339 "build/test-classes")
12342 `(("java-log4j-api" ,java-log4j-api)
12343 ("java-log4j-core" ,java-log4j-core)
12344 ("java-slf4j-api" ,java-slf4j-api)
12345 ("java-slf4j-simple" ,java-slf4j-simple)
12346 ("java-biojava-core" ,java-biojava-core-4.0)
12347 ("java-forester" ,java-forester-1.005)))
12349 `(("java-junit" ,java-junit)
12350 ("java-hamcrest-core" ,java-hamcrest-core)))
12351 (home-page "http://biojava.org")
12352 (synopsis "Biojava interface to the forester phylogenomics library")
12353 (description "The phylo module provides a biojava interface layer to the
12354 forester phylogenomics library for constructing phylogenetic trees.")))
12356 (define-public java-biojava-alignment-4.0
12357 (package (inherit java-biojava-core-4.0)
12358 (name "java-biojava-alignment")
12359 (build-system ant-build-system)
12362 #:jar-name "biojava-alignment.jar"
12363 #:source-dir "biojava-alignment/src/main/java/"
12364 #:test-dir "biojava-alignment/src/test"
12366 (modify-phases %standard-phases
12367 (add-before 'build 'copy-resources
12369 (copy-recursively "biojava-alignment/src/main/resources"
12372 (add-before 'check 'copy-test-resources
12374 (copy-recursively "biojava-alignment/src/test/resources"
12375 "build/test-classes")
12378 `(("java-log4j-api" ,java-log4j-api)
12379 ("java-log4j-core" ,java-log4j-core)
12380 ("java-slf4j-api" ,java-slf4j-api)
12381 ("java-slf4j-simple" ,java-slf4j-simple)
12382 ("java-biojava-core" ,java-biojava-core-4.0)
12383 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12384 ("java-forester" ,java-forester-1.005)))
12386 `(("java-junit" ,java-junit)
12387 ("java-hamcrest-core" ,java-hamcrest-core)))
12388 (home-page "http://biojava.org")
12389 (synopsis "Biojava API for genetic sequence alignment")
12390 (description "The alignment module of BioJava provides an API that
12394 @item implementations of dynamic programming algorithms for sequence
12396 @item reading and writing of popular alignment file formats;
12397 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12400 (define-public dropseq-tools
12402 (name "dropseq-tools")
12407 (uri "http://mccarrolllab.com/download/1276/")
12408 (file-name (string-append "dropseq-tools-" version ".zip"))
12411 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12412 ;; Delete bundled libraries
12413 (modules '((guix build utils)))
12416 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12417 (delete-file-recursively "3rdParty")
12419 (build-system ant-build-system)
12421 `(#:tests? #f ; test data are not included
12422 #:test-target "test"
12423 #:build-target "all"
12424 #:source-dir "public/src/"
12427 (list (string-append "-Dpicard.executable.dir="
12428 (assoc-ref %build-inputs "java-picard")
12430 #:modules ((ice-9 match)
12433 (guix build java-utils)
12434 (guix build ant-build-system))
12436 (modify-phases %standard-phases
12437 ;; FIXME: fails with "java.io.FileNotFoundException:
12438 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12439 (delete 'generate-jar-indices)
12440 ;; All dependencies must be linked to "lib", because that's where
12441 ;; they will be searched for when the Class-Path property of the
12442 ;; manifest is computed.
12443 (add-after 'unpack 'record-references
12444 (lambda* (#:key inputs #:allow-other-keys)
12445 (mkdir-p "jar/lib")
12446 (let ((dirs (filter-map (match-lambda
12448 (if (and (string-prefix? "java-" name)
12449 (not (string=? name "java-testng")))
12452 (for-each (lambda (jar)
12453 (symlink jar (string-append "jar/lib/" (basename jar))))
12454 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12457 ;; There is no installation target
12459 (lambda* (#:key inputs outputs #:allow-other-keys)
12460 (let* ((out (assoc-ref outputs "out"))
12461 (bin (string-append out "/bin"))
12462 (share (string-append out "/share/java/"))
12463 (lib (string-append share "/lib/"))
12464 (scripts (list "BAMTagHistogram"
12465 "BAMTagofTagCounts"
12466 "BaseDistributionAtReadPosition"
12467 "CollapseBarcodesInPlace"
12468 "CollapseTagWithContext"
12470 "CreateIntervalsFiles"
12471 "DetectBeadSynthesisErrors"
12472 "DigitalExpression"
12473 "Drop-seq_alignment.sh"
12476 "GatherGeneGCLength"
12477 "GatherMolecularBarcodeDistributionByGene"
12478 "GatherReadQualityMetrics"
12481 "SelectCellsByNumTranscripts"
12482 "SingleCellRnaSeqMetricsCollector"
12483 "TagBamWithReadSequenceExtended"
12484 "TagReadWithGeneExon"
12485 "TagReadWithInterval"
12486 "TrimStartingSequence"
12487 "ValidateReference")))
12488 (for-each mkdir-p (list bin share lib))
12489 (install-file "dist/dropseq.jar" share)
12490 (for-each (lambda (script)
12491 (chmod script #o555)
12492 (install-file script bin))
12494 (substitute* (map (lambda (script)
12495 (string-append bin "/" script))
12497 (("^java") (which "java"))
12498 (("jar_deploy_dir=.*")
12499 (string-append "jar_deploy_dir=" share "\n"))))
12501 ;; FIXME: We do this after stripping jars because we don't want it to
12502 ;; copy all these jars and strip them. We only want to install
12503 ;; links. Arguably, this is a problem with the ant-build-system.
12504 (add-after 'strip-jar-timestamps 'install-links
12505 (lambda* (#:key outputs #:allow-other-keys)
12506 (let* ((out (assoc-ref outputs "out"))
12507 (share (string-append out "/share/java/"))
12508 (lib (string-append share "/lib/")))
12509 (for-each (lambda (jar)
12510 (symlink (readlink jar)
12511 (string-append lib (basename jar))))
12512 (find-files "jar/lib" "\\.jar$")))
12515 `(("jdk" ,icedtea-8)
12516 ("java-picard" ,java-picard-2.10.3)
12517 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12518 ("java-commons-math3" ,java-commons-math3)
12519 ("java-commons-jexl2" ,java-commons-jexl-2)
12520 ("java-commons-collections4" ,java-commons-collections4)
12521 ("java-commons-lang2" ,java-commons-lang)
12522 ("java-commons-io" ,java-commons-io)
12523 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12524 ("java-guava" ,java-guava)
12525 ("java-la4j" ,java-la4j)
12526 ("java-biojava-core" ,java-biojava-core-4.0)
12527 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12528 ("java-jdistlib" ,java-jdistlib)
12529 ("java-simple-xml" ,java-simple-xml)
12530 ("java-snakeyaml" ,java-snakeyaml)))
12533 ("java-testng" ,java-testng)))
12534 (home-page "http://mccarrolllab.com/dropseq/")
12535 (synopsis "Tools for Drop-seq analyses")
12536 (description "Drop-seq is a technology to enable biologists to
12537 analyze RNA expression genome-wide in thousands of individual cells at
12538 once. This package provides tools to perform Drop-seq analyses.")
12539 (license license:expat)))
12541 (define-public pigx-rnaseq
12543 (name "pigx-rnaseq")
12547 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12548 "releases/download/v" version
12549 "/pigx_rnaseq-" version ".tar.gz"))
12552 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12553 (build-system gnu-build-system)
12555 `(#:parallel-tests? #f ; not supported
12557 (modify-phases %standard-phases
12558 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12559 (add-after 'unpack 'disable-resource-intensive-test
12561 (substitute* "Makefile.in"
12562 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12563 (("^ tests/test_multiqc/test.sh") "")
12564 (("^ test.sh") ""))
12567 `(("coreutils" ,coreutils)
12570 ("snakemake" ,snakemake)
12572 ("multiqc" ,multiqc)
12574 ("trim-galore" ,trim-galore)
12576 ("samtools" ,samtools)
12577 ("r-minimal" ,r-minimal)
12578 ("r-rmarkdown" ,r-rmarkdown)
12579 ("r-ggplot2" ,r-ggplot2)
12580 ("r-ggrepel" ,r-ggrepel)
12581 ("r-gprofiler" ,r-gprofiler)
12582 ("r-deseq2" ,r-deseq2)
12584 ("r-knitr" ,r-knitr)
12585 ("r-pheatmap" ,r-pheatmap)
12586 ("r-corrplot" ,r-corrplot)
12587 ("r-reshape2" ,r-reshape2)
12588 ("r-plotly" ,r-plotly)
12589 ("r-scales" ,r-scales)
12590 ("r-summarizedexperiment" ,r-summarizedexperiment)
12591 ("r-crosstalk" ,r-crosstalk)
12592 ("r-tximport" ,r-tximport)
12593 ("r-rtracklayer" ,r-rtracklayer)
12594 ("r-rjson" ,r-rjson)
12596 ("ghc-pandoc" ,ghc-pandoc)
12597 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12598 ("python-wrapper" ,python-wrapper)
12599 ("python-pyyaml" ,python-pyyaml)))
12600 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12601 (synopsis "Analysis pipeline for RNA sequencing experiments")
12602 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12603 reporting for RNA sequencing experiments. It is easy to use and produces high
12604 quality reports. The inputs are reads files from the sequencing experiment,
12605 and a configuration file which describes the experiment. In addition to
12606 quality control of the experiment, the pipeline produces a differential
12607 expression report comparing samples in an easily configurable manner.")
12608 (license license:gpl3+)))
12610 (define-public pigx-chipseq
12612 (name "pigx-chipseq")
12616 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12617 "releases/download/v" version
12618 "/pigx_chipseq-" version ".tar.gz"))
12621 "0akbxdmsjsq5fzbwaap04hqjpsfgv1l6yrc2pwgbya1xgqvcq6vy"))))
12622 (build-system gnu-build-system)
12623 ;; parts of the tests rely on access to the network
12624 (arguments '(#:tests? #f))
12627 ("coreutils" ,coreutils)
12628 ("r-minimal" ,r-minimal)
12629 ("r-argparser" ,r-argparser)
12630 ("r-biocparallel" ,r-biocparallel)
12631 ("r-biostrings" ,r-biostrings)
12632 ("r-chipseq" ,r-chipseq)
12633 ("r-data-table" ,r-data-table)
12634 ("r-dplyr" ,r-dplyr)
12635 ("r-genomation" ,r-genomation)
12636 ("r-genomicalignments" ,r-genomicalignments)
12637 ("r-genomicranges" ,r-genomicranges)
12638 ("r-rsamtools" ,r-rsamtools)
12639 ("r-rtracklayer" ,r-rtracklayer)
12640 ("r-s4vectors" ,r-s4vectors)
12641 ("r-stringr" ,r-stringr)
12642 ("r-tibble" ,r-tibble)
12643 ("r-tidyr" ,r-tidyr)
12644 ("r-jsonlite" ,r-jsonlite)
12645 ("r-heatmaply" ,r-heatmaply)
12646 ("r-htmlwidgets" ,r-htmlwidgets)
12647 ("r-ggplot2" ,r-ggplot2)
12648 ("r-plotly" ,r-plotly)
12649 ("r-rmarkdown" ,r-rmarkdown)
12650 ("python-wrapper" ,python-wrapper)
12651 ("python-pyyaml" ,python-pyyaml)
12652 ("python-magic" ,python-magic)
12653 ("python-xlrd" ,python-xlrd)
12654 ("trim-galore" ,trim-galore)
12656 ("multiqc" ,multiqc)
12658 ("ghc-pandoc" ,ghc-pandoc)
12659 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12663 ("snakemake" ,snakemake)
12664 ("samtools" ,samtools)
12665 ("bedtools" ,bedtools)
12666 ("kentutils" ,kentutils)))
12668 `(("python-pytest" ,python-pytest)))
12669 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12670 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12671 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12672 calling and reporting for ChIP sequencing experiments. It is easy to use and
12673 produces high quality reports. The inputs are reads files from the sequencing
12674 experiment, and a configuration file which describes the experiment. In
12675 addition to quality control of the experiment, the pipeline enables to set up
12676 multiple peak calling analysis and allows the generation of a UCSC track hub
12677 in an easily configurable manner.")
12678 (license license:gpl3+)))
12680 (define-public pigx-bsseq
12682 (name "pigx-bsseq")
12686 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12687 "releases/download/v" version
12688 "/pigx_bsseq-" version ".tar.gz"))
12691 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12692 (build-system gnu-build-system)
12695 (modify-phases %standard-phases
12696 (add-before 'check 'set-timezone
12697 ;; The readr package is picky about timezones.
12698 (lambda* (#:key inputs #:allow-other-keys)
12699 (setenv "TZ" "UTC+1")
12701 (string-append (assoc-ref inputs "tzdata")
12702 "/share/zoneinfo"))
12705 `(("tzdata" ,tzdata)))
12707 `(("coreutils" ,coreutils)
12710 ("r-minimal" ,r-minimal)
12711 ("r-annotationhub" ,r-annotationhub)
12713 ("r-genomation" ,r-genomation)
12714 ("r-methylkit" ,r-methylkit)
12715 ("r-rtracklayer" ,r-rtracklayer)
12716 ("r-rmarkdown" ,r-rmarkdown)
12717 ("r-bookdown" ,r-bookdown)
12718 ("r-ggplot2" ,r-ggplot2)
12719 ("r-ggbio" ,r-ggbio)
12720 ("ghc-pandoc" ,ghc-pandoc)
12721 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12722 ("python-wrapper" ,python-wrapper)
12723 ("python-pyyaml" ,python-pyyaml)
12724 ("snakemake" ,snakemake)
12725 ("bismark" ,bismark)
12728 ("trim-galore" ,trim-galore)
12729 ("cutadapt" ,cutadapt)
12730 ("samtools" ,samtools)))
12731 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12732 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12733 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12734 data of bisulfite experiments; it produces reports on aggregate methylation
12735 and coverage and can be used to produce information on differential
12736 methylation and segmentation.")
12737 (license license:gpl3+)))
12739 (define-public pigx-scrnaseq
12741 (name "pigx-scrnaseq")
12745 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12746 "releases/download/v" version
12747 "/pigx_scrnaseq-" version ".tar.gz"))
12750 "0zv0sc5amivxhb95vx2gfx6l9bh7n80fh7h47dalnwxxnfvnzai4"))))
12751 (build-system gnu-build-system)
12753 `(#:configure-flags
12754 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12755 "/share/java/picard.jar")
12756 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12757 "/share/java/dropseq.jar"))))
12759 `(("coreutils" ,coreutils)
12761 ("dropseq-tools" ,dropseq-tools)
12763 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12764 ("java" ,icedtea-8)
12765 ("python-wrapper" ,python-wrapper)
12766 ("python-pyyaml" ,python-pyyaml)
12767 ("python-pandas" ,python-pandas)
12768 ("python-magic" ,python-magic)
12769 ("python-numpy" ,python-numpy)
12770 ("python-loompy" ,python-loompy-for-pigx-scrnaseq)
12771 ("ghc-pandoc" ,ghc-pandoc)
12772 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12773 ("samtools" ,samtools)
12774 ("snakemake" ,snakemake)
12776 ("r-minimal" ,r-minimal)
12777 ("r-argparser" ,r-argparser)
12778 ("r-cowplot" ,r-cowplot)
12779 ("r-data-table" ,r-data-table)
12780 ("r-delayedarray" ,r-delayedarray)
12781 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12782 ("r-dplyr" ,r-dplyr)
12783 ("r-dropbead" ,r-dropbead)
12785 ("r-genomicalignments" ,r-genomicalignments)
12786 ("r-genomicfiles" ,r-genomicfiles)
12787 ("r-genomicranges" ,r-genomicranges)
12788 ("r-ggplot2" ,r-ggplot2)
12789 ("r-hdf5array" ,r-hdf5array)
12790 ("r-pheatmap" ,r-pheatmap)
12791 ("r-rmarkdown" ,r-rmarkdown)
12792 ("r-rsamtools" ,r-rsamtools)
12793 ("r-rtracklayer" ,r-rtracklayer)
12794 ("r-rtsne" ,r-rtsne)
12795 ("r-scater" ,r-scater)
12796 ("r-scran" ,r-scran)
12797 ("r-singlecellexperiment" ,r-singlecellexperiment)
12798 ("r-stringr" ,r-stringr)
12799 ("r-yaml" ,r-yaml)))
12800 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12801 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12802 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12803 quality control for single cell RNA sequencing experiments. The inputs are
12804 read files from the sequencing experiment, and a configuration file which
12805 describes the experiment. It produces processed files for downstream analysis
12806 and interactive quality reports. The pipeline is designed to work with UMI
12808 (license license:gpl3+)))
12810 (define-public pigx
12816 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12817 "releases/download/v" version
12818 "/pigx-" version ".tar.gz"))
12821 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12822 (build-system gnu-build-system)
12824 `(("python" ,python)
12825 ("pigx-bsseq" ,pigx-bsseq)
12826 ("pigx-chipseq" ,pigx-chipseq)
12827 ("pigx-rnaseq" ,pigx-rnaseq)
12828 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12829 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12830 (synopsis "Analysis pipelines for genomics")
12831 (description "PiGx is a collection of genomics pipelines. It includes the
12832 following pipelines:
12835 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12836 @item PiGx RNAseq for RNAseq samples
12837 @item PiGx scRNAseq for single cell dropseq analysis
12838 @item PiGx ChIPseq for reads from ChIPseq experiments
12841 All pipelines are easily configured with a simple sample sheet and a
12842 descriptive settings file. The result is a set of comprehensive, interactive
12843 HTML reports with interesting findings about your samples.")
12844 (license license:gpl3+)))
12846 (define-public genrich
12852 (uri (git-reference
12853 (url "https://github.com/jsh58/Genrich.git")
12854 (commit (string-append "v" version))))
12857 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12858 (build-system gnu-build-system)
12860 `(#:tests? #f ; there are none
12862 (modify-phases %standard-phases
12863 (delete 'configure)
12865 (lambda* (#:key outputs #:allow-other-keys)
12866 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12870 (home-page "https://github.com/jsh58/Genrich")
12871 (synopsis "Detecting sites of genomic enrichment")
12872 (description "Genrich is a peak-caller for genomic enrichment
12873 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12874 following the assay and produces a file detailing peaks of significant
12876 (license license:expat)))
12878 (define-public mantis
12879 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12883 (version (git-version "0" revision commit))
12886 (uri (git-reference
12887 (url "https://github.com/splatlab/mantis.git")
12889 (file-name (git-file-name name version))
12892 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12893 (build-system cmake-build-system)
12894 (arguments '(#:tests? #f)) ; there are none
12896 `(("sdsl-lite" ,sdsl-lite)
12897 ("openssl" ,openssl)
12899 (home-page "https://github.com/splatlab/mantis")
12900 (synopsis "Large-scale sequence-search index data structure")
12901 (description "Mantis is a space-efficient data structure that can be
12902 used to index thousands of raw-read genomics experiments and facilitate
12903 large-scale sequence searches on those experiments. Mantis uses counting
12904 quotient filters instead of Bloom filters, enabling rapid index builds and
12905 queries, small indexes, and exact results, i.e., no false positives or
12906 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12907 representation, so it supports fast graph traversal and other topological
12908 analyses in addition to large-scale sequence-level searches.")
12909 ;; uses __uint128_t and inline assembly
12910 (supported-systems '("x86_64-linux"))
12911 (license license:bsd-3))))
12913 (define-public r-diversitree
12915 (name "r-diversitree")
12920 (uri (cran-uri "diversitree" version))
12923 "1jqfjmmaigq581l4zxysmkhld0xv6izlbr1hihf9zplkix36majc"))))
12924 (build-system r-build-system)
12926 `(("gfortran" ,gfortran)))
12927 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12930 ("r-desolve" ,r-desolve)
12932 ("r-subplex" ,r-subplex)))
12933 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
12934 (synopsis "Comparative 'phylogenetic' analyses of diversification")
12935 (description "This package contains a number of comparative \"phylogenetic\"
12936 methods, mostly focusing on analysing diversification and character evolution.
12937 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
12938 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
12939 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
12940 include Markov models of discrete and continuous trait evolution and constant
12941 rate speciation and extinction.")
12942 (license license:gpl2+)))
12944 (define-public sjcount
12945 ;; There is no tag for version 3.2, nor is there a release archive.
12946 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12950 (version (git-version "3.2" revision commit))
12953 (uri (git-reference
12954 (url "https://github.com/pervouchine/sjcount-full.git")
12956 (file-name (string-append name "-" version "-checkout"))
12959 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12960 (build-system gnu-build-system)
12962 `(#:tests? #f ; requires a 1.4G test file
12964 (list (string-append "SAMTOOLS_DIR="
12965 (assoc-ref %build-inputs "samtools")
12968 (modify-phases %standard-phases
12969 (replace 'configure
12970 (lambda* (#:key inputs #:allow-other-keys)
12971 (substitute* "makefile"
12972 (("-I \\$\\{SAMTOOLS_DIR\\}")
12973 (string-append "-I" (assoc-ref inputs "samtools")
12974 "/include/samtools"))
12975 (("-lz ") "-lz -lpthread "))
12978 (lambda* (#:key outputs #:allow-other-keys)
12979 (for-each (lambda (tool)
12981 (string-append (assoc-ref outputs "out")
12983 '("j_count" "b_count" "sjcount"))
12986 `(("samtools" ,samtools-0.1)
12988 (home-page "https://github.com/pervouchine/sjcount-full/")
12989 (synopsis "Annotation-agnostic splice junction counting pipeline")
12990 (description "Sjcount is a utility for fast quantification of splice
12991 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
12992 version does count multisplits.")
12993 (license license:gpl3+))))
12995 (define-public minimap2
13002 (uri (string-append "https://github.com/lh3/minimap2/"
13003 "releases/download/v" version "/"
13004 "minimap2-" version ".tar.bz2"))
13007 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13008 (build-system gnu-build-system)
13010 `(#:tests? #f ; there are none
13013 (let ((system ,(or (%current-target-system)
13014 (%current-system))))
13016 ((string-prefix? "x86_64" system)
13018 ((or (string-prefix? "armhf" system)
13019 (string-prefix? "aarch64" system))
13021 (_ "sse2only=1"))))
13023 (modify-phases %standard-phases
13024 (delete 'configure)
13026 (lambda* (#:key outputs #:allow-other-keys)
13027 (let* ((out (assoc-ref outputs "out"))
13028 (bin (string-append out "/bin"))
13029 (man (string-append out "/share/man/man1")))
13030 (install-file "minimap2" bin)
13032 (install-file "minimap2.1" man))
13036 (home-page "https://lh3.github.io/minimap2/")
13037 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13038 (description "Minimap2 is a versatile sequence alignment program that
13039 aligns DNA or mRNA sequences against a large reference database. Typical use
13043 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13044 @item finding overlaps between long reads with error rate up to ~15%;
13045 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13046 reads against a reference genome;
13047 @item aligning Illumina single- or paired-end reads;
13048 @item assembly-to-assembly alignment;
13049 @item full-genome alignment between two closely related species with
13050 divergence below ~15%.
13052 (license license:expat)))
13054 (define-public r-circus
13061 (uri (git-reference
13062 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13063 (commit (string-append "v" version))))
13064 (file-name (git-file-name name version))
13067 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13068 (build-system r-build-system)
13070 `(("r-annotationdbi" ,r-annotationdbi)
13071 ("r-annotationhub" ,r-annotationhub)
13072 ("r-biomart" ,r-biomart)
13073 ("r-data-table" ,r-data-table)
13075 ("r-genomicfeatures" ,r-genomicfeatures)
13076 ("r-genomicranges" ,r-genomicranges)
13077 ("r-ggplot2" ,r-ggplot2)
13079 ("r-iranges" ,r-iranges)
13080 ("r-rcolorbrewer" ,r-rcolorbrewer)
13081 ("r-rmysql" ,r-rmysql)
13082 ("r-s4vectors" ,r-s4vectors)
13083 ("r-stringr" ,r-stringr)
13084 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13086 `(("r-knitr" ,r-knitr)))
13087 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13088 (synopsis "Annotation, analysis and visualization of circRNA data")
13089 (description "Circus is an R package for annotation, analysis and
13090 visualization of circRNA data. Users can annotate their circRNA candidates
13091 with host genes, gene featrues they are spliced from, and discriminate between
13092 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13093 can be calculated, and a number of descriptive plots easily generated.")
13094 (license license:artistic2.0)))
13096 (define-public gffread
13097 ;; We cannot use the tagged release because it is not in sync with gclib.
13098 ;; See https://github.com/gpertea/gffread/issues/26
13099 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13103 (version (git-version "0.9.12" revision commit))
13107 (uri (git-reference
13108 (url "https://github.com/gpertea/gffread.git")
13110 (file-name (git-file-name name version))
13113 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13114 (build-system gnu-build-system)
13116 `(#:tests? #f ; no check target
13118 (list "GCLDIR=gclib")
13120 (modify-phases %standard-phases
13121 (delete 'configure)
13122 (add-after 'unpack 'copy-gclib-source
13123 (lambda* (#:key inputs #:allow-other-keys)
13125 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13127 ;; There is no install target
13129 (lambda* (#:key outputs #:allow-other-keys)
13130 (let* ((out (assoc-ref outputs "out"))
13131 (bin (string-append out "/bin")))
13132 (install-file "gffread" bin))
13136 ,(let ((version "0.10.3")
13137 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13141 (uri (git-reference
13142 (url "https://github.com/gpertea/gclib.git")
13144 (file-name (git-file-name "gclib" version))
13147 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13148 (home-page "https://github.com/gpertea/gffread/")
13149 (synopsis "Parse and convert GFF/GTF files")
13151 "This package provides a GFF/GTF file parsing utility providing format
13152 conversions, region filtering, FASTA sequence extraction and more.")
13153 ;; gffread is under Expat, but gclib is under Artistic 2.0
13154 (license (list license:expat
13155 license:artistic2.0)))))
13157 (define-public find-circ
13158 ;; The last release was in 2015. The license was clarified in 2017, so we
13159 ;; take the latest commit.
13160 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13164 (version (git-version "1.2" revision commit))
13168 (uri (git-reference
13169 (url "https://github.com/marvin-jens/find_circ.git")
13171 (file-name (git-file-name name version))
13174 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13175 (build-system gnu-build-system)
13177 `(#:tests? #f ; there are none
13179 ;; There is no actual build system.
13180 (modify-phases %standard-phases
13181 (delete 'configure)
13184 (lambda* (#:key outputs #:allow-other-keys)
13185 (let* ((out (assoc-ref outputs "out"))
13186 (bin (string-append out "/bin"))
13187 (path (getenv "PYTHONPATH")))
13188 (for-each (lambda (script)
13189 (install-file script bin)
13190 (wrap-program (string-append bin "/" script)
13191 `("PYTHONPATH" ":" prefix (,path))))
13196 "unmapped2anchors.py")))
13199 `(("python2" ,python-2)
13200 ("python2-pysam" ,python2-pysam)
13201 ("python2-numpy" ,python2-numpy)))
13202 (home-page "https://github.com/marvin-jens/find_circ")
13203 (synopsis "circRNA detection from RNA-seq reads")
13204 (description "This package provides tools to detect head-to-tail
13205 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13207 (license license:gpl3))))
13209 (define-public python-scanpy
13211 (name "python-scanpy")
13213 ;; Fetch from git because the pypi tarball does not include tests.
13217 (uri (git-reference
13218 (url "https://github.com/theislab/scanpy.git")
13220 (file-name (git-file-name name version))
13223 "0zn6x6c0cnm1a20i6isigwb51g3pr9zpjk8r1minjqnxi5yc9pm4"))))
13224 (build-system python-build-system)
13227 (modify-phases %standard-phases
13229 (lambda* (#:key inputs #:allow-other-keys)
13230 ;; These tests require Internet access.
13231 (delete-file-recursively "scanpy/tests/notebooks")
13232 (delete-file "scanpy/tests/test_clustering.py")
13234 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13235 (delete-file "scanpy/tests/test_plotting.py")
13236 (delete-file "scanpy/tests/test_preprocessing.py")
13237 (delete-file "scanpy/tests/test_read_10x.py")
13239 (setenv "PYTHONPATH"
13240 (string-append (getcwd) ":"
13241 (getenv "PYTHONPATH")))
13245 `(("python-anndata" ,python-anndata)
13246 ("python-h5py" ,python-h5py)
13247 ("python-igraph" ,python-igraph)
13248 ("python-joblib" ,python-joblib)
13249 ("python-louvain" ,python-louvain)
13250 ("python-matplotlib" ,python-matplotlib)
13251 ("python-natsort" ,python-natsort)
13252 ("python-networkx" ,python-networkx)
13253 ("python-numba" ,python-numba)
13254 ("python-pandas" ,python-pandas)
13255 ("python-scikit-learn" ,python-scikit-learn)
13256 ("python-scipy" ,python-scipy)
13257 ("python-seaborn" ,python-seaborn)
13258 ("python-statsmodels" ,python-statsmodels)
13259 ("python-tables" ,python-tables)))
13261 `(("python-pytest" ,python-pytest)))
13262 (home-page "https://github.com/theislab/scanpy")
13263 (synopsis "Single-Cell Analysis in Python.")
13264 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13265 expression data. It includes preprocessing, visualization, clustering,
13266 pseudotime and trajectory inference and differential expression testing. The
13267 Python-based implementation efficiently deals with datasets of more than one
13269 (license license:bsd-3)))
13271 (define-public python-bbknn
13273 (name "python-bbknn")
13278 (uri (pypi-uri "bbknn" version))
13281 "1qgdganvj3lyxj84v7alm23b9vqhwpn8z0115qndpnpy90qxynwz"))))
13282 (build-system python-build-system)
13284 `(("python-annoy" ,python-annoy)
13285 ("python-cython" ,python-cython)
13286 ("python-faiss" ,python-faiss)
13287 ("python-numpy" ,python-numpy)
13288 ("python-scanpy" ,python-scanpy)))
13289 (home-page "https://github.com/Teichlab/bbknn")
13290 (synopsis "Batch balanced KNN")
13291 (description "BBKNN is a batch effect removal tool that can be directly
13292 used in the Scanpy workflow. It serves as an alternative to
13293 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13294 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13295 technical artifacts are present in the data, they will make it challenging to
13296 link corresponding cell types across different batches. BBKNN actively
13297 combats this effect by splitting your data into batches and finding a smaller
13298 number of neighbours for each cell within each of the groups. This helps
13299 create connections between analogous cells in different batches without
13300 altering the counts or PCA space.")
13301 (license license:expat)))
13303 (define-public gffcompare
13304 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13307 (name "gffcompare")
13308 (version (git-version "0.10.15" revision commit))
13312 (uri (git-reference
13313 (url "https://github.com/gpertea/gffcompare/")
13315 (file-name (git-file-name name version))
13317 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13318 (build-system gnu-build-system)
13320 `(#:tests? #f ; no check target
13322 (modify-phases %standard-phases
13323 (delete 'configure)
13324 (add-before 'build 'copy-gclib-source
13325 (lambda* (#:key inputs #:allow-other-keys)
13328 (assoc-ref inputs "gclib-source") "../gclib")
13331 (lambda* (#:key outputs #:allow-other-keys)
13332 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13333 (install-file "gffcompare" bin)
13336 `(("gclib-source" ; see 'README.md' of gffcompare
13337 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13340 (version (git-version "0.10.3" revision commit)))
13343 (uri (git-reference
13344 (url "https://github.com/gpertea/gclib/")
13346 (file-name (git-file-name name version))
13348 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13349 (home-page "https://github.com/gpertea/gffcompare/")
13350 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13352 "@code{gffcompare} is a tool that can:
13354 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13355 (Cufflinks, Stringtie);
13356 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13357 resulted from assembly of different samples);
13358 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13359 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13363 license:expat ;license for gffcompare
13364 license:artistic2.0))))) ;license for gclib
13366 (define-public python-intervaltree
13368 (name "python-intervaltree")
13373 (uri (pypi-uri "intervaltree" version))
13376 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13377 (build-system python-build-system)
13378 ;; FIXME: error when collecting tests
13379 (arguments '(#:tests? #f))
13381 `(("python-sortedcontainers" ,python-sortedcontainers)))
13383 `(("python-pytest" ,python-pytest)))
13384 (home-page "https://github.com/chaimleib/intervaltree")
13385 (synopsis "Editable interval tree data structure")
13387 "This package provides a mutable, self-balancing interval tree
13388 implementation for Python. Queries may be by point, by range overlap, or by
13389 range envelopment. This library was designed to allow tagging text and time
13390 intervals, where the intervals include the lower bound but not the upper
13392 (license license:asl2.0)))
13394 (define-public python-pypairix
13396 (name "python-pypairix")
13401 (uri (pypi-uri "pypairix" version))
13404 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13405 (build-system python-build-system)
13406 ;; FIXME: the tests fail because test.support cannot be loaded:
13407 ;; ImportError: cannot import name 'support'
13408 (arguments '(#:tests? #f))
13411 (home-page "https://github.com/4dn-dcic/pairix")
13412 (synopsis "Support for querying pairix-indexed bgzipped text files")
13414 "Pypairix is a Python module for fast querying on a pairix-indexed
13415 bgzipped text file that contains a pair of genomic coordinates per line.")
13416 (license license:expat)))
13418 (define-public python-pyfaidx
13420 (name "python-pyfaidx")
13421 (version "0.5.4.2")
13425 (uri (pypi-uri "pyfaidx" version))
13428 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13429 (build-system python-build-system)
13431 `(("python-setuptools" ,python-setuptools)
13432 ("python-six" ,python-six)))
13433 (home-page "http://mattshirley.com")
13434 (synopsis "Random access to fasta subsequences")
13436 "This package provides procedures for efficient pythonic random access to
13437 fasta subsequences.")
13438 (license license:bsd-3)))
13440 (define-public python-cooler
13442 (name "python-cooler")
13447 (uri (pypi-uri "cooler" version))
13450 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13451 (build-system python-build-system)
13453 `(("python-biopython" ,python-biopython)
13454 ("python-click" ,python-click)
13455 ("python-cytoolz" ,python-cytoolz)
13456 ("python-dask" ,python-dask)
13457 ("python-h5py" ,python-h5py)
13458 ("python-multiprocess" ,python-multiprocess)
13459 ("python-pandas" ,python-pandas)
13460 ("python-pyfaidx" ,python-pyfaidx)
13461 ("python-pypairix" ,python-pypairix)
13462 ("python-pysam" ,python-pysam)
13463 ("python-scipy" ,python-scipy)))
13465 `(("python-mock" ,python-mock)
13466 ("python-nose" ,python-nose)
13467 ("python-numpydoc" ,python-numpydoc)
13468 ("python-sphinx" ,python-sphinx)))
13469 (home-page "https://github.com/mirnylab/cooler")
13470 (synopsis "Sparse binary format for genomic interaction matrices")
13472 "Cooler is a support library for a sparse, compressed, binary persistent
13473 storage format, called @code{cool}, used to store genomic interaction data,
13474 such as Hi-C contact matrices.")
13475 (license license:bsd-3)))
13477 (define-public python-hicexplorer
13479 (name "python-hicexplorer")
13483 ;; The latest version is not available on Pypi.
13485 (uri (git-reference
13486 (url "https://github.com/deeptools/HiCExplorer.git")
13488 (file-name (git-file-name name version))
13491 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13492 (build-system python-build-system)
13495 (modify-phases %standard-phases
13496 (add-after 'unpack 'loosen-up-requirements
13498 (substitute* "setup.py"
13502 `(("python-biopython" ,python-biopython)
13503 ("python-configparser" ,python-configparser)
13504 ("python-cooler" ,python-cooler)
13505 ("python-future" ,python-future)
13506 ("python-intervaltree" ,python-intervaltree)
13507 ("python-jinja2" ,python-jinja2)
13508 ("python-matplotlib" ,python-matplotlib)
13509 ("python-numpy" ,python-numpy)
13510 ("python-pandas" ,python-pandas)
13511 ("python-pybigwig" ,python-pybigwig)
13512 ("python-pysam" ,python-pysam)
13513 ("python-scipy" ,python-scipy)
13514 ("python-six" ,python-six)
13515 ("python-tables" ,python-tables)
13516 ("python-unidecode" ,python-unidecode)))
13517 (home-page "http://hicexplorer.readthedocs.io")
13518 (synopsis "Process, analyze and visualize Hi-C data")
13520 "HiCExplorer is a powerful and easy to use set of tools to process,
13521 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13522 contact matrices, correction of contacts, TAD detection, A/B compartments,
13523 merging, reordering or chromosomes, conversion from different formats
13524 including cooler and detection of long-range contacts. Moreover, it allows
13525 the visualization of multiple contact matrices along with other types of data
13526 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13527 genomic scores), long range contacts and the visualization of viewpoints.")
13528 (license license:gpl3)))
13530 (define-public python-pygenometracks
13532 (name "python-pygenometracks")
13537 (uri (pypi-uri "pyGenomeTracks" version))
13540 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13541 (build-system python-build-system)
13543 `(("python-configparser" ,python-configparser)
13544 ("python-future" ,python-future)
13545 ("python-hicexplorer" ,python-hicexplorer)
13546 ("python-intervaltree" ,python-intervaltree)
13547 ("python-matplotlib" ,python-matplotlib)
13548 ("python-numpy" ,python-numpy)
13549 ("python-pybigwig" ,python-pybigwig)))
13551 `(("python-pytest" ,python-pytest)))
13552 (home-page "https://pygenometracks.readthedocs.io")
13553 (synopsis "Program and library to plot beautiful genome browser tracks")
13555 "This package aims to produce high-quality genome browser tracks that
13556 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13557 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13558 pyGenomeTracks can make plots with or without Hi-C data.")
13559 (license license:gpl3+)))
13561 (define-public python-hic2cool
13563 (name "python-hic2cool")
13568 (uri (pypi-uri "hic2cool" version))
13571 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13572 (build-system python-build-system)
13573 (arguments '(#:tests? #f)) ; no tests included
13575 `(("python-cooler" ,python-cooler)))
13576 (home-page "https://github.com/4dn-dcic/hic2cool")
13577 (synopsis "Converter for .hic and .cool files")
13579 "This package provides a converter between @code{.hic} files (from
13580 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13581 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13583 (license license:expat)))
13585 (define-public r-pore
13593 (string-append "mirror://sourceforge/rpore/" version
13594 "/poRe_" version ".tar.gz"))
13596 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13597 (properties `((upstream-name . "poRe")))
13598 (build-system r-build-system)
13600 `(("r-bit64" ,r-bit64)
13601 ("r-data-table" ,r-data-table)
13602 ("r-rhdf5" ,r-rhdf5)
13603 ("r-shiny" ,r-shiny)
13604 ("r-svdialogs" ,r-svdialogs)))
13605 (home-page "https://sourceforge.net/projects/rpore/")
13606 (synopsis "Visualize Nanopore sequencing data")
13608 "This package provides graphical user interfaces to organize and visualize Nanopore
13610 ;; This is free software but the license variant is unclear:
13611 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13612 (license license:bsd-3)))
13614 (define-public r-xbioc
13615 (let ((revision "1")
13616 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13619 (version (git-version "0.1.16" revision commit))
13622 (uri (git-reference
13623 (url "https://github.com/renozao/xbioc.git")
13625 (file-name (git-file-name name version))
13628 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13629 (build-system r-build-system)
13631 `(("r-annotationdbi" ,r-annotationdbi)
13632 ("r-assertthat" ,r-assertthat)
13633 ("r-biobase" ,r-biobase)
13634 ("r-biocmanager" ,r-biocmanager)
13635 ("r-digest" ,r-digest)
13636 ("r-pkgmaker" ,r-pkgmaker)
13638 ("r-reshape2" ,r-reshape2)
13639 ("r-stringr" ,r-stringr)))
13640 (home-page "https://github.com/renozao/xbioc/")
13641 (synopsis "Extra base functions for Bioconductor")
13642 (description "This package provides extra utility functions to perform
13643 common tasks in the analysis of omics data, leveraging and enhancing features
13644 provided by Bioconductor packages.")
13645 (license license:gpl3+))))
13647 (define-public r-cssam
13648 (let ((revision "1")
13649 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13652 (version (git-version "1.4" revision commit))
13655 (uri (git-reference
13656 (url "https://github.com/shenorrLab/csSAM.git")
13658 (file-name (git-file-name name version))
13661 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13662 (build-system r-build-system)
13664 `(("r-formula" ,r-formula)
13665 ("r-ggplot2" ,r-ggplot2)
13666 ("r-pkgmaker" ,r-pkgmaker)
13668 ("r-rngtools" ,r-rngtools)
13669 ("r-scales" ,r-scales)))
13670 (home-page "https://github.com/shenorrLab/csSAM/")
13671 (synopsis "Cell type-specific statistical analysis of microarray")
13672 (description "This package implements the method csSAM that computes
13673 cell-specific differential expression from measured cell proportions using
13676 (license license:lgpl2.1+))))
13678 (define-public r-bseqsc
13679 (let ((revision "1")
13680 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13683 (version (git-version "1.0" revision commit))
13686 (uri (git-reference
13687 (url "https://github.com/shenorrLab/bseqsc.git")
13689 (file-name (git-file-name name version))
13692 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13693 (build-system r-build-system)
13695 `(("r-abind" ,r-abind)
13696 ("r-annotationdbi" ,r-annotationdbi)
13697 ("r-biobase" ,r-biobase)
13698 ("r-cssam" ,r-cssam)
13699 ("r-dplyr" ,r-dplyr)
13700 ("r-e1071" ,r-e1071)
13701 ("r-edger" ,r-edger)
13702 ("r-ggplot2" ,r-ggplot2)
13704 ("r-openxlsx" ,r-openxlsx)
13705 ("r-pkgmaker" ,r-pkgmaker)
13707 ("r-preprocesscore" ,r-preprocesscore)
13708 ("r-rngtools" ,r-rngtools)
13709 ("r-scales" ,r-scales)
13710 ("r-stringr" ,r-stringr)
13711 ("r-xbioc" ,r-xbioc)))
13712 (home-page "https://github.com/shenorrLab/bseqsc")
13713 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13714 (description "BSeq-sc is a bioinformatics analysis pipeline that
13715 leverages single-cell sequencing data to estimate cell type proportion and
13716 cell type-specific gene expression differences from RNA-seq data from bulk
13717 tissue samples. This is a companion package to the publication \"A
13718 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13719 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13720 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13721 (license license:gpl2+))))
13723 (define-public porechop
13724 ;; The recommended way to install is to clone the git repository
13725 ;; https://github.com/rrwick/Porechop#installation
13726 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13730 (version (git-version "0.2.3" revision commit))
13734 (uri (git-reference
13735 (url "https://github.com/rrwick/Porechop.git")
13737 (file-name (git-file-name name version))
13739 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13740 (build-system python-build-system)
13741 (home-page "https://github.com/rrwick/porechop")
13742 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13744 "The porechop package is a tool for finding and removing adapters from Oxford
13745 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13746 has an adapter in its middle, it is treated as chimeric and chopped into
13747 separate reads. Porechop performs thorough alignments to effectively find
13748 adapters, even at low sequence identity. Porechop also supports demultiplexing
13749 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13750 Barcoding Kit or Rapid Barcoding Kit.")
13751 (license license:gpl3+))))
13753 (define-public poretools
13754 ;; The latest release was in 2016 and the latest commit is from 2017
13755 ;; the recommended way to install is to clone the git repository
13756 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13757 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13761 (version (git-version "0.6.0" revision commit))
13765 (uri (git-reference
13766 (url "https://github.com/arq5x/poretools.git")
13768 (file-name (git-file-name name version))
13770 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13771 (build-system python-build-system)
13772 ;; requires python >=2.7, <3.0, and the same for python dependencies
13773 (arguments `(#:python ,python-2))
13777 `(("python-dateutil" ,python2-dateutil)
13778 ("python-h5py" ,python2-h5py)
13779 ("python-matplotlib" ,python2-matplotlib)
13780 ("python-pandas" ,python2-pandas)
13781 ("python-seaborn" ,python2-seaborn)))
13782 (home-page "https://poretools.readthedocs.io")
13783 (synopsis "Toolkit for working with nanopore sequencing data")
13785 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13786 This @code{poretools} package is a flexible toolkit for exploring datasets
13787 generated by nanopore sequencing devices for the purposes of quality control and
13788 downstream analysis. Poretools operates directly on the native FAST5, a variant
13789 of the Hierarchical Data Format (HDF5) standard.")
13790 (license license:expat))))
13792 (define-public r-absfiltergsea
13794 (name "r-absfiltergsea")
13799 (uri (cran-uri "AbsFilterGSEA" version))
13801 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13802 (properties `((upstream-name . "AbsFilterGSEA")))
13803 (build-system r-build-system)
13805 `(("r-biobase" ,r-biobase)
13806 ("r-deseq" ,r-deseq)
13807 ("r-limma" ,r-limma)
13809 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13810 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13811 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13813 "This package provides a function that performs gene-permuting of a gene-set
13814 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13815 Without filtering, users can perform (original) two-tailed or one-tailed
13817 (license license:gpl2)))
13819 (define-public jamm
13822 (version "1.0.7.5")
13826 (uri (git-reference
13827 (url "https://github.com/mahmoudibrahim/JAMM.git")
13828 (commit (string-append "JAMMv" version))))
13829 (file-name (git-file-name name version))
13832 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13833 (build-system gnu-build-system)
13835 `(#:tests? #f ; there are none
13837 (modify-phases %standard-phases
13838 (delete 'configure)
13841 (lambda* (#:key inputs outputs #:allow-other-keys)
13842 (let* ((out (assoc-ref outputs "out"))
13843 (libexec (string-append out "/libexec/jamm"))
13844 (bin (string-append out "/bin")))
13845 (substitute* '("JAMM.sh"
13846 "SignalGenerator.sh")
13848 (string-append "sPath=\"" libexec "\"\n")))
13849 (for-each (lambda (file)
13850 (install-file file libexec))
13851 (list "bincalculator.r"
13863 (chmod script #o555)
13864 (install-file script bin)
13865 (wrap-program (string-append bin "/" script)
13866 `("PATH" ":" prefix
13867 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13868 ,(string-append (assoc-ref inputs "gawk") "/bin")
13869 ,(string-append (assoc-ref inputs "perl") "/bin")
13870 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13871 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13872 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13873 (list "JAMM.sh" "SignalGenerator.sh")))
13877 ("coreutils" ,coreutils)
13880 ("r-minimal" ,r-minimal)
13881 ;;("r-parallel" ,r-parallel)
13882 ("r-signal" ,r-signal)
13883 ("r-mclust" ,r-mclust)))
13884 (home-page "https://github.com/mahmoudibrahim/JAMM")
13885 (synopsis "Peak finder for NGS datasets")
13887 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13888 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13889 boundaries accurately. JAMM is applicable to both broad and narrow
13891 (license license:gpl3+)))
13893 (define-public ngless
13900 (uri (git-reference
13901 (url "https://gitlab.com/ngless/ngless.git")
13902 (commit (string-append "v" version))))
13903 (file-name (git-file-name name version))
13906 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
13907 (build-system haskell-build-system)
13909 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13910 ; error: parse error on input import
13911 ; import Options.Applicative
13913 (modify-phases %standard-phases
13914 (add-after 'unpack 'create-cabal-file
13915 (lambda _ (invoke "hpack") #t))
13916 ;; These tools are expected to be installed alongside ngless.
13917 (add-after 'install 'link-tools
13918 (lambda* (#:key inputs outputs #:allow-other-keys)
13919 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13920 (symlink (string-append (assoc-ref inputs "prodigal")
13922 (string-append bin "ngless-" ,version "-prodigal"))
13923 (symlink (string-append (assoc-ref inputs "minimap2")
13925 (string-append bin "ngless-" ,version "-minimap2"))
13926 (symlink (string-append (assoc-ref inputs "samtools")
13928 (string-append bin "ngless-" ,version "-samtools"))
13929 (symlink (string-append (assoc-ref inputs "bwa")
13931 (string-append bin "ngless-" ,version "-bwa"))
13934 `(("prodigal" ,prodigal)
13936 ("samtools" ,samtools)
13937 ("minimap2" ,minimap2)
13938 ("ghc-aeson" ,ghc-aeson)
13939 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13940 ("ghc-async" ,ghc-async)
13941 ("ghc-atomic-write" ,ghc-atomic-write)
13942 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13943 ("ghc-chart" ,ghc-chart)
13944 ("ghc-chart-cairo" ,ghc-chart-cairo)
13945 ("ghc-conduit" ,ghc-conduit)
13946 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13947 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
13948 ("ghc-conduit-extra" ,ghc-conduit-extra)
13949 ("ghc-configurator" ,ghc-configurator)
13950 ("ghc-convertible" ,ghc-convertible)
13951 ("ghc-data-default" ,ghc-data-default)
13952 ("ghc-double-conversion" ,ghc-double-conversion)
13953 ("ghc-edit-distance" ,ghc-edit-distance)
13954 ("ghc-either" ,ghc-either)
13955 ("ghc-errors" ,ghc-errors)
13956 ("ghc-extra" ,ghc-extra)
13957 ("ghc-filemanip" ,ghc-filemanip)
13958 ("ghc-file-embed" ,ghc-file-embed)
13959 ("ghc-gitrev" ,ghc-gitrev)
13960 ("ghc-hashtables" ,ghc-hashtables)
13961 ("ghc-http-conduit" ,ghc-http-conduit)
13962 ("ghc-inline-c" ,ghc-inline-c)
13963 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13964 ("ghc-intervalmap" ,ghc-intervalmap)
13965 ("ghc-missingh" ,ghc-missingh)
13966 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13967 ("ghc-parsec" ,ghc-parsec)
13968 ("ghc-regex" ,ghc-regex)
13969 ("ghc-safe" ,ghc-safe)
13970 ("ghc-safeio" ,ghc-safeio)
13971 ("ghc-strict" ,ghc-strict)
13972 ("ghc-tar" ,ghc-tar)
13973 ("ghc-text" ,ghc-text)
13974 ("ghc-unliftio" ,ghc-unliftio)
13975 ("ghc-unliftio-core" ,ghc-unliftio-core)
13976 ("ghc-vector" ,ghc-vector)
13977 ("ghc-yaml" ,ghc-yaml)
13978 ("ghc-zlib" ,ghc-zlib)))
13981 ("r-hdf5r" ,r-hdf5r)
13982 ("r-iterators" ,r-iterators)
13983 ("r-itertools" ,r-itertools)
13984 ("r-matrix" ,r-matrix)))
13986 `(("ghc-hpack" ,ghc-hpack)
13987 ("ghc-quickcheck" ,ghc-quickcheck)
13988 ("ghc-test-framework" ,ghc-test-framework)
13989 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
13990 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
13991 ("ghc-test-framework-th" ,ghc-test-framework-th)))
13992 (home-page "https://gitlab.com/ngless/ngless")
13993 (synopsis "DSL for processing next-generation sequencing data")
13994 (description "Ngless is a domain-specific language for
13995 @dfn{next-generation sequencing} (NGS) data processing.")
13996 (license license:expat)))
13998 (define-public filtlong
13999 ;; The recommended way to install is to clone the git repository
14000 ;; https://github.com/rrwick/Filtlong#installation
14001 ;; and the lastest release is more than nine months old
14002 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14006 (version (git-version "0.2.0" revision commit))
14010 (uri (git-reference
14011 (url "https://github.com/rrwick/Filtlong.git")
14013 (file-name (git-file-name name version))
14015 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14016 (build-system gnu-build-system)
14018 `(#:tests? #f ; no check target
14020 (modify-phases %standard-phases
14021 (delete 'configure)
14023 (lambda* (#:key outputs #:allow-other-keys)
14024 (let* ((out (assoc-ref outputs "out"))
14025 (bin (string-append out "/bin"))
14026 (scripts (string-append out "/share/filtlong/scripts")))
14027 (install-file "bin/filtlong" bin)
14028 (install-file "scripts/histogram.py" scripts)
14029 (install-file "scripts/read_info_histograms.sh" scripts))
14031 (add-after 'install 'wrap-program
14032 (lambda* (#:key inputs outputs #:allow-other-keys)
14033 (let* ((out (assoc-ref outputs "out"))
14034 (path (getenv "PYTHONPATH")))
14035 (wrap-program (string-append out
14036 "/share/filtlong/scripts/histogram.py")
14037 `("PYTHONPATH" ":" prefix (,path))))
14039 (add-before 'check 'patch-tests
14041 (substitute* "scripts/read_info_histograms.sh"
14042 (("awk") (which "gawk")))
14045 `(("gawk" ,gawk) ;for read_info_histograms.sh
14046 ("python" ,python-2) ;required for histogram.py
14048 (home-page "https://github.com/rrwick/Filtlong/")
14049 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14051 "The Filtlong package is a tool for filtering long reads by quality.
14052 It can take a set of long reads and produce a smaller, better subset. It uses
14053 both read length (longer is better) and read identity (higher is better) when
14054 choosing which reads pass the filter.")
14055 (license (list license:gpl3 ;filtlong
14056 license:asl2.0))))) ;histogram.py
14058 (define-public nanopolish
14059 ;; The recommended way to install is to clone the git repository
14060 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14061 ;; Also, the differences between release and current version seem to be
14063 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14066 (name "nanopolish")
14067 (version (git-version "0.11.1" revision commit))
14071 (uri (git-reference
14072 (url "https://github.com/jts/nanopolish.git")
14075 (file-name (git-file-name name version))
14077 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14078 (modules '((guix build utils)))
14081 (delete-file-recursively "htslib")
14083 (build-system gnu-build-system)
14086 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14087 #:tests? #f ; no check target
14089 (modify-phases %standard-phases
14090 (add-after 'unpack 'find-eigen
14091 (lambda* (#:key inputs #:allow-other-keys)
14093 (string-append (assoc-ref inputs "eigen")
14094 "/include/eigen3"))
14096 (delete 'configure)
14098 (lambda* (#:key outputs #:allow-other-keys)
14099 (let* ((out (assoc-ref outputs "out"))
14100 (bin (string-append out "/bin"))
14101 (scripts (string-append out "/share/nanopolish/scripts")))
14103 (install-file "nanopolish" bin)
14104 (for-each (lambda (file) (install-file file scripts))
14105 (find-files "scripts" ".*"))
14107 (add-after 'install 'wrap-programs
14108 (lambda* (#:key outputs #:allow-other-keys)
14109 (for-each (lambda (file)
14110 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14111 (find-files "/share/nanopolish/scripts" "\\.py"))
14112 (for-each (lambda (file)
14113 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14114 (find-files "/share/nanopolish/scripts" "\\.pl"))
14121 ("python" ,python-wrapper)
14122 ("python-biopython" ,python-biopython)
14123 ("python-numpy" ,python-numpy)
14124 ("python-pysam" ,python-pysam)
14125 ("python-scikit-learn" , python-scikit-learn)
14126 ("python-scipy" ,python-scipy)
14128 (home-page "https://github.com/jts/nanopolish")
14129 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14131 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14132 Nanopolish can calculate an improved consensus sequence for a draft genome
14133 assembly, detect base modifications, call SNPs (Single nucleotide
14134 polymorphisms) and indels with respect to a reference genome and more.")
14135 (license license:expat))))
14137 (define-public cnvkit
14144 (uri (git-reference
14145 (url "https://github.com/etal/cnvkit.git")
14146 (commit (string-append "v" version))))
14147 (file-name (git-file-name name version))
14149 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14150 (build-system python-build-system)
14152 `(("python-biopython" ,python-biopython)
14153 ("python-future" ,python-future)
14154 ("python-matplotlib" ,python-matplotlib)
14155 ("python-numpy" ,python-numpy)
14156 ("python-reportlab" ,python-reportlab)
14157 ("python-pandas" ,python-pandas)
14158 ("python-pysam" ,python-pysam)
14159 ("python-pyfaidx" ,python-pyfaidx)
14160 ("python-scipy" ,python-scipy)
14162 ("r-dnacopy" ,r-dnacopy)))
14163 (home-page "https://cnvkit.readthedocs.org/")
14164 (synopsis "Copy number variant detection from targeted DNA sequencing")
14166 "CNVkit is a Python library and command-line software toolkit to infer
14167 and visualize copy number from high-throughput DNA sequencing data. It is
14168 designed for use with hybrid capture, including both whole-exome and custom
14169 target panels, and short-read sequencing platforms such as Illumina and Ion
14171 (license license:asl2.0)))
14173 (define-public python-pyfit-sne
14175 (name "python-pyfit-sne")
14180 (uri (git-reference
14181 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14183 (file-name (git-file-name name version))
14185 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14186 (build-system python-build-system)
14188 `(("python-numpy" ,python-numpy)))
14192 `(("python-cython" ,python-cython)))
14193 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14194 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14196 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14197 method for dimensionality reduction and visualization of high dimensional
14198 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14199 approximate the gradient at each iteration of gradient descent. This package
14200 is a Cython wrapper for FIt-SNE.")
14201 (license license:bsd-4)))
14203 (define-public bbmap
14209 (uri (string-append
14210 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14213 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14214 (build-system ant-build-system)
14216 `(#:build-target "dist"
14217 #:tests? #f ; there are none
14219 (list (string-append "-Dmpijar="
14220 (assoc-ref %build-inputs "java-openmpi")
14222 #:modules ((guix build ant-build-system)
14224 (guix build java-utils))
14226 (modify-phases %standard-phases
14227 (add-after 'build 'build-jni-library
14229 (with-directory-excursion "jni"
14230 (invoke "make" "-f" "makefile.linux"))))
14231 ;; There is no install target
14232 (replace 'install (install-jars "dist"))
14233 (add-after 'install 'install-scripts-and-documentation
14234 (lambda* (#:key outputs #:allow-other-keys)
14235 (substitute* "calcmem.sh"
14236 (("\\| awk ") (string-append "| " (which "awk") " ")))
14237 (let* ((scripts (find-files "." "\\.sh$"))
14238 (out (assoc-ref outputs "out"))
14239 (bin (string-append out "/bin"))
14240 (doc (string-append out "/share/doc/bbmap"))
14241 (jni (string-append out "/lib/jni")))
14242 (substitute* scripts
14243 (("\\$DIR\"\"docs") doc)
14245 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14246 (("^NATIVELIBDIR.*")
14247 (string-append "NATIVELIBDIR=" jni "\n"))
14249 (string-append "CMD=\"" (which "java"))))
14250 (for-each (lambda (script) (install-file script bin)) scripts)
14252 ;; Install JNI library
14253 (install-file "jni/libbbtoolsjni.so" jni)
14255 ;; Install documentation
14256 (install-file "docs/readme.txt" doc)
14257 (copy-recursively "docs/guides" doc))
14262 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14263 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14264 ("java-openmpi" ,java-openmpi)))
14265 (home-page "http://sourceforge.net/projects/bbmap/")
14266 (synopsis "Aligner and other tools for short sequencing reads")
14268 "This package provides bioinformatic tools to align, deduplicate,
14269 reformat, filter and normalize DNA and RNA-seq data. It includes the
14270 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14271 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14272 simplify assemblies by removing duplicate or contained subsequences that share
14273 a target percent identity; Reformat, to convert reads between
14274 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14275 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14276 to an artifact/contaminant file.")
14277 (license license:bsd-3)))
14279 (define-public velvet
14285 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14286 "velvet_" version ".tgz"))
14289 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14290 ;; Delete bundled libraries
14291 (modules '((guix build utils)))
14294 (delete-file "Manual.pdf")
14295 (delete-file-recursively "third-party")
14297 (build-system gnu-build-system)
14299 `(#:make-flags '("OPENMP=t")
14300 #:test-target "test"
14302 (modify-phases %standard-phases
14303 (delete 'configure)
14304 (add-after 'unpack 'fix-zlib-include
14306 (substitute* "src/binarySequences.c"
14307 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14310 (lambda* (#:key outputs #:allow-other-keys)
14311 (let* ((out (assoc-ref outputs "out"))
14312 (bin (string-append out "/bin"))
14313 (doc (string-append out "/share/doc/velvet")))
14316 (install-file "velveth" bin)
14317 (install-file "velvetg" bin)
14318 (install-file "Manual.pdf" doc)
14319 (install-file "Columbus_manual.pdf" doc)
14322 `(("openmpi" ,openmpi)
14325 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14326 texlive-latex-hyperref)))))
14327 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14328 (synopsis "Nucleic acid sequence assembler for very short reads")
14330 "Velvet is a de novo genomic assembler specially designed for short read
14331 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14332 short read sequences, removes errors then produces high quality unique
14333 contigs. It then uses paired read information, if available, to retrieve the
14334 repeated areas between contigs.")
14335 (license license:gpl2+)))
14337 (define-public python-velocyto
14339 (name "python-velocyto")
14340 (version "0.17.17")
14344 (uri (pypi-uri "velocyto" version))
14347 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14348 (build-system python-build-system)
14350 `(("python-click" ,python-click)
14351 ("python-cython" ,python-cython)
14352 ("python-h5py" ,python-h5py)
14353 ("python-loompy" ,python-loompy)
14354 ("python-matplotlib" ,python-matplotlib)
14355 ("python-numba" ,python-numba)
14356 ("python-numpy" ,python-numpy)
14357 ("python-pandas" ,python-pandas)
14358 ("python-pysam" ,python-pysam)
14359 ("python-scikit-learn" ,python-scikit-learn)
14360 ("python-scipy" ,python-scipy)))
14361 (home-page "https://github.com/velocyto-team/velocyto.py")
14362 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14364 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14365 includes a command line tool and an analysis pipeline.")
14366 (license license:bsd-2)))
14368 (define-public arriba
14375 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14376 "download/v" version "/arriba_v" version ".tar.gz"))
14379 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14380 (build-system gnu-build-system)
14382 `(#:tests? #f ; there are none
14384 (modify-phases %standard-phases
14385 (replace 'configure
14386 (lambda* (#:key inputs #:allow-other-keys)
14387 (let ((htslib (assoc-ref inputs "htslib")))
14388 (substitute* "Makefile"
14389 (("-I\\$\\(HTSLIB\\)/htslib")
14390 (string-append "-I" htslib "/include/htslib"))
14391 ((" \\$\\(HTSLIB\\)/libhts.a")
14392 (string-append " " htslib "/lib/libhts.so"))))
14393 (substitute* "run_arriba.sh"
14394 (("^STAR ") (string-append (which "STAR") " "))
14395 (("samtools --version-only")
14396 (string-append (which "samtools") " --version-only"))
14397 (("samtools index")
14398 (string-append (which "samtools") " index"))
14400 (string-append (which "samtools") " sort")))
14403 (lambda* (#:key outputs #:allow-other-keys)
14404 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14405 (install-file "arriba" bin)
14406 (install-file "run_arriba.sh" bin)
14407 (install-file "draw_fusions.R" bin)
14408 (wrap-program (string-append bin "/draw_fusions.R")
14409 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14412 `(("htslib" ,htslib)
14413 ("r-minimal" ,r-minimal)
14414 ("r-circlize" ,r-circlize)
14415 ("r-genomicalignments" ,r-genomicalignments)
14416 ("r-genomicranges" ,r-genomicranges)
14417 ("samtools" ,samtools)
14420 (home-page "https://github.com/suhrig/arriba")
14421 (synopsis "Gene fusion detection from RNA-Seq data ")
14423 "Arriba is a command-line tool for the detection of gene fusions from
14424 RNA-Seq data. It was developed for the use in a clinical research setting.
14425 Therefore, short runtimes and high sensitivity were important design criteria.
14426 It is based on the fast STAR aligner and the post-alignment runtime is
14427 typically just around two minutes. In contrast to many other fusion detection
14428 tools which build on STAR, Arriba does not require to reduce the
14429 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14430 ;; All code is under the Expat license with the exception of
14431 ;; "draw_fusions.R", which is under GPLv3.
14432 (license (list license:expat license:gpl3))))
14434 (define-public adapterremoval
14436 (name "adapterremoval")
14441 (uri (git-reference
14442 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14443 (commit (string-append "v" version))))
14444 (file-name (git-file-name name version))
14447 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14448 (build-system gnu-build-system)
14450 `(#:make-flags (list "COLOR_BUILD=no"
14451 (string-append "PREFIX="
14452 (assoc-ref %outputs "out")))
14453 #:test-target "test"
14455 (modify-phases %standard-phases
14456 (delete 'configure))))
14459 (home-page "https://adapterremoval.readthedocs.io/")
14460 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14462 "This program searches for and removes remnant adapter sequences from
14463 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14464 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14465 analyze both single end and paired end data, and can be used to merge
14466 overlapping paired-ended reads into (longer) consensus sequences.
14467 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14468 sequence for paired-ended data, for which this information is not available.")
14469 (license license:gpl3+)))
14471 (define-public pplacer
14472 (let ((commit "807f6f3"))
14475 ;; The commit should be updated with each version change.
14476 (version "1.1.alpha19")
14480 (uri (git-reference
14481 (url "https://github.com/matsen/pplacer.git")
14482 (commit (string-append "v" version))))
14483 (file-name (git-file-name name version))
14485 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14486 (build-system ocaml-build-system)
14488 `(#:modules ((guix build ocaml-build-system)
14492 (modify-phases %standard-phases
14493 (delete 'configure)
14494 (add-after 'unpack 'fix-build-with-latest-ocaml
14496 (substitute* "myocamlbuild.ml"
14497 (("dep \\[\"c_pam\"\\]" m)
14498 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14500 (("let run_and_read" m)
14505 let pos = String.index s ch in
14506 x := (String.before s pos)::!x;
14507 go (String.after s (pos + 1))
14510 with Not_found -> !x
14511 let split_nl s = split s '\\n'
14512 let before_space s =
14513 try String.before s (String.index s ' ')
14514 with Not_found -> s
14517 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14518 (string-append "List.map before_space (split_nl & " m ")"))
14519 ((" blank_sep_strings &") "")
14520 ((" Lexing.from_string &") ""))
14522 (add-after 'unpack 'replace-bundled-cddlib
14523 (lambda* (#:key inputs #:allow-other-keys)
14524 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14525 (local-dir "cddlib_guix"))
14527 (with-directory-excursion local-dir
14528 (invoke "tar" "xvf" cddlib-src))
14529 (let ((cddlib-src-folder
14530 (string-append local-dir "/"
14531 (list-ref (scandir local-dir) 2)
14533 (for-each make-file-writable (find-files "cdd_src" ".*"))
14537 (string-append "cdd_src/" (basename file))))
14538 (find-files cddlib-src-folder ".*[ch]$")))
14540 (add-after 'unpack 'fix-makefile
14542 ;; Remove system calls to 'git'.
14543 (substitute* "Makefile"
14544 (("^DESCRIPT:=pplacer-.*")
14546 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14547 (substitute* "myocamlbuild.ml"
14548 (("git describe --tags --long .*\\\" with")
14550 "echo -n v" ,version "-" ,commit "\" with")))
14553 (lambda* (#:key outputs #:allow-other-keys)
14554 (let* ((out (assoc-ref outputs "out"))
14555 (bin (string-append out "/bin")))
14556 (copy-recursively "bin" bin))
14559 `(("zlib" ,zlib "static")
14561 ("ocaml-ounit" ,ocaml-ounit)
14562 ("ocaml-batteries" ,ocaml-batteries)
14563 ("ocaml-camlzip" ,camlzip)
14564 ("ocaml-csv" ,ocaml-csv)
14565 ("ocaml-sqlite3" ,ocaml-sqlite3)
14566 ("ocaml-xmlm" ,ocaml-xmlm)
14567 ("ocaml-mcl" ,ocaml-mcl)
14568 ("ocaml-gsl" ,ocaml-gsl-1)))
14570 `(("cddlib-src" ,(package-source cddlib))
14571 ("ocamlbuild" ,ocamlbuild)
14572 ("pkg-config" ,pkg-config)))
14574 `(("pplacer-scripts" ,pplacer-scripts)))
14575 (synopsis "Phylogenetic placement of biological sequences")
14577 "Pplacer places query sequences on a fixed reference phylogenetic tree
14578 to maximize phylogenetic likelihood or posterior probability according to a
14579 reference alignment. Pplacer is designed to be fast, to give useful
14580 information about uncertainty, and to offer advanced visualization and
14581 downstream analysis.")
14582 (home-page "http://matsen.fhcrc.org/pplacer")
14583 (license license:gpl3))))
14585 ;; This package is installed alongside 'pplacer'. It is a separate package so
14586 ;; that it can use the python-build-system for the scripts that are
14587 ;; distributed alongside the main OCaml binaries.
14588 (define pplacer-scripts
14591 (name "pplacer-scripts")
14592 (build-system python-build-system)
14594 `(#:python ,python-2
14596 (modify-phases %standard-phases
14597 (add-after 'unpack 'enter-scripts-dir
14598 (lambda _ (chdir "scripts") #t))
14600 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14601 (add-after 'install 'wrap-executables
14602 (lambda* (#:key inputs outputs #:allow-other-keys)
14603 (let* ((out (assoc-ref outputs "out"))
14604 (bin (string-append out "/bin")))
14605 (let ((path (string-append
14606 (assoc-ref inputs "hmmer") "/bin:"
14607 (assoc-ref inputs "infernal") "/bin")))
14609 (wrap-program (string-append bin "/refpkg_align.py")
14610 `("PATH" ":" prefix (,path))))
14611 (let ((path (string-append
14612 (assoc-ref inputs "hmmer") "/bin")))
14613 (wrap-program (string-append bin "/hrefpkg_query.py")
14614 `("PATH" ":" prefix (,path)))))
14617 `(("infernal" ,infernal)
14620 `(("python-biopython" ,python2-biopython)
14621 ("taxtastic" ,taxtastic)))
14622 (synopsis "Pplacer Python scripts")))
14624 (define-public python2-checkm-genome
14626 (name "python2-checkm-genome")
14631 (uri (pypi-uri "checkm-genome" version))
14634 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14635 (build-system python-build-system)
14637 `(#:python ,python-2
14638 #:tests? #f)) ; some tests are interactive
14640 `(("python-dendropy" ,python2-dendropy)
14641 ("python-matplotlib" ,python2-matplotlib)
14642 ("python-numpy" ,python2-numpy)
14643 ("python-pysam" ,python2-pysam)
14644 ("python-scipy" ,python2-scipy)))
14645 (home-page "http://pypi.python.org/pypi/checkm/")
14646 (synopsis "Assess the quality of putative genome bins")
14648 "CheckM provides a set of tools for assessing the quality of genomes
14649 recovered from isolates, single cells, or metagenomes. It provides robust
14650 estimates of genome completeness and contamination by using collocated sets of
14651 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14652 Assessment of genome quality can also be examined using plots depicting key
14653 genomic characteristics (e.g., GC, coding density) which highlight sequences
14654 outside the expected distributions of a typical genome. CheckM also provides
14655 tools for identifying genome bins that are likely candidates for merging based
14656 on marker set compatibility, similarity in genomic characteristics, and
14657 proximity within a reference genome.")
14658 (license license:gpl3+)))
14660 (define-public umi-tools
14667 (uri (pypi-uri "umi_tools" version))
14670 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14671 (build-system python-build-system)
14673 `(("python-setuptools" ,python-setuptools)
14674 ("python-pandas" ,python-pandas)
14675 ("python-future" ,python-future)
14676 ("python-scipy" ,python-scipy)
14677 ("python-matplotlib" ,python-matplotlib)
14678 ("python-regex" ,python-regex)
14679 ("python-pysam" ,python-pysam)))
14681 `(("python-setuptools" ,python-setuptools)
14682 ("python-cython" ,python-cython)))
14683 (home-page "https://github.com/CGATOxford/UMI-tools")
14684 (synopsis "Tools for analyzing unique modular identifiers")
14685 (description "This package provides tools for dealing with @dfn{Unique
14686 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14687 genetic sequences. There are six tools: the @code{extract} and
14688 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14689 cell barcodes for alignment. The remaining commands, @code{group},
14690 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14691 duplicates using the UMIs and perform different levels of analysis depending
14692 on the needs of the user.")
14693 (license license:expat)))
14695 (define-public ataqv
14702 (uri (git-reference
14703 (url "https://github.com/ParkerLab/ataqv.git")
14705 (file-name (git-file-name name version))
14708 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14709 (build-system gnu-build-system)
14712 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14713 (string-append "BOOST_ROOT="
14714 (assoc-ref %build-inputs "boost"))
14715 (string-append "HTSLIB_ROOT="
14716 (assoc-ref %build-inputs "htslib")))
14717 #:test-target "test"
14719 (modify-phases %standard-phases
14720 (delete 'configure))))
14724 ("ncurses" ,ncurses)
14728 (home-page "https://github.com/ParkerLab/ataqv")
14729 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14730 (description "This package provides a toolkit for measuring and comparing
14731 ATAC-seq results. It was written to make it easier to spot differences that
14732 might be caused by ATAC-seq library prep or sequencing. The main program,
14733 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14734 (license license:gpl3+)))
14736 (define-public r-psiplot
14743 (uri (git-reference
14744 (url "https://github.com/kcha/psiplot.git")
14745 (commit (string-append "v" version))))
14746 (file-name (git-file-name name version))
14748 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14749 (build-system r-build-system)
14751 `(("r-mass" ,r-mass)
14752 ("r-dplyr" ,r-dplyr)
14753 ("r-tidyr" ,r-tidyr)
14754 ("r-purrr" ,r-purrr)
14755 ("r-readr" ,r-readr)
14756 ("r-magrittr" ,r-magrittr)
14757 ("r-ggplot2" ,r-ggplot2)))
14758 (home-page "https://github.com/kcha/psiplot")
14759 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14761 "PSIplot is an R package for generating plots of @dfn{percent
14762 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
14763 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
14764 are generated using @code{ggplot2}.")
14765 (license license:expat)))
14767 (define-public python-ont-fast5-api
14769 (name "python-ont-fast5-api")
14774 (uri (git-reference
14775 (url "https://github.com/nanoporetech/ont_fast5_api.git")
14776 (commit (string-append "release_" version))))
14777 (file-name (git-file-name name version))
14780 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
14781 (build-system python-build-system)
14783 `(("python-numpy" ,python-numpy)
14784 ("python-six" ,python-six)
14785 ("python-h5py" ,python-h5py)
14786 ("python-progressbar33" ,python-progressbar33)))
14787 (home-page "https://github.com/nanoporetech/ont_fast5_api")
14788 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
14790 "This package provides a concrete implementation of the fast5 file schema
14791 using the generic @code{h5py} library, plain-named methods to interact with
14792 and reflect the fast5 file schema, and tools to convert between
14793 @code{multi_read} and @code{single_read} formats.")
14794 (license license:mpl2.0)))
14796 (define-public tbsp
14797 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
14801 (version (git-version "1.0.0" revision commit))
14805 (uri (git-reference
14806 (url "https://github.com/phoenixding/tbsp.git")
14810 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
14811 (build-system python-build-system)
14812 (arguments '(#:tests? #f)) ; no tests included
14814 `(("python-matplotlib" ,python-matplotlib)
14815 ("python-networkx" ,python-networkx)
14816 ("python-numpy" ,python-numpy)
14817 ("python-pybigwig" ,python-pybigwig)
14818 ("python-biopython" ,python-biopython)
14819 ("python-scikit-learn" ,python-scikit-learn)
14820 ("python-scipy" ,python-scipy)))
14821 (home-page "https://github.com/phoenixding/tbsp/")
14822 (synopsis "SNP-based trajectory inference")
14824 "Several studies focus on the inference of developmental and response
14825 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
14826 computational methods, often referred to as pseudo-time ordering, have been
14827 developed for this task. CRISPR has also been used to reconstruct lineage
14828 trees by inserting random mutations. The tbsp package implements an
14829 alternative method to detect significant, cell type specific sequence
14830 mutations from scRNA-Seq data.")
14831 (license license:expat))))