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-check)
81 #:use-module (gnu packages haskell-web)
82 #:use-module (gnu packages haskell-xyz)
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))
1113 (home-page "http://biopp.univ-montp2.fr")
1114 (synopsis "C++ libraries for Bioinformatics")
1116 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1117 analysis, phylogenetics, molecular evolution and population genetics. It is
1118 Object Oriented and is designed to be both easy to use and computer efficient.
1119 Bio++ intends to help programmers to write computer expensive programs, by
1120 providing them a set of re-usable tools.")
1121 (license license:cecill-c))))
1123 (define-public bpp-phyl
1124 ;; The last release was in 2014 and the recommended way to install from source
1125 ;; is to clone the git repository, so we do this.
1126 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1127 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1130 (version (string-append "2.2.0-1." (string-take commit 7)))
1134 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1136 (file-name (string-append name "-" version "-checkout"))
1139 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1140 (build-system cmake-build-system)
1142 `(#:parallel-build? #f
1143 ;; If out-of-source, test data is not copied into the build directory
1144 ;; so the tests fail.
1145 #:out-of-source? #f))
1147 `(("bpp-core" ,bpp-core)
1148 ("bpp-seq" ,bpp-seq)))
1149 (home-page "http://biopp.univ-montp2.fr")
1150 (synopsis "Bio++ phylogenetic Library")
1152 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1153 analysis, phylogenetics, molecular evolution and population genetics. This
1154 library provides phylogenetics-related modules.")
1155 (license license:cecill-c))))
1157 (define-public bpp-popgen
1158 ;; The last release was in 2014 and the recommended way to install from source
1159 ;; is to clone the git repository, so we do this.
1160 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1161 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1164 (version (string-append "2.2.0-1." (string-take commit 7)))
1168 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1170 (file-name (string-append name "-" version "-checkout"))
1173 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1174 (build-system cmake-build-system)
1176 `(#:parallel-build? #f
1177 #:tests? #f)) ; There are no tests.
1179 `(("bpp-core" ,bpp-core)
1180 ("bpp-seq" ,bpp-seq)))
1181 (home-page "http://biopp.univ-montp2.fr")
1182 (synopsis "Bio++ population genetics library")
1184 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1185 analysis, phylogenetics, molecular evolution and population genetics. This
1186 library provides population genetics-related modules.")
1187 (license license:cecill-c))))
1189 (define-public bpp-seq
1190 ;; The last release was in 2014 and the recommended way to install from source
1191 ;; is to clone the git repository, so we do this.
1192 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1193 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1196 (version (string-append "2.2.0-1." (string-take commit 7)))
1200 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1202 (file-name (string-append name "-" version "-checkout"))
1205 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1206 (build-system cmake-build-system)
1208 `(#:parallel-build? #f
1209 ;; If out-of-source, test data is not copied into the build directory
1210 ;; so the tests fail.
1211 #:out-of-source? #f))
1213 `(("bpp-core" ,bpp-core)))
1214 (home-page "http://biopp.univ-montp2.fr")
1215 (synopsis "Bio++ sequence library")
1217 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1218 analysis, phylogenetics, molecular evolution and population genetics. This
1219 library provides sequence-related modules.")
1220 (license license:cecill-c))))
1222 (define-public bppsuite
1223 ;; The last release was in 2014 and the recommended way to install from source
1224 ;; is to clone the git repository, so we do this.
1225 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1226 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1229 (version (string-append "2.2.0-1." (string-take commit 7)))
1233 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1235 (file-name (string-append name "-" version "-checkout"))
1238 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1239 (build-system cmake-build-system)
1241 `(#:parallel-build? #f
1242 #:tests? #f)) ; There are no tests.
1246 ("texinfo" ,texinfo)))
1248 `(("bpp-core" ,bpp-core)
1249 ("bpp-seq" ,bpp-seq)
1250 ("bpp-phyl" ,bpp-phyl)
1251 ("bpp-phyl" ,bpp-popgen)))
1252 (home-page "http://biopp.univ-montp2.fr")
1253 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1255 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1256 analysis, phylogenetics, molecular evolution and population genetics. This
1257 package provides command line tools using the Bio++ library.")
1258 (license license:cecill-c))))
1260 (define-public blast+
1267 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1268 version "/ncbi-blast-" version "+-src.tar.gz"))
1271 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1272 (modules '((guix build utils)))
1275 ;; Remove bundled bzip2, zlib and pcre.
1276 (delete-file-recursively "c++/src/util/compress/bzip2")
1277 (delete-file-recursively "c++/src/util/compress/zlib")
1278 (delete-file-recursively "c++/src/util/regexp")
1279 (substitute* "c++/src/util/compress/Makefile.in"
1280 (("bzip2 zlib api") "api"))
1281 ;; Remove useless msbuild directory
1282 (delete-file-recursively
1283 "c++/src/build-system/project_tree_builder/msbuild")
1285 (build-system gnu-build-system)
1287 `(;; There are two(!) tests for this massive library, and both fail with
1288 ;; "unparsable timing stats".
1289 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1290 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1293 #:parallel-build? #f ; not supported
1295 (modify-phases %standard-phases
1296 (add-before 'configure 'set-HOME
1297 ;; $HOME needs to be set at some point during the configure phase
1298 (lambda _ (setenv "HOME" "/tmp") #t))
1299 (add-after 'unpack 'enter-dir
1300 (lambda _ (chdir "c++") #t))
1301 (add-after 'enter-dir 'fix-build-system
1303 (define (which* cmd)
1304 (cond ((string=? cmd "date")
1305 ;; make call to "date" deterministic
1310 (format (current-error-port)
1311 "WARNING: Unable to find absolute path for ~s~%"
1315 ;; Rewrite hardcoded paths to various tools
1316 (substitute* (append '("src/build-system/configure.ac"
1317 "src/build-system/configure"
1318 "src/build-system/helpers/run_with_lock.c"
1319 "scripts/common/impl/if_diff.sh"
1320 "scripts/common/impl/run_with_lock.sh"
1321 "src/build-system/Makefile.configurables.real"
1322 "src/build-system/Makefile.in.top"
1323 "src/build-system/Makefile.meta.gmake=no"
1324 "src/build-system/Makefile.meta.in"
1325 "src/build-system/Makefile.meta_l"
1326 "src/build-system/Makefile.meta_p"
1327 "src/build-system/Makefile.meta_r"
1328 "src/build-system/Makefile.mk.in"
1329 "src/build-system/Makefile.requirements"
1330 "src/build-system/Makefile.rules_with_autodep.in")
1331 (find-files "scripts/common/check" "\\.sh$"))
1332 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1333 (or (which* cmd) all)))
1335 (substitute* (find-files "src/build-system" "^config.*")
1336 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1339 ;; rewrite "/var/tmp" in check script
1340 (substitute* "scripts/common/check/check_make_unix.sh"
1341 (("/var/tmp") "/tmp"))
1343 ;; do not reset PATH
1344 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1346 (("action=/bin/") "action=")
1347 (("export PATH") ":"))
1350 (lambda* (#:key inputs outputs #:allow-other-keys)
1351 (let ((out (assoc-ref outputs "out"))
1352 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1353 (include (string-append (assoc-ref outputs "include")
1354 "/include/ncbi-tools++")))
1355 ;; The 'configure' script doesn't recognize things like
1356 ;; '--enable-fast-install'.
1357 (invoke "./configure.orig"
1358 (string-append "--with-build-root=" (getcwd) "/build")
1359 (string-append "--prefix=" out)
1360 (string-append "--libdir=" lib)
1361 (string-append "--includedir=" include)
1362 (string-append "--with-bz2="
1363 (assoc-ref inputs "bzip2"))
1364 (string-append "--with-z="
1365 (assoc-ref inputs "zlib"))
1366 (string-append "--with-pcre="
1367 (assoc-ref inputs "pcre"))
1368 ;; Each library is built twice by default, once
1369 ;; with "-static" in its name, and again
1374 (outputs '("out" ; 21 MB
1383 ("python" ,python-wrapper)))
1386 (home-page "http://blast.ncbi.nlm.nih.gov")
1387 (synopsis "Basic local alignment search tool")
1389 "BLAST is a popular method of performing a DNA or protein sequence
1390 similarity search, using heuristics to produce results quickly. It also
1391 calculates an “expect value” that estimates how many matches would have
1392 occurred at a given score by chance, which can aid a user in judging how much
1393 confidence to have in an alignment.")
1394 ;; Most of the sources are in the public domain, with the following
1397 ;; * ./c++/include/util/bitset/
1398 ;; * ./c++/src/html/ncbi_menu*.js
1400 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1402 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1404 ;; * ./c++/src/corelib/teamcity_*
1405 (license (list license:public-domain
1411 (define-public bless
1417 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1421 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1422 (modules '((guix build utils)))
1425 ;; Remove bundled boost, pigz, zlib, and .git directory
1426 ;; FIXME: also remove bundled sources for murmurhash3 and
1427 ;; kmc once packaged.
1428 (delete-file-recursively "boost")
1429 (delete-file-recursively "pigz")
1430 (delete-file-recursively "google-sparsehash")
1431 (delete-file-recursively "zlib")
1432 (delete-file-recursively ".git")
1434 (build-system gnu-build-system)
1436 '(#:tests? #f ;no "check" target
1438 (list (string-append "ZLIB="
1439 (assoc-ref %build-inputs "zlib:static")
1441 (string-append "LDFLAGS="
1442 (string-join '("-lboost_filesystem"
1449 (modify-phases %standard-phases
1450 (add-after 'unpack 'do-not-build-bundled-pigz
1451 (lambda* (#:key inputs outputs #:allow-other-keys)
1452 (substitute* "Makefile"
1453 (("cd pigz/pigz-2.3.3; make") ""))
1455 (add-after 'unpack 'patch-paths-to-executables
1456 (lambda* (#:key inputs outputs #:allow-other-keys)
1457 (substitute* "parse_args.cpp"
1458 (("kmc_binary = .*")
1459 (string-append "kmc_binary = \""
1460 (assoc-ref outputs "out")
1462 (("pigz_binary = .*")
1463 (string-append "pigz_binary = \""
1464 (assoc-ref inputs "pigz")
1468 (lambda* (#:key outputs #:allow-other-keys)
1469 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1470 (for-each (lambda (file)
1471 (install-file file bin))
1472 '("bless" "kmc/bin/kmc"))
1474 (delete 'configure))))
1478 `(("openmpi" ,openmpi)
1480 ("sparsehash" ,sparsehash)
1482 ("zlib:static" ,zlib "static")
1484 (supported-systems '("x86_64-linux"))
1485 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1486 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1488 "@dfn{Bloom-filter-based error correction solution for high-throughput
1489 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1490 correction tool for genomic reads produced by @dfn{Next-generation
1491 sequencing} (NGS). BLESS produces accurate correction results with much less
1492 memory compared with previous solutions and is also able to tolerate a higher
1493 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1494 errors at the end of reads.")
1495 (license license:gpl3+)))
1497 (define-public bowtie
1504 (url "https://github.com/BenLangmead/bowtie2.git")
1505 (commit (string-append "v" version))))
1506 (file-name (git-file-name name version))
1509 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1510 (modules '((guix build utils)))
1513 (substitute* "Makefile"
1514 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1515 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1516 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1518 (build-system gnu-build-system)
1523 (string-append "prefix=" (assoc-ref %outputs "out")))
1525 (modify-phases %standard-phases
1530 "scripts/test/simple_tests.pl"
1531 "--bowtie2=./bowtie2"
1532 "--bowtie2-build=./bowtie2-build")
1537 ("python" ,python-wrapper)))
1540 ("perl-clone" ,perl-clone)
1541 ("perl-test-deep" ,perl-test-deep)
1542 ("perl-test-simple" ,perl-test-simple)))
1543 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1544 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1546 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1547 reads to long reference sequences. It is particularly good at aligning reads
1548 of about 50 up to 100s or 1,000s of characters, and particularly good at
1549 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1550 genome with an FM Index to keep its memory footprint small: for the human
1551 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1552 gapped, local, and paired-end alignment modes.")
1553 (supported-systems '("x86_64-linux"))
1554 (license license:gpl3+)))
1556 (define-public bowtie1
1562 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1563 version "/bowtie-src-x86_64.zip"))
1566 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1567 (modules '((guix build utils)))
1569 '(substitute* "Makefile"
1570 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1571 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1572 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1573 (build-system gnu-build-system)
1575 '(#:tests? #f ; no "check" target
1578 (string-append "prefix=" (assoc-ref %outputs "out")))
1580 (modify-phases %standard-phases
1581 (delete 'configure))))
1585 (supported-systems '("x86_64-linux"))
1586 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1587 (synopsis "Fast aligner for short nucleotide sequence reads")
1589 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1590 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1591 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1592 keep its memory footprint small: typically about 2.2 GB for the human
1593 genome (2.9 GB for paired-end).")
1594 (license license:artistic2.0)))
1596 (define-public tophat
1603 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1607 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1608 (modules '((guix build utils)))
1611 ;; Remove bundled SeqAn and samtools
1612 (delete-file-recursively "src/SeqAn-1.4.2")
1613 (delete-file-recursively "src/samtools-0.1.18")
1615 (build-system gnu-build-system)
1617 '(#:parallel-build? #f ; not supported
1619 (modify-phases %standard-phases
1620 (add-after 'unpack 'use-system-samtools
1621 (lambda* (#:key inputs #:allow-other-keys)
1622 (substitute* "src/Makefile.in"
1623 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1624 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1625 (("SAMPROG = samtools_0\\.1\\.18") "")
1626 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1627 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1628 (substitute* '("src/common.cpp"
1630 (("samtools_0.1.18") (which "samtools")))
1631 (substitute* '("src/common.h"
1632 "src/bam2fastx.cpp")
1633 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1634 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1635 (substitute* '("src/bwt_map.h"
1637 "src/align_status.h")
1638 (("#include <bam.h>") "#include <samtools/bam.h>")
1639 (("#include <sam.h>") "#include <samtools/sam.h>"))
1644 ("samtools" ,samtools-0.1)
1645 ("ncurses" ,ncurses)
1646 ("python" ,python-2)
1649 ("seqan" ,seqan-1)))
1650 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1651 (synopsis "Spliced read mapper for RNA-Seq data")
1653 "TopHat is a fast splice junction mapper for nucleotide sequence
1654 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1655 mammalian-sized genomes using the ultra high-throughput short read
1656 aligner Bowtie, and then analyzes the mapping results to identify
1657 splice junctions between exons.")
1658 ;; TopHat is released under the Boost Software License, Version 1.0
1659 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1660 (license license:boost1.0)))
1669 "https://github.com/lh3/bwa/releases/download/v"
1670 version "/bwa-" version ".tar.bz2"))
1673 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1674 (build-system gnu-build-system)
1676 '(#:tests? #f ;no "check" target
1678 (modify-phases %standard-phases
1680 (lambda* (#:key outputs #:allow-other-keys)
1681 (let ((bin (string-append
1682 (assoc-ref outputs "out") "/bin"))
1684 (assoc-ref outputs "out") "/share/doc/bwa"))
1686 (assoc-ref outputs "out") "/share/man/man1")))
1687 (install-file "bwa" bin)
1688 (install-file "README.md" doc)
1689 (install-file "bwa.1" man))
1691 ;; no "configure" script
1692 (delete 'configure))))
1693 (inputs `(("zlib" ,zlib)))
1694 ;; Non-portable SSE instructions are used so building fails on platforms
1695 ;; other than x86_64.
1696 (supported-systems '("x86_64-linux"))
1697 (home-page "http://bio-bwa.sourceforge.net/")
1698 (synopsis "Burrows-Wheeler sequence aligner")
1700 "BWA is a software package for mapping low-divergent sequences against a
1701 large reference genome, such as the human genome. It consists of three
1702 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1703 designed for Illumina sequence reads up to 100bp, while the rest two for
1704 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1705 features such as long-read support and split alignment, but BWA-MEM, which is
1706 the latest, is generally recommended for high-quality queries as it is faster
1707 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1708 70-100bp Illumina reads.")
1709 (license license:gpl3+)))
1711 (define-public bwa-pssm
1712 (package (inherit bwa)
1718 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1720 (file-name (git-file-name name version))
1723 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1724 (build-system gnu-build-system)
1729 (home-page "http://bwa-pssm.binf.ku.dk/")
1730 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1732 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1733 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1734 existing aligners it is fast and sensitive. Unlike most other aligners,
1735 however, it is also adaptible in the sense that one can direct the alignment
1736 based on known biases within the data set. It is coded as a modification of
1737 the original BWA alignment program and shares the genome index structure as
1738 well as many of the command line options.")
1739 (license license:gpl3+)))
1741 (define-public bwa-meth
1748 (url "https://github.com/brentp/bwa-meth.git")
1749 (commit (string-append "v" version))))
1750 (file-name (git-file-name name version))
1753 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1754 (build-system python-build-system)
1757 (modify-phases %standard-phases
1758 (add-after 'unpack 'keep-references-to-bwa
1759 (lambda* (#:key inputs #:allow-other-keys)
1760 (substitute* "bwameth.py"
1761 (("bwa (mem|index)" _ command)
1762 (string-append (which "bwa") " " command))
1763 ;; There's an ill-advised check for "samtools" on PATH.
1769 `(("python-toolshed" ,python-toolshed)))
1770 (home-page "https://github.com/brentp/bwa-meth")
1771 (synopsis "Fast and accurante alignment of BS-Seq reads")
1773 "BWA-Meth works for single-end reads and for paired-end reads from the
1774 directional protocol (most common). It uses the method employed by
1775 methylcoder and Bismark of in silico conversion of all C's to T's in both
1776 reference and reads. It recovers the original read (needed to tabulate
1777 methylation) by attaching it as a comment which BWA appends as a tag to the
1778 read. It performs favorably to existing aligners gauged by number of on and
1779 off-target reads for a capture method that targets CpG-rich region.")
1780 (license license:expat)))
1782 (define-public python-bx-python
1784 (name "python-bx-python")
1788 (uri (pypi-uri "bx-python" version))
1791 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1792 (build-system python-build-system)
1793 ;; Tests fail because test data are not included
1794 (arguments '(#:tests? #f))
1796 `(("python-numpy" ,python-numpy)
1797 ("python-six" ,python-six)))
1801 `(("python-lzo" ,python-lzo)
1802 ("python-nose" ,python-nose)
1803 ("python-cython" ,python-cython)))
1804 (home-page "https://github.com/bxlab/bx-python")
1805 (synopsis "Tools for manipulating biological data")
1807 "bx-python provides tools for manipulating biological data, particularly
1808 multiple sequence alignments.")
1809 (license license:expat)))
1811 (define-public python2-bx-python
1812 (package-with-python2 python-bx-python))
1814 (define-public python-pysam
1816 (name "python-pysam")
1820 ;; Test data is missing on PyPi.
1822 (url "https://github.com/pysam-developers/pysam.git")
1823 (commit (string-append "v" version))))
1824 (file-name (git-file-name name version))
1827 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1828 (modules '((guix build utils)))
1830 ;; Drop bundled htslib. TODO: Also remove samtools
1832 (delete-file-recursively "htslib")
1834 (build-system python-build-system)
1836 `(#:modules ((ice-9 ftw)
1838 (guix build python-build-system)
1841 (modify-phases %standard-phases
1842 (add-before 'build 'set-flags
1843 (lambda* (#:key inputs #:allow-other-keys)
1844 (setenv "HTSLIB_MODE" "external")
1845 (setenv "HTSLIB_LIBRARY_DIR"
1846 (string-append (assoc-ref inputs "htslib") "/lib"))
1847 (setenv "HTSLIB_INCLUDE_DIR"
1848 (string-append (assoc-ref inputs "htslib") "/include"))
1849 (setenv "LDFLAGS" "-lncurses")
1850 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1853 (lambda* (#:key inputs outputs #:allow-other-keys)
1854 ;; This file contains tests that require a connection to the
1856 (delete-file "tests/tabix_test.py")
1857 ;; FIXME: This test fails
1858 (delete-file "tests/AlignmentFile_test.py")
1859 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1860 (setenv "PYTHONPATH"
1862 (getenv "PYTHONPATH")
1863 ":" (getcwd) "/build/"
1864 (car (scandir "build"
1865 (negate (cut string-prefix? "." <>))))))
1866 ;; Step out of source dir so python does not import from CWD.
1867 (with-directory-excursion "tests"
1868 (setenv "HOME" "/tmp")
1869 (invoke "make" "-C" "pysam_data")
1870 (invoke "make" "-C" "cbcf_data")
1871 ;; Running nosetests without explicitly asking for a single
1872 ;; process leads to a crash. Running with multiple processes
1873 ;; fails because the tests are not designed to run in parallel.
1875 ;; FIXME: tests keep timing out on some systems.
1876 (invoke "nosetests" "-v" "--processes" "1")))))))
1878 `(("htslib" ,htslib))) ; Included from installed header files.
1880 `(("ncurses" ,ncurses)
1884 `(("python-cython" ,python-cython)
1885 ;; Dependencies below are are for tests only.
1886 ("samtools" ,samtools)
1887 ("bcftools" ,bcftools)
1888 ("python-nose" ,python-nose)))
1889 (home-page "https://github.com/pysam-developers/pysam")
1890 (synopsis "Python bindings to the SAMtools C API")
1892 "Pysam is a Python module for reading and manipulating files in the
1893 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1894 also includes an interface for tabix.")
1895 (license license:expat)))
1897 (define-public python2-pysam
1898 (package-with-python2 python-pysam))
1900 (define-public python-twobitreader
1902 (name "python-twobitreader")
1907 (url "https://github.com/benjschiller/twobitreader")
1909 (file-name (git-file-name name version))
1912 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1913 (build-system python-build-system)
1914 ;; Tests are not included
1915 (arguments '(#:tests? #f))
1917 `(("python-sphinx" ,python-sphinx)))
1918 (home-page "https://github.com/benjschiller/twobitreader")
1919 (synopsis "Python library for reading .2bit files")
1921 "twobitreader is a Python library for reading .2bit files as used by the
1922 UCSC genome browser.")
1923 (license license:artistic2.0)))
1925 (define-public python2-twobitreader
1926 (package-with-python2 python-twobitreader))
1928 (define-public python-plastid
1930 (name "python-plastid")
1934 (uri (pypi-uri "plastid" version))
1937 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1938 (build-system python-build-system)
1940 ;; Some test files are not included.
1943 `(("python-numpy" ,python-numpy)
1944 ("python-scipy" ,python-scipy)
1945 ("python-pandas" ,python-pandas)
1946 ("python-pysam" ,python-pysam)
1947 ("python-matplotlib" ,python-matplotlib)
1948 ("python-biopython" ,python-biopython)
1949 ("python-twobitreader" ,python-twobitreader)
1950 ("python-termcolor" ,python-termcolor)))
1952 `(("python-cython" ,python-cython)
1953 ("python-nose" ,python-nose)))
1954 (home-page "https://github.com/joshuagryphon/plastid")
1955 (synopsis "Python library for genomic analysis")
1957 "plastid is a Python library for genomic analysis – in particular,
1958 high-throughput sequencing data – with an emphasis on simplicity.")
1959 (license license:bsd-3)))
1961 (define-public python2-plastid
1962 (package-with-python2 python-plastid))
1964 (define-public tetoolkit
1971 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1973 (file-name (git-file-name name version))
1976 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1977 (build-system python-build-system)
1979 `(#:python ,python-2 ; not guaranteed to work with Python 3
1981 (modify-phases %standard-phases
1982 (add-after 'unpack 'make-writable
1984 (for-each make-file-writable (find-files "."))
1986 (add-after 'unpack 'patch-invocations
1987 (lambda* (#:key inputs #:allow-other-keys)
1988 (substitute* '("bin/TEtranscripts"
1991 (string-append "'" (which "sort") " "))
1993 (string-append "'" (which "rm") " -f "))
1994 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
1995 (substitute* "TEToolkit/IO/ReadInputs.py"
1996 (("BamToBED") (which "bamToBed")))
1997 (substitute* "TEToolkit/Normalization.py"
1999 (string-append "\"" (which "Rscript") "\"")))
2001 (add-after 'install 'wrap-program
2002 (lambda* (#:key outputs #:allow-other-keys)
2003 ;; Make sure the executables find R packages.
2004 (let ((out (assoc-ref outputs "out")))
2007 (wrap-program (string-append out "/bin/" script)
2008 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2013 `(("coreutils" ,coreutils)
2014 ("bedtools" ,bedtools)
2015 ("python-argparse" ,python2-argparse)
2016 ("python-pysam" ,python2-pysam)
2017 ("r-minimal" ,r-minimal)
2018 ("r-deseq2" ,r-deseq2)))
2019 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2020 (synopsis "Transposable elements in differential enrichment analysis")
2022 "This is package for including transposable elements in differential
2023 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2024 RNA-seq (and similar data) and annotates reads to both genes and transposable
2025 elements. TEtranscripts then performs differential analysis using DESeq2.
2026 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2027 are not included due to their size.")
2028 (license license:gpl3+)))
2030 (define-public cd-hit
2036 (uri (string-append "https://github.com/weizhongli/cdhit"
2037 "/releases/download/V" version
2039 "-2017-0621-source.tar.gz"))
2042 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2043 (build-system gnu-build-system)
2045 `(#:tests? #f ; there are no tests
2047 ;; Executables are copied directly to the PREFIX.
2048 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2049 ;; Support longer sequences (e.g. Pacbio sequences)
2052 (modify-phases %standard-phases
2053 ;; No "configure" script
2055 ;; Remove sources of non-determinism
2056 (add-after 'unpack 'be-timeless
2058 (substitute* "cdhit-utility.c++"
2059 ((" \\(built on \" __DATE__ \"\\)") ""))
2060 (substitute* "cdhit-common.c++"
2061 (("__DATE__") "\"0\"")
2062 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2064 ;; The "install" target does not create the target directory.
2065 (add-before 'install 'create-target-dir
2066 (lambda* (#:key outputs #:allow-other-keys)
2067 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2071 (home-page "http://weizhongli-lab.org/cd-hit/")
2072 (synopsis "Cluster and compare protein or nucleotide sequences")
2074 "CD-HIT is a program for clustering and comparing protein or nucleotide
2075 sequences. CD-HIT is designed to be fast and handle extremely large
2077 ;; The manual says: "It can be copied under the GNU General Public License
2078 ;; version 2 (GPLv2)."
2079 (license license:gpl2)))
2081 (define-public clipper
2088 (url "https://github.com/YeoLab/clipper.git")
2090 (file-name (git-file-name name version))
2093 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2094 (modules '((guix build utils)))
2097 ;; remove unnecessary setup dependency
2098 (substitute* "setup.py"
2099 (("setup_requires = .*") ""))
2101 (build-system python-build-system)
2103 `(#:python ,python-2 ; only Python 2 is supported
2105 (modify-phases %standard-phases
2106 ;; This is fixed in upstream commit
2107 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2108 (add-after 'unpack 'fix-typo
2110 (substitute* "clipper/src/readsToWiggle.pyx"
2114 `(("htseq" ,python2-htseq)
2115 ("python-pybedtools" ,python2-pybedtools)
2116 ("python-cython" ,python2-cython)
2117 ("python-scikit-learn" ,python2-scikit-learn)
2118 ("python-matplotlib" ,python2-matplotlib)
2119 ("python-pandas" ,python2-pandas)
2120 ("python-pysam" ,python2-pysam)
2121 ("python-numpy" ,python2-numpy)
2122 ("python-scipy" ,python2-scipy)))
2124 `(("python-mock" ,python2-mock) ; for tests
2125 ("python-nose" ,python2-nose) ; for tests
2126 ("python-pytz" ,python2-pytz))) ; for tests
2127 (home-page "https://github.com/YeoLab/clipper")
2128 (synopsis "CLIP peak enrichment recognition")
2130 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2131 (license license:gpl2)))
2133 (define-public codingquarry
2135 (name "codingquarry")
2140 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2144 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2145 (build-system gnu-build-system)
2147 '(#:tests? #f ; no "check" target
2149 (modify-phases %standard-phases
2152 (lambda* (#:key outputs #:allow-other-keys)
2153 (let* ((out (assoc-ref outputs "out"))
2154 (bin (string-append out "/bin"))
2155 (doc (string-append out "/share/doc/codingquarry")))
2156 (install-file "INSTRUCTIONS.pdf" doc)
2157 (copy-recursively "QuarryFiles"
2158 (string-append out "/QuarryFiles"))
2159 (install-file "CodingQuarry" bin)
2160 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2162 (inputs `(("openmpi" ,openmpi)))
2163 (native-search-paths
2164 (list (search-path-specification
2165 (variable "QUARRY_PATH")
2166 (files '("QuarryFiles")))))
2167 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2168 (synopsis "Fungal gene predictor")
2169 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2170 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2171 (home-page "https://sourceforge.net/projects/codingquarry/")
2172 (license license:gpl3+)))
2174 (define-public couger
2181 "http://couger.oit.duke.edu/static/assets/COUGER"
2185 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2186 (build-system gnu-build-system)
2190 (modify-phases %standard-phases
2195 (lambda* (#:key outputs #:allow-other-keys)
2196 (let* ((out (assoc-ref outputs "out"))
2197 (bin (string-append out "/bin")))
2198 (copy-recursively "src" (string-append out "/src"))
2200 ;; Add "src" directory to module lookup path.
2201 (substitute* "couger"
2203 (string-append "import sys\nsys.path.append(\""
2204 out "\")\nfrom argparse")))
2205 (install-file "couger" bin))
2208 'install 'wrap-program
2209 (lambda* (#:key inputs outputs #:allow-other-keys)
2210 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2211 (let* ((out (assoc-ref outputs "out"))
2212 (path (getenv "PYTHONPATH")))
2213 (wrap-program (string-append out "/bin/couger")
2214 `("PYTHONPATH" ":" prefix (,path))))
2217 `(("python" ,python-2)
2218 ("python2-pillow" ,python2-pillow)
2219 ("python2-numpy" ,python2-numpy)
2220 ("python2-scipy" ,python2-scipy)
2221 ("python2-matplotlib" ,python2-matplotlib)))
2223 `(("r-minimal" ,r-minimal)
2225 ("randomjungle" ,randomjungle)))
2227 `(("unzip" ,unzip)))
2228 (home-page "http://couger.oit.duke.edu")
2229 (synopsis "Identify co-factors in sets of genomic regions")
2231 "COUGER can be applied to any two sets of genomic regions bound by
2232 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2233 putative co-factors that provide specificity to each TF. The framework
2234 determines the genomic targets uniquely-bound by each TF, and identifies a
2235 small set of co-factors that best explain the in vivo binding differences
2236 between the two TFs.
2238 COUGER uses classification algorithms (support vector machines and random
2239 forests) with features that reflect the DNA binding specificities of putative
2240 co-factors. The features are generated either from high-throughput TF-DNA
2241 binding data (from protein binding microarray experiments), or from large
2242 collections of DNA motifs.")
2243 (license license:gpl3+)))
2245 (define-public clustal-omega
2247 (name "clustal-omega")
2251 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2255 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2256 (build-system gnu-build-system)
2258 `(("argtable" ,argtable)))
2259 (home-page "http://www.clustal.org/omega/")
2260 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2262 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2263 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2264 of handling data-sets of hundreds of thousands of sequences in reasonable
2266 (license license:gpl2+)))
2268 (define-public crossmap
2274 (uri (pypi-uri "CrossMap" version))
2277 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2278 (build-system python-build-system)
2279 (arguments `(#:python ,python-2))
2281 `(("python-bx-python" ,python2-bx-python)
2282 ("python-numpy" ,python2-numpy)
2283 ("python-pysam" ,python2-pysam)
2286 `(("python-cython" ,python2-cython)
2287 ("python-nose" ,python2-nose)))
2288 (home-page "http://crossmap.sourceforge.net/")
2289 (synopsis "Convert genome coordinates between assemblies")
2291 "CrossMap is a program for conversion of genome coordinates or annotation
2292 files between different genome assemblies. It supports most commonly used
2293 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2294 (license license:gpl2+)))
2296 (define-public python-dnaio
2298 (name "python-dnaio")
2303 (uri (pypi-uri "dnaio" version))
2306 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2307 (build-system python-build-system)
2309 `(("python-cython" ,python-cython)
2310 ("python-pytest" ,python-pytest)
2311 ("python-xopen" ,python-xopen)))
2312 (home-page "https://github.com/marcelm/dnaio/")
2313 (synopsis "Read FASTA and FASTQ files efficiently")
2315 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2316 files. The code was previously part of the cutadapt tool.")
2317 (license license:expat)))
2319 (define-public cutadapt
2325 (uri (pypi-uri "cutadapt" version))
2328 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2329 (build-system python-build-system)
2331 `(("python-dnaio" ,python-dnaio)
2332 ("python-xopen" ,python-xopen)))
2334 `(("python-cython" ,python-cython)
2335 ("python-pytest" ,python-pytest)
2336 ("python-setuptools-scm" ,python-setuptools-scm)))
2337 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2338 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2340 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2341 other types of unwanted sequence from high-throughput sequencing reads.")
2342 (license license:expat)))
2344 (define-public libbigwig
2351 (url "https://github.com/dpryan79/libBigWig.git")
2353 (file-name (git-file-name name version))
2356 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2357 (build-system gnu-build-system)
2359 `(#:test-target "test"
2360 #:tests? #f ; tests require access to the web
2363 (string-append "prefix=" (assoc-ref %outputs "out")))
2365 (modify-phases %standard-phases
2366 (delete 'configure))))
2371 `(("doxygen" ,doxygen)
2373 ("python" ,python-2)))
2374 (home-page "https://github.com/dpryan79/libBigWig")
2375 (synopsis "C library for handling bigWig files")
2377 "This package provides a C library for parsing local and remote BigWig
2379 (license license:expat)))
2381 (define-public python-pybigwig
2383 (name "python-pybigwig")
2387 (uri (pypi-uri "pyBigWig" version))
2390 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2391 (modules '((guix build utils)))
2394 ;; Delete bundled libBigWig sources
2395 (delete-file-recursively "libBigWig")
2397 (build-system python-build-system)
2400 (modify-phases %standard-phases
2401 (add-after 'unpack 'link-with-libBigWig
2402 (lambda* (#:key inputs #:allow-other-keys)
2403 (substitute* "setup.py"
2404 (("libs=\\[") "libs=[\"BigWig\", "))
2407 `(("python-numpy" ,python-numpy)))
2409 `(("libbigwig" ,libbigwig)
2412 (home-page "https://github.com/dpryan79/pyBigWig")
2413 (synopsis "Access bigWig files in Python using libBigWig")
2415 "This package provides Python bindings to the libBigWig library for
2416 accessing bigWig files.")
2417 (license license:expat)))
2419 (define-public python2-pybigwig
2420 (package-with-python2 python-pybigwig))
2422 (define-public python-dendropy
2424 (name "python-dendropy")
2429 ;; Source from GitHub so that tests are included.
2431 (url "https://github.com/jeetsukumaran/DendroPy.git")
2432 (commit (string-append "v" version))))
2433 (file-name (git-file-name name version))
2436 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2437 (build-system python-build-system)
2438 (home-page "http://packages.python.org/DendroPy/")
2439 (synopsis "Library for phylogenetics and phylogenetic computing")
2441 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2442 writing, simulation, processing and manipulation of phylogenetic
2443 trees (phylogenies) and characters.")
2444 (license license:bsd-3)))
2446 (define-public python2-dendropy
2447 (let ((base (package-with-python2 python-dendropy)))
2452 (modify-phases %standard-phases
2453 (add-after 'unpack 'remove-failing-test
2455 ;; This test fails when the full test suite is run, as documented
2456 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2457 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2458 (("test_collection_comments_and_annotations")
2459 "do_not_test_collection_comments_and_annotations"))
2461 ,@(package-arguments base))))))
2463 (define-public python-py2bit
2465 (name "python-py2bit")
2470 (uri (pypi-uri "py2bit" version))
2473 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2474 (build-system python-build-system)
2475 (home-page "https://github.com/dpryan79/py2bit")
2476 (synopsis "Access 2bit files using lib2bit")
2478 "This package provides Python bindings for lib2bit to access 2bit files
2480 (license license:expat)))
2482 (define-public deeptools
2489 (url "https://github.com/deeptools/deepTools.git")
2491 (file-name (git-file-name name version))
2494 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2495 (build-system python-build-system)
2498 (modify-phases %standard-phases
2499 ;; This phase fails, but it's not needed.
2500 (delete 'reset-gzip-timestamps))))
2502 `(("python-plotly" ,python-plotly)
2503 ("python-scipy" ,python-scipy)
2504 ("python-numpy" ,python-numpy)
2505 ("python-numpydoc" ,python-numpydoc)
2506 ("python-matplotlib" ,python-matplotlib)
2507 ("python-pysam" ,python-pysam)
2508 ("python-py2bit" ,python-py2bit)
2509 ("python-pybigwig" ,python-pybigwig)))
2511 `(("python-mock" ,python-mock) ;for tests
2512 ("python-nose" ,python-nose) ;for tests
2513 ("python-pytz" ,python-pytz))) ;for tests
2514 (home-page "https://github.com/deeptools/deepTools")
2515 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2517 "DeepTools addresses the challenge of handling the large amounts of data
2518 that are now routinely generated from DNA sequencing centers. To do so,
2519 deepTools contains useful modules to process the mapped reads data to create
2520 coverage files in standard bedGraph and bigWig file formats. By doing so,
2521 deepTools allows the creation of normalized coverage files or the comparison
2522 between two files (for example, treatment and control). Finally, using such
2523 normalized and standardized files, multiple visualizations can be created to
2524 identify enrichments with functional annotations of the genome.")
2525 (license license:gpl3+)))
2527 (define-public delly
2534 (url "https://github.com/dellytools/delly.git")
2535 (commit (string-append "v" version))))
2536 (file-name (git-file-name name version))
2538 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2539 (modules '((guix build utils)))
2542 (delete-file-recursively "src/htslib")
2544 (build-system gnu-build-system)
2546 `(#:tests? #f ; There are no tests to run.
2548 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2549 (string-append "prefix=" (assoc-ref %outputs "out")))
2551 (modify-phases %standard-phases
2552 (delete 'configure) ; There is no configure phase.
2553 (add-after 'install 'install-templates
2554 (lambda* (#:key outputs #:allow-other-keys)
2555 (let ((templates (string-append (assoc-ref outputs "out")
2556 "/share/delly/templates")))
2558 (copy-recursively "excludeTemplates" templates)
2565 (home-page "https://github.com/dellytools/delly")
2566 (synopsis "Integrated structural variant prediction method")
2567 (description "Delly is an integrated structural variant prediction method
2568 that can discover and genotype deletions, tandem duplications, inversions and
2569 translocations at single-nucleotide resolution in short-read massively parallel
2570 sequencing data. It uses paired-ends and split-reads to sensitively and
2571 accurately delineate genomic rearrangements throughout the genome.")
2572 (license license:gpl3+)))
2574 (define-public diamond
2581 (url "https://github.com/bbuchfink/diamond.git")
2582 (commit (string-append "v" version))))
2583 (file-name (git-file-name name version))
2586 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2587 (build-system cmake-build-system)
2589 '(#:tests? #f ; no "check" target
2591 (modify-phases %standard-phases
2592 (add-after 'unpack 'remove-native-compilation
2594 (substitute* "CMakeLists.txt" (("-march=native") ""))
2598 (home-page "https://github.com/bbuchfink/diamond")
2599 (synopsis "Accelerated BLAST compatible local sequence aligner")
2601 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2602 translated DNA query sequences against a protein reference database (BLASTP
2603 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2604 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2605 data and settings.")
2606 (license license:agpl3+)))
2608 (define-public discrover
2616 (url "https://github.com/maaskola/discrover.git")
2618 (file-name (git-file-name name version))
2621 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2622 (build-system cmake-build-system)
2624 `(#:tests? #f ; there are no tests
2626 (modify-phases %standard-phases
2627 (add-after 'unpack 'fix-latex-errors
2629 (with-fluids ((%default-port-encoding #f))
2630 (substitute* "doc/references.bib"
2631 (("\\{S\\}illanp[^,]+,")
2632 "{S}illanp{\\\"a}{\\\"a},")))
2633 ;; XXX: I just can't get pdflatex to not complain about these
2634 ;; characters. They end up in the manual via the generated
2635 ;; discrover-cli-help.txt.
2636 (substitute* "src/hmm/cli.cpp"
2640 ;; This seems to be a syntax error.
2641 (substitute* "doc/discrover-manual.tex"
2642 (("theverbbox\\[t\\]") "theverbbox"))
2644 (add-after 'unpack 'add-missing-includes
2646 (substitute* "src/executioninformation.hpp"
2647 (("#define EXECUTIONINFORMATION_HPP" line)
2648 (string-append line "\n#include <random>")))
2649 (substitute* "src/plasma/fasta.hpp"
2650 (("#define FASTA_HPP" line)
2651 (string-append line "\n#include <random>")))
2653 ;; FIXME: this is needed because we're using texlive-union, which
2654 ;; doesn't handle fonts correctly. It expects to be able to generate
2655 ;; fonts in the home directory.
2656 (add-before 'build 'setenv-HOME
2657 (lambda _ (setenv "HOME" "/tmp") #t)))))
2661 ("rmath-standalone" ,rmath-standalone)))
2663 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2664 texlive-fonts-amsfonts
2667 texlive-latex-examplep
2668 texlive-latex-hyperref
2670 texlive-latex-natbib
2671 texlive-bibtex ; style files used by natbib
2672 texlive-latex-pgf ; tikz
2673 texlive-latex-verbatimbox)))
2674 ("imagemagick" ,imagemagick)))
2675 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2676 (synopsis "Discover discriminative nucleotide sequence motifs")
2677 (description "Discrover is a motif discovery method to find binding sites
2678 of nucleic acid binding proteins.")
2679 (license license:gpl3+)))
2681 (define-public eigensoft
2689 (url "https://github.com/DReichLab/EIG.git")
2690 (commit (string-append "v" version))))
2691 (file-name (git-file-name name version))
2694 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2695 (modules '((guix build utils)))
2696 ;; Remove pre-built binaries.
2698 (delete-file-recursively "bin")
2701 (build-system gnu-build-system)
2703 `(#:tests? #f ; There are no tests.
2704 #:make-flags '("CC=gcc")
2706 (modify-phases %standard-phases
2707 ;; There is no configure phase, but the Makefile is in a
2710 (lambda _ (chdir "src") #t))
2711 ;; The provided install target only copies executables to
2712 ;; the "bin" directory in the build root.
2713 (add-after 'install 'actually-install
2714 (lambda* (#:key outputs #:allow-other-keys)
2715 (let* ((out (assoc-ref outputs "out"))
2716 (bin (string-append out "/bin")))
2717 (for-each (lambda (file)
2718 (install-file file bin))
2719 (find-files "../bin" ".*"))
2724 ("openblas" ,openblas)
2726 ("gfortran" ,gfortran "lib")))
2727 (home-page "https://github.com/DReichLab/EIG")
2728 (synopsis "Tools for population genetics")
2729 (description "The EIGENSOFT package provides tools for population
2730 genetics and stratification correction. EIGENSOFT implements methods commonly
2731 used in population genetics analyses such as PCA, computation of Tracy-Widom
2732 statistics, and finding related individuals in structured populations. It
2733 comes with a built-in plotting script and supports multiple file formats and
2734 quantitative phenotypes.")
2735 ;; The license of the eigensoft tools is Expat, but since it's
2736 ;; linking with the GNU Scientific Library (GSL) the effective
2737 ;; license is the GPL.
2738 (license license:gpl3+)))
2740 (define-public edirect
2743 (version "12.1.20190819")
2746 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2747 "/versions/" version
2748 "/edirect-" version ".tar.gz"))
2751 "1i9s9mppcfqd60pfywpm8vdyz5vpnyslw22nd7dv0bhykrdnkz9g"))))
2752 (build-system perl-build-system)
2755 (modify-phases %standard-phases
2758 (delete 'check) ; simple check after install
2760 (lambda* (#:key outputs #:allow-other-keys)
2761 (install-file "edirect.pl"
2762 (string-append (assoc-ref outputs "out") "/bin"))
2764 (add-after 'install 'wrap-program
2765 (lambda* (#:key outputs #:allow-other-keys)
2766 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2767 (let* ((out (assoc-ref outputs "out"))
2768 (path (getenv "PERL5LIB")))
2769 (wrap-program (string-append out "/bin/edirect.pl")
2770 `("PERL5LIB" ":" prefix (,path))))
2772 (add-after 'wrap-program 'check
2773 (lambda* (#:key outputs #:allow-other-keys)
2774 (invoke (string-append (assoc-ref outputs "out")
2779 `(("perl-html-parser" ,perl-html-parser)
2780 ("perl-encode-locale" ,perl-encode-locale)
2781 ("perl-file-listing" ,perl-file-listing)
2782 ("perl-html-tagset" ,perl-html-tagset)
2783 ("perl-html-tree" ,perl-html-tree)
2784 ("perl-http-cookies" ,perl-http-cookies)
2785 ("perl-http-date" ,perl-http-date)
2786 ("perl-http-message" ,perl-http-message)
2787 ("perl-http-negotiate" ,perl-http-negotiate)
2788 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2789 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2790 ("perl-net-http" ,perl-net-http)
2791 ("perl-uri" ,perl-uri)
2792 ("perl-www-robotrules" ,perl-www-robotrules)
2793 ("perl-xml-simple" ,perl-xml-simple)
2795 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2796 (synopsis "Tools for accessing the NCBI's set of databases")
2798 "Entrez Direct (EDirect) is a method for accessing the National Center
2799 for Biotechnology Information's (NCBI) set of interconnected
2800 databases (publication, sequence, structure, gene, variation, expression,
2801 etc.) from a terminal. Functions take search terms from command-line
2802 arguments. Individual operations are combined to build multi-step queries.
2803 Record retrieval and formatting normally complete the process.
2805 EDirect also provides an argument-driven function that simplifies the
2806 extraction of data from document summaries or other results that are returned
2807 in structured XML format. This can eliminate the need for writing custom
2808 software to answer ad hoc questions.")
2809 (license license:public-domain)))
2811 (define-public exonerate
2820 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2821 "exonerate-" version ".tar.gz"))
2824 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2825 (build-system gnu-build-system)
2827 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2829 `(("pkg-config" ,pkg-config)))
2833 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2834 (synopsis "Generic tool for biological sequence alignment")
2836 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2837 the alignment of sequences using a many alignment models, either exhaustive
2838 dynamic programming or a variety of heuristics.")
2839 (license license:gpl3)))
2841 (define-public express
2849 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2850 version "/express-" version "-src.tgz"))
2853 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2854 (build-system cmake-build-system)
2856 `(#:tests? #f ;no "check" target
2858 (modify-phases %standard-phases
2859 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2860 (lambda* (#:key inputs #:allow-other-keys)
2861 (substitute* "CMakeLists.txt"
2862 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2863 "set(Boost_USE_STATIC_LIBS OFF)")
2864 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2865 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2866 (substitute* "src/CMakeLists.txt"
2867 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2868 (string-append (assoc-ref inputs "bamtools") "/lib"))
2869 (("libprotobuf.a") "libprotobuf.so"))
2873 ("bamtools" ,bamtools)
2874 ("protobuf" ,protobuf)
2876 (home-page "http://bio.math.berkeley.edu/eXpress")
2877 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2879 "eXpress is a streaming tool for quantifying the abundances of a set of
2880 target sequences from sampled subsequences. Example applications include
2881 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2882 analysis (from RNA-Seq), transcription factor binding quantification in
2883 ChIP-Seq, and analysis of metagenomic data.")
2884 (license license:artistic2.0)))
2886 (define-public express-beta-diversity
2888 (name "express-beta-diversity")
2893 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2894 (commit (string-append "v" version))))
2895 (file-name (git-file-name name version))
2898 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2899 (build-system gnu-build-system)
2902 (modify-phases %standard-phases
2904 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2906 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2908 (lambda* (#:key outputs #:allow-other-keys)
2909 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2910 (install-file "../scripts/convertToEBD.py" bin)
2911 (install-file "../bin/ExpressBetaDiversity" bin)
2914 `(("python" ,python-2)))
2915 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2916 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2918 "Express Beta Diversity (EBD) calculates ecological beta diversity
2919 (dissimilarity) measures between biological communities. EBD implements a
2920 variety of diversity measures including those that make use of phylogenetic
2921 similarity of community members.")
2922 (license license:gpl3+)))
2924 (define-public fasttree
2931 "http://www.microbesonline.org/fasttree/FastTree-"
2935 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2936 (build-system gnu-build-system)
2938 `(#:tests? #f ; no "check" target
2940 (modify-phases %standard-phases
2944 (lambda* (#:key source #:allow-other-keys)
2947 "-finline-functions"
2958 "-finline-functions"
2967 (lambda* (#:key outputs #:allow-other-keys)
2968 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2969 (install-file "FastTree" bin)
2970 (install-file "FastTreeMP" bin)
2972 (home-page "http://www.microbesonline.org/fasttree")
2973 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2975 "FastTree can handle alignments with up to a million of sequences in a
2976 reasonable amount of time and memory. For large alignments, FastTree is
2977 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2978 (license license:gpl2+)))
2980 (define-public fastx-toolkit
2982 (name "fastx-toolkit")
2988 "https://github.com/agordon/fastx_toolkit/releases/download/"
2989 version "/fastx_toolkit-" version ".tar.bz2"))
2992 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2993 (build-system gnu-build-system)
2995 `(("libgtextutils" ,libgtextutils)))
2997 `(("pkg-config" ,pkg-config)))
2998 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2999 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3001 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3002 FASTA/FASTQ files preprocessing.
3004 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3005 containing multiple short-reads sequences. The main processing of such
3006 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3007 is sometimes more productive to preprocess the files before mapping the
3008 sequences to the genome---manipulating the sequences to produce better mapping
3009 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3010 (license license:agpl3+)))
3012 (define-public flexbar
3019 (url "https://github.com/seqan/flexbar.git")
3020 (commit (string-append "v" version))))
3021 (file-name (git-file-name name version))
3024 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3025 (build-system cmake-build-system)
3028 (modify-phases %standard-phases
3029 (add-after 'unpack 'do-not-tune-to-CPU
3031 (substitute* "src/CMakeLists.txt"
3032 ((" -march=native") ""))
3035 (lambda* (#:key outputs #:allow-other-keys)
3036 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3037 (with-directory-excursion "../source/test"
3038 (invoke "bash" "flexbar_test.sh"))
3041 (lambda* (#:key outputs #:allow-other-keys)
3042 (let* ((out (string-append (assoc-ref outputs "out")))
3043 (bin (string-append out "/bin/")))
3044 (install-file "flexbar" bin))
3050 `(("pkg-config" ,pkg-config)
3052 (home-page "https://github.com/seqan/flexbar")
3053 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3055 "Flexbar preprocesses high-throughput nucleotide sequencing data
3056 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3057 Moreover, trimming and filtering features are provided. Flexbar increases
3058 read mapping rates and improves genome and transcriptome assemblies. It
3059 supports next-generation sequencing data in fasta/q and csfasta/q format from
3060 Illumina, Roche 454, and the SOLiD platform.")
3061 (license license:bsd-3)))
3063 (define-public fraggenescan
3065 (name "fraggenescan")
3071 (string-append "mirror://sourceforge/fraggenescan/"
3072 "FragGeneScan" version ".tar.gz"))
3074 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3075 (build-system gnu-build-system)
3078 (modify-phases %standard-phases
3080 (add-before 'build 'patch-paths
3081 (lambda* (#:key outputs #:allow-other-keys)
3082 (let* ((out (string-append (assoc-ref outputs "out")))
3083 (share (string-append out "/share/fraggenescan/")))
3084 (substitute* "run_FragGeneScan.pl"
3086 (string-append "system(\"" (which "rm")))
3088 (string-append "system(\"" (which "mv")))
3089 (("\\\"awk") (string-append "\"" (which "awk")))
3090 ;; This script and other programs expect the training files
3091 ;; to be in the non-standard location bin/train/XXX. Change
3092 ;; this to be share/fraggenescan/train/XXX instead.
3093 (("^\\$train.file = \\$dir.*")
3094 (string-append "$train_file = \""
3096 "train/\".$FGS_train_file;")))
3097 (substitute* "run_hmm.c"
3098 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3099 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3103 (invoke "make" "clean")
3104 (invoke "make" "fgs")
3107 (lambda* (#:key outputs #:allow-other-keys)
3108 (let* ((out (string-append (assoc-ref outputs "out")))
3109 (bin (string-append out "/bin/"))
3110 (share (string-append out "/share/fraggenescan/train")))
3111 (install-file "run_FragGeneScan.pl" bin)
3112 (install-file "FragGeneScan" bin)
3113 (copy-recursively "train" share))
3116 (add-after 'install 'post-install-check
3117 ;; In lieu of 'make check', run one of the examples and check the
3118 ;; output files gets created.
3119 (lambda* (#:key outputs #:allow-other-keys)
3120 (let* ((out (string-append (assoc-ref outputs "out")))
3121 (bin (string-append out "/bin/"))
3122 (frag (string-append bin "run_FragGeneScan.pl")))
3123 ;; Test complete genome.
3125 "-genome=./example/NC_000913.fna"
3129 (unless (and (file-exists? "test2.faa")
3130 (file-exists? "test2.ffn")
3131 (file-exists? "test2.gff")
3132 (file-exists? "test2.out"))
3133 (error "Expected files do not exist."))
3134 ;; Test incomplete sequences.
3136 "-genome=./example/NC_000913-fgs.ffn"
3143 ("python" ,python-2))) ;not compatible with python 3.
3144 (home-page "https://sourceforge.net/projects/fraggenescan/")
3145 (synopsis "Finds potentially fragmented genes in short reads")
3147 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3148 short and error-prone DNA sequencing reads. It can also be applied to predict
3149 genes in incomplete assemblies or complete genomes.")
3150 ;; GPL3+ according to private correspondense with the authors.
3151 (license license:gpl3+)))
3153 (define-public fxtract
3154 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3162 (url "https://github.com/ctSkennerton/fxtract.git")
3164 (file-name (git-file-name name version))
3167 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3168 (build-system gnu-build-system)
3170 `(#:make-flags (list
3171 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3173 #:test-target "fxtract_test"
3175 (modify-phases %standard-phases
3177 (add-before 'build 'copy-util
3178 (lambda* (#:key inputs #:allow-other-keys)
3180 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3182 ;; Do not use make install as this requires additional dependencies.
3184 (lambda* (#:key outputs #:allow-other-keys)
3185 (let* ((out (assoc-ref outputs "out"))
3186 (bin (string-append out"/bin")))
3187 (install-file "fxtract" bin)
3193 ;; ctskennerton-util is licensed under GPL2.
3194 `(("ctskennerton-util"
3198 (url "https://github.com/ctSkennerton/util.git")
3199 (commit util-commit)))
3200 (file-name (string-append
3201 "ctstennerton-util-" util-commit "-checkout"))
3204 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3205 (home-page "https://github.com/ctSkennerton/fxtract")
3206 (synopsis "Extract sequences from FASTA and FASTQ files")
3208 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3209 or FASTQ) file given a subsequence. It uses a simple substring search for
3210 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3211 lookups or multi-pattern searching as required. By default fxtract looks in
3212 the sequence of each record but can also be told to look in the header,
3213 comment or quality sections.")
3214 ;; 'util' requires SSE instructions.
3215 (supported-systems '("x86_64-linux"))
3216 (license license:expat))))
3218 (define-public gemma
3225 (url "https://github.com/xiangzhou/GEMMA.git")
3226 (commit (string-append "v" version))))
3227 (file-name (git-file-name name version))
3230 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3233 ("gfortran" ,gfortran "lib")
3236 ("openblas" ,openblas)
3238 (build-system gnu-build-system)
3241 '(,@(match (%current-system)
3243 '("FORCE_DYNAMIC=1"))
3245 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3247 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3249 (modify-phases %standard-phases
3251 (add-after 'unpack 'find-eigen
3252 (lambda* (#:key inputs #:allow-other-keys)
3253 ;; Ensure that Eigen headers can be found
3254 (setenv "CPLUS_INCLUDE_PATH"
3255 (string-append (assoc-ref inputs "eigen")
3258 (add-before 'build 'bin-mkdir
3263 (lambda* (#:key outputs #:allow-other-keys)
3264 (let ((out (assoc-ref outputs "out")))
3265 (install-file "bin/gemma"
3269 #:tests? #f)) ; no tests included yet
3270 (home-page "https://github.com/xiangzhou/GEMMA")
3271 (synopsis "Tool for genome-wide efficient mixed model association")
3273 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3274 standard linear mixed model resolver with application in genome-wide
3275 association studies (GWAS).")
3276 (license license:gpl3)))
3285 (url "https://github.com/nboley/grit.git")
3287 (file-name (git-file-name name version))
3290 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3291 (build-system python-build-system)
3293 `(#:python ,python-2
3295 (modify-phases %standard-phases
3296 (add-after 'unpack 'generate-from-cython-sources
3297 (lambda* (#:key inputs outputs #:allow-other-keys)
3298 ;; Delete these C files to force fresh generation from pyx sources.
3299 (delete-file "grit/sparsify_support_fns.c")
3300 (delete-file "grit/call_peaks_support_fns.c")
3301 (substitute* "setup.py"
3302 (("Cython.Setup") "Cython.Build"))
3305 `(("python-scipy" ,python2-scipy)
3306 ("python-numpy" ,python2-numpy)
3307 ("python-pysam" ,python2-pysam)
3308 ("python-networkx" ,python2-networkx)))
3310 `(("python-cython" ,python2-cython)))
3311 (home-page "http://grit-bio.org")
3312 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3314 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3315 full length transcript models. When none of these data sources are available,
3316 GRIT can be run by providing a candidate set of TES or TSS sites. In
3317 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3318 also be run in quantification mode, where it uses a provided GTF file and just
3319 estimates transcript expression.")
3320 (license license:gpl3+)))
3322 (define-public hisat
3329 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3330 version "-beta-source.zip"))
3333 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3334 (build-system gnu-build-system)
3336 `(#:tests? #f ;no check target
3337 #:make-flags '("allall"
3338 ;; Disable unsupported `popcnt' instructions on
3339 ;; architectures other than x86_64
3340 ,@(if (string-prefix? "x86_64"
3341 (or (%current-target-system)
3344 '("POPCNT_CAPABILITY=0")))
3346 (modify-phases %standard-phases
3347 (add-after 'unpack 'patch-sources
3349 ;; XXX Cannot use snippet because zip files are not supported
3350 (substitute* "Makefile"
3351 (("^CC = .*$") "CC = gcc")
3352 (("^CPP = .*$") "CPP = g++")
3353 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3354 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3355 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3356 (substitute* '("hisat-build" "hisat-inspect")
3357 (("/usr/bin/env") (which "env")))
3360 (lambda* (#:key outputs #:allow-other-keys)
3361 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3362 (for-each (lambda (file)
3363 (install-file file bin))
3366 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3368 (delete 'configure))))
3370 `(("unzip" ,unzip)))
3375 ;; Non-portable SSE instructions are used so building fails on platforms
3376 ;; other than x86_64.
3377 (supported-systems '("x86_64-linux"))
3378 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3379 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3381 "HISAT is a fast and sensitive spliced alignment program for mapping
3382 RNA-seq reads. In addition to one global FM index that represents a whole
3383 genome, HISAT uses a large set of small FM indexes that collectively cover the
3384 whole genome. These small indexes (called local indexes) combined with
3385 several alignment strategies enable effective alignment of RNA-seq reads, in
3386 particular, reads spanning multiple exons.")
3387 (license license:gpl3+)))
3389 (define-public hisat2
3396 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3397 "/downloads/hisat2-" version "-source.zip"))
3400 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3401 (build-system gnu-build-system)
3403 `(#:tests? #f ; no check target
3404 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3405 #:modules ((guix build gnu-build-system)
3409 (modify-phases %standard-phases
3410 (add-after 'unpack 'make-deterministic
3412 (substitute* "Makefile"
3417 (lambda* (#:key outputs #:allow-other-keys)
3418 (let* ((out (assoc-ref outputs "out"))
3419 (bin (string-append out "/bin/"))
3420 (doc (string-append out "/share/doc/hisat2/")))
3422 (cut install-file <> bin)
3424 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3426 (install-file "doc/manual.inc.html" doc))
3429 `(("unzip" ,unzip) ; needed for archive from ftp
3431 ("pandoc" ,ghc-pandoc))) ; for documentation
3432 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3433 (synopsis "Graph-based alignment of genomic sequencing reads")
3434 (description "HISAT2 is a fast and sensitive alignment program for mapping
3435 next-generation sequencing reads (both DNA and RNA) to a population of human
3436 genomes (as well as to a single reference genome). In addition to using one
3437 global @dfn{graph FM} (GFM) index that represents a population of human
3438 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3439 the whole genome. These small indexes, combined with several alignment
3440 strategies, enable rapid and accurate alignment of sequencing reads. This new
3441 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3442 ;; HISAT2 contains files from Bowtie2, which is released under
3443 ;; GPLv2 or later. The HISAT2 source files are released under
3445 (license license:gpl3+)))
3447 (define-public hmmer
3455 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3458 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3459 (build-system gnu-build-system)
3460 (native-inputs `(("perl" ,perl)))
3461 (home-page "http://hmmer.org/")
3462 (synopsis "Biosequence analysis using profile hidden Markov models")
3464 "HMMER is used for searching sequence databases for homologs of protein
3465 sequences, and for making protein sequence alignments. It implements methods
3466 using probabilistic models called profile hidden Markov models (profile
3468 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3470 (supported-systems '("x86_64-linux" "i686-linux"))
3471 (license license:bsd-3)))
3473 (define-public htseq
3479 (uri (pypi-uri "HTSeq" version))
3482 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3483 (build-system python-build-system)
3485 `(("python-cython" ,python-cython)))
3486 ;; Numpy needs to be propagated when htseq is used as a Python library.
3488 `(("python-numpy" ,python-numpy)))
3490 `(("python-pysam" ,python-pysam)
3491 ("python-matplotlib" ,python-matplotlib)))
3492 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3493 (synopsis "Analysing high-throughput sequencing data with Python")
3495 "HTSeq is a Python package that provides infrastructure to process data
3496 from high-throughput sequencing assays.")
3497 (license license:gpl3+)))
3499 (define-public python2-htseq
3500 (package-with-python2 htseq))
3502 (define-public java-htsjdk
3504 (name "java-htsjdk")
3505 (version "2.3.0") ; last version without build dependency on gradle
3509 (url "https://github.com/samtools/htsjdk.git")
3511 (file-name (git-file-name name version))
3514 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3515 (modules '((guix build utils)))
3517 ;; Delete pre-built binaries
3519 (delete-file-recursively "lib")
3522 (build-system ant-build-system)
3524 `(#:tests? #f ; test require Internet access
3527 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3528 "/share/java/htsjdk/"))
3529 #:build-target "all"
3531 (modify-phases %standard-phases
3532 ;; The build phase also installs the jars
3533 (delete 'install))))
3535 `(("java-ngs" ,java-ngs)
3536 ("java-snappy-1" ,java-snappy-1)
3537 ("java-commons-compress" ,java-commons-compress)
3538 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3539 ("java-commons-jexl-2" ,java-commons-jexl-2)
3540 ("java-xz" ,java-xz)))
3542 `(("java-testng" ,java-testng)))
3543 (home-page "http://samtools.github.io/htsjdk/")
3544 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3546 "HTSJDK is an implementation of a unified Java library for accessing
3547 common file formats, such as SAM and VCF, used for high-throughput
3548 sequencing (HTS) data. There are also an number of useful utilities for
3549 manipulating HTS data.")
3550 (license license:expat)))
3552 (define-public java-htsjdk-latest
3554 (name "java-htsjdk")
3559 (url "https://github.com/samtools/htsjdk.git")
3561 (file-name (string-append name "-" version "-checkout"))
3564 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3565 (build-system ant-build-system)
3567 `(#:tests? #f ; test require Scala
3569 #:jar-name "htsjdk.jar"
3571 (modify-phases %standard-phases
3572 (add-after 'unpack 'remove-useless-build.xml
3573 (lambda _ (delete-file "build.xml") #t))
3574 ;; The tests require the scalatest package.
3575 (add-after 'unpack 'remove-tests
3576 (lambda _ (delete-file-recursively "src/test") #t)))))
3578 `(("java-ngs" ,java-ngs)
3579 ("java-snappy-1" ,java-snappy-1)
3580 ("java-commons-compress" ,java-commons-compress)
3581 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3582 ("java-commons-jexl-2" ,java-commons-jexl-2)
3583 ("java-xz" ,java-xz)))
3585 `(("java-junit" ,java-junit)))
3586 (home-page "http://samtools.github.io/htsjdk/")
3587 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3589 "HTSJDK is an implementation of a unified Java library for accessing
3590 common file formats, such as SAM and VCF, used for high-throughput
3591 sequencing (HTS) data. There are also an number of useful utilities for
3592 manipulating HTS data.")
3593 (license license:expat)))
3595 ;; This is needed for picard 2.10.3
3596 (define-public java-htsjdk-2.10.1
3597 (package (inherit java-htsjdk-latest)
3598 (name "java-htsjdk")
3603 (url "https://github.com/samtools/htsjdk.git")
3605 (file-name (string-append name "-" version "-checkout"))
3608 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3609 (build-system ant-build-system)
3611 `(#:tests? #f ; tests require Scala
3613 #:jar-name "htsjdk.jar"
3615 (modify-phases %standard-phases
3616 (add-after 'unpack 'remove-useless-build.xml
3617 (lambda _ (delete-file "build.xml") #t))
3618 ;; The tests require the scalatest package.
3619 (add-after 'unpack 'remove-tests
3620 (lambda _ (delete-file-recursively "src/test") #t)))))))
3622 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3623 ;; recent version of java-htsjdk, which depends on gradle.
3624 (define-public java-picard
3626 (name "java-picard")
3631 (url "https://github.com/broadinstitute/picard.git")
3633 (file-name (string-append "java-picard-" version "-checkout"))
3636 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3637 (modules '((guix build utils)))
3640 ;; Delete pre-built binaries.
3641 (delete-file-recursively "lib")
3643 (substitute* "build.xml"
3644 ;; Remove build-time dependency on git.
3645 (("failifexecutionfails=\"true\"")
3646 "failifexecutionfails=\"false\"")
3648 (("depends=\"compile-htsjdk, ")
3650 (("depends=\"compile-htsjdk-tests, ")
3652 ;; Build picard-lib.jar before building picard.jar
3653 (("name=\"picard-jar\" depends=\"" line)
3654 (string-append line "picard-lib-jar, ")))
3656 (build-system ant-build-system)
3658 `(#:build-target "picard-jar"
3659 #:test-target "test"
3660 ;; Tests require jacoco:coverage.
3663 (list (string-append "-Dhtsjdk_lib_dir="
3664 (assoc-ref %build-inputs "java-htsjdk")
3665 "/share/java/htsjdk/")
3666 "-Dhtsjdk-classes=dist/tmp"
3667 (string-append "-Dhtsjdk-version="
3668 ,(package-version java-htsjdk)))
3671 (modify-phases %standard-phases
3672 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3673 (delete 'generate-jar-indices)
3674 (add-after 'unpack 'use-our-htsjdk
3675 (lambda* (#:key inputs #:allow-other-keys)
3676 (substitute* "build.xml"
3677 (("\\$\\{htsjdk\\}/lib")
3678 (string-append (assoc-ref inputs "java-htsjdk")
3679 "/share/java/htsjdk/")))
3681 (add-after 'unpack 'make-test-target-independent
3682 (lambda* (#:key inputs #:allow-other-keys)
3683 (substitute* "build.xml"
3684 (("name=\"test\" depends=\"compile, ")
3685 "name=\"test\" depends=\""))
3687 (replace 'install (install-jars "dist")))))
3689 `(("java-htsjdk" ,java-htsjdk)
3690 ("java-guava" ,java-guava)))
3692 `(("java-testng" ,java-testng)))
3693 (home-page "http://broadinstitute.github.io/picard/")
3694 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3695 (description "Picard is a set of Java command line tools for manipulating
3696 high-throughput sequencing (HTS) data and formats. Picard is implemented
3697 using the HTSJDK Java library to support accessing file formats that are
3698 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3700 (license license:expat)))
3702 ;; This is needed for dropseq-tools
3703 (define-public java-picard-2.10.3
3705 (name "java-picard")
3710 (url "https://github.com/broadinstitute/picard.git")
3712 (file-name (string-append "java-picard-" version "-checkout"))
3715 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3716 (build-system ant-build-system)
3718 `(#:jar-name "picard.jar"
3719 ;; Tests require jacoco:coverage.
3722 #:main-class "picard.cmdline.PicardCommandLine"
3723 #:modules ((guix build ant-build-system)
3725 (guix build java-utils)
3730 (modify-phases %standard-phases
3731 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3732 (delete 'generate-jar-indices)
3733 (add-after 'unpack 'remove-useless-build.xml
3734 (lambda _ (delete-file "build.xml") #t))
3735 ;; This is necessary to ensure that htsjdk is found when using
3736 ;; picard.jar as an executable.
3737 (add-before 'build 'edit-classpath-in-manifest
3738 (lambda* (#:key inputs #:allow-other-keys)
3739 (chmod "build.xml" #o664)
3740 (call-with-output-file "build.xml.new"
3744 (with-input-from-file "build.xml"
3745 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3746 `((target . ,(lambda (tag . kids)
3747 (let ((name ((sxpath '(name *text*))
3749 ;; FIXME: We're breaking the line
3750 ;; early with a dummy path to
3751 ;; ensure that the store reference
3752 ;; isn't broken apart and can still
3753 ;; be found by the reference
3758 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3759 ;; maximum line length is 70
3760 (string-tabulate (const #\b) 57)
3761 (assoc-ref inputs "java-htsjdk"))))
3762 (if (member "manifest" name)
3765 (@ (file "${manifest.file}")
3766 (match "\\r\\n\\r\\n")
3767 (replace "${line.separator}")))
3770 (file "${manifest.file}")
3773 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3774 (*text* . ,(lambda (_ txt) txt))))
3776 (rename-file "build.xml.new" "build.xml")
3779 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3781 `(("java-testng" ,java-testng)
3782 ("java-guava" ,java-guava)))
3783 (home-page "http://broadinstitute.github.io/picard/")
3784 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3785 (description "Picard is a set of Java command line tools for manipulating
3786 high-throughput sequencing (HTS) data and formats. Picard is implemented
3787 using the HTSJDK Java library to support accessing file formats that are
3788 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3790 (license license:expat)))
3792 ;; This is the last version of Picard to provide net.sf.samtools
3793 (define-public java-picard-1.113
3794 (package (inherit java-picard)
3795 (name "java-picard")
3800 (url "https://github.com/broadinstitute/picard.git")
3802 (file-name (string-append "java-picard-" version "-checkout"))
3805 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3806 (modules '((guix build utils)))
3809 ;; Delete pre-built binaries.
3810 (delete-file-recursively "lib")
3813 (build-system ant-build-system)
3815 `(#:build-target "picard-jar"
3816 #:test-target "test"
3817 ;; FIXME: the class path at test time is wrong.
3818 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3819 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3822 ;; This is only used for tests.
3824 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3826 (modify-phases %standard-phases
3827 ;; FIXME: This phase fails.
3828 (delete 'generate-jar-indices)
3829 ;; Do not use bundled ant bzip2.
3830 (add-after 'unpack 'use-ant-bzip
3831 (lambda* (#:key inputs #:allow-other-keys)
3832 (substitute* "build.xml"
3833 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3834 (string-append (assoc-ref inputs "ant")
3837 (add-after 'unpack 'make-test-target-independent
3838 (lambda* (#:key inputs #:allow-other-keys)
3839 (substitute* "build.xml"
3840 (("name=\"test\" depends=\"compile, ")
3841 "name=\"test\" depends=\"compile-tests, ")
3842 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3843 "name=\"compile\" depends=\"compile-src\""))
3845 (add-after 'unpack 'fix-deflater-path
3846 (lambda* (#:key outputs #:allow-other-keys)
3847 (substitute* "src/java/net/sf/samtools/Defaults.java"
3848 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3849 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3850 (assoc-ref outputs "out")
3851 "/lib/jni/libIntelDeflater.so"
3854 ;; Build the deflater library, because we've previously deleted the
3855 ;; pre-built one. This can only be built with access to the JDK
3857 (add-after 'build 'build-jni
3858 (lambda* (#:key inputs #:allow-other-keys)
3861 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3862 "-xf" (assoc-ref inputs "jdk-src"))
3863 (invoke "javah" "-jni"
3864 "-classpath" "classes"
3866 "net.sf.samtools.util.zip.IntelDeflater")
3867 (with-directory-excursion "src/c/inteldeflater"
3868 (invoke "gcc" "-I../../../lib" "-I."
3869 (string-append "-I" (assoc-ref inputs "jdk")
3871 "-I../../../jdk-src/src/share/native/common/"
3872 "-I../../../jdk-src/src/solaris/native/common/"
3873 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3874 (invoke "gcc" "-shared"
3875 "-o" "../../../lib/jni/libIntelDeflater.so"
3876 "IntelDeflater.o" "-lz" "-lstdc++"))
3878 ;; We can only build everything else after building the JNI library.
3879 (add-after 'build-jni 'build-rest
3880 (lambda* (#:key make-flags #:allow-other-keys)
3881 (apply invoke `("ant" "all" ,@make-flags))
3883 (add-before 'build 'set-JAVA6_HOME
3885 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3887 (replace 'install (install-jars "dist"))
3888 (add-after 'install 'install-jni-lib
3889 (lambda* (#:key outputs #:allow-other-keys)
3890 (let ((jni (string-append (assoc-ref outputs "out")
3893 (install-file "lib/jni/libIntelDeflater.so" jni)
3896 `(("java-snappy-1" ,java-snappy-1)
3897 ("java-commons-jexl-2" ,java-commons-jexl-2)
3898 ("java-cofoja" ,java-cofoja)
3899 ("ant" ,ant) ; for bzip2 support at runtime
3902 `(("ant-apache-bcel" ,ant-apache-bcel)
3903 ("ant-junit" ,ant-junit)
3904 ("java-testng" ,java-testng)
3905 ("java-commons-bcel" ,java-commons-bcel)
3906 ("java-jcommander" ,java-jcommander)
3907 ("jdk" ,icedtea-8 "jdk")
3908 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3910 (define-public fastqc
3917 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3918 "projects/fastqc/fastqc_v"
3919 version "_source.zip"))
3922 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3923 (build-system ant-build-system)
3925 `(#:tests? #f ; there are no tests
3926 #:build-target "build"
3928 (modify-phases %standard-phases
3929 (add-after 'unpack 'fix-dependencies
3930 (lambda* (#:key inputs #:allow-other-keys)
3931 (substitute* "build.xml"
3933 (string-append (assoc-ref inputs "java-jbzip2")
3934 "/share/java/jbzip2.jar"))
3936 (string-append (assoc-ref inputs "java-picard-1.113")
3937 "/share/java/sam-1.112.jar"))
3939 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3940 "/share/java/sis-jhdf5.jar")))
3942 ;; There is no installation target
3944 (lambda* (#:key inputs outputs #:allow-other-keys)
3945 (let* ((out (assoc-ref outputs "out"))
3946 (bin (string-append out "/bin"))
3947 (share (string-append out "/share/fastqc/"))
3948 (exe (string-append share "/fastqc")))
3949 (for-each mkdir-p (list bin share))
3950 (copy-recursively "bin" share)
3952 (("my \\$java_bin = 'java';")
3953 (string-append "my $java_bin = '"
3954 (assoc-ref inputs "java")
3957 (symlink exe (string-append bin "/fastqc"))
3961 ("perl" ,perl) ; needed for the wrapper script
3962 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3963 ("java-picard-1.113" ,java-picard-1.113)
3964 ("java-jbzip2" ,java-jbzip2)))
3966 `(("unzip" ,unzip)))
3967 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3968 (synopsis "Quality control tool for high throughput sequence data")
3970 "FastQC aims to provide a simple way to do some quality control
3971 checks on raw sequence data coming from high throughput sequencing
3972 pipelines. It provides a modular set of analyses which you can use to
3973 give a quick impression of whether your data has any problems of which
3974 you should be aware before doing any further analysis.
3976 The main functions of FastQC are:
3979 @item Import of data from BAM, SAM or FastQ files (any variant);
3980 @item Providing a quick overview to tell you in which areas there may
3982 @item Summary graphs and tables to quickly assess your data;
3983 @item Export of results to an HTML based permanent report;
3984 @item Offline operation to allow automated generation of reports
3985 without running the interactive application.
3987 (license license:gpl3+)))
3989 (define-public fastp
3997 (url "https://github.com/OpenGene/fastp.git")
3998 (commit (string-append "v" version))))
3999 (file-name (git-file-name name version))
4002 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4003 (build-system gnu-build-system)
4005 `(#:tests? #f ; there are none
4007 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4009 (modify-phases %standard-phases
4011 (add-before 'install 'create-target-dir
4012 (lambda* (#:key outputs #:allow-other-keys)
4013 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4017 (home-page "https://github.com/OpenGene/fastp/")
4018 (synopsis "All-in-one FastQ preprocessor")
4020 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4021 FastQ files. This tool has multi-threading support to afford high
4023 (license license:expat)))
4025 (define-public htslib
4032 "https://github.com/samtools/htslib/releases/download/"
4033 version "/htslib-" version ".tar.bz2"))
4036 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4037 (build-system gnu-build-system)
4040 ("openssl" ,openssl)))
4041 ;; This is referred to in the pkg-config file as a required library.
4046 (home-page "http://www.htslib.org")
4047 (synopsis "C library for reading/writing high-throughput sequencing data")
4049 "HTSlib is a C library for reading/writing high-throughput sequencing
4050 data. It also provides the @command{bgzip}, @command{htsfile}, and
4051 @command{tabix} utilities.")
4052 ;; Files under cram/ are released under the modified BSD license;
4053 ;; the rest is released under the Expat license
4054 (license (list license:expat license:bsd-3))))
4056 ;; This package should be removed once no packages rely upon it.
4064 "https://github.com/samtools/htslib/releases/download/"
4065 version "/htslib-" version ".tar.bz2"))
4068 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4077 (url "https://github.com/nboley/idr.git")
4079 (file-name (git-file-name name version))
4082 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4083 ;; Delete generated C code.
4085 '(begin (delete-file "idr/inv_cdf.c") #t))))
4086 (build-system python-build-system)
4087 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4088 ;; are no longer part of this package. It also asserts False, which
4089 ;; causes the tests to always fail.
4090 (arguments `(#:tests? #f))
4092 `(("python-scipy" ,python-scipy)
4093 ("python-sympy" ,python-sympy)
4094 ("python-numpy" ,python-numpy)
4095 ("python-matplotlib" ,python-matplotlib)))
4097 `(("python-cython" ,python-cython)))
4098 (home-page "https://github.com/nboley/idr")
4099 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4101 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4102 to measure the reproducibility of findings identified from replicate
4103 experiments and provide highly stable thresholds based on reproducibility.")
4104 (license license:gpl2+)))
4106 (define-public jellyfish
4112 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4113 "releases/download/v" version
4114 "/jellyfish-" version ".tar.gz"))
4117 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4118 (build-system gnu-build-system)
4119 (outputs '("out" ;for library
4120 "ruby" ;for Ruby bindings
4121 "python")) ;for Python bindings
4124 (list (string-append "--enable-ruby-binding="
4125 (assoc-ref %outputs "ruby"))
4126 (string-append "--enable-python-binding="
4127 (assoc-ref %outputs "python")))
4129 (modify-phases %standard-phases
4130 (add-before 'check 'set-SHELL-variable
4132 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4134 (setenv "SHELL" (which "bash"))
4140 ("python" ,python-2)
4141 ("pkg-config" ,pkg-config)))
4143 `(("htslib" ,htslib)))
4144 (synopsis "Tool for fast counting of k-mers in DNA")
4146 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4147 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4148 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4149 is a command-line program that reads FASTA and multi-FASTA files containing
4150 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4151 translated into a human-readable text format using the @code{jellyfish dump}
4152 command, or queried for specific k-mers with @code{jellyfish query}.")
4153 (home-page "http://www.genome.umd.edu/jellyfish.html")
4154 ;; JELLYFISH seems to be 64-bit only.
4155 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4156 ;; The combined work is published under the GPLv3 or later. Individual
4157 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4158 (license (list license:gpl3+ license:expat))))
4160 (define-public khmer
4168 (url "https://github.com/dib-lab/khmer.git")
4169 (commit (string-append "v" version))))
4170 (file-name (git-file-name name version))
4173 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4174 (modules '((guix build utils)))
4177 ;; Delete bundled libraries. We do not replace the bundled seqan
4178 ;; as it is a modified subset of the old version 1.4.1.
4180 ;; We do not replace the bundled MurmurHash as the canonical
4181 ;; repository for this code 'SMHasher' is unsuitable for providing
4183 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4184 (delete-file-recursively "third-party/zlib")
4185 (delete-file-recursively "third-party/bzip2")
4186 (delete-file-recursively "third-party/seqan")
4187 (substitute* "setup.cfg"
4188 (("# libraries = z,bz2")
4189 "libraries = z,bz2")
4190 (("include:third-party/zlib:third-party/bzip2")
4193 (build-system python-build-system)
4196 (modify-phases %standard-phases
4197 (add-after 'unpack 'set-cc
4198 (lambda _ (setenv "CC" "gcc") #t))
4200 (add-before 'reset-gzip-timestamps 'make-files-writable
4201 (lambda* (#:key outputs #:allow-other-keys)
4202 ;; Make sure .gz files are writable so that the
4203 ;; 'reset-gzip-timestamps' phase can do its work.
4204 (let ((out (assoc-ref outputs "out")))
4205 (for-each make-file-writable
4206 (find-files out "\\.gz$"))
4209 `(("python-cython" ,python-cython)
4210 ("python-pytest" ,python-pytest)
4211 ("python-pytest-runner" ,python-pytest-runner)))
4216 ("python-screed" ,python-screed)
4217 ("python-bz2file" ,python-bz2file)))
4218 (home-page "https://khmer.readthedocs.org/")
4219 (synopsis "K-mer counting, filtering and graph traversal library")
4220 (description "The khmer software is a set of command-line tools for
4221 working with DNA shotgun sequencing data from genomes, transcriptomes,
4222 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4223 sometimes better. Khmer can also identify and fix problems with shotgun
4225 ;; When building on i686, armhf and mips64el, we get the following error:
4226 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4227 (supported-systems '("x86_64-linux" "aarch64-linux"))
4228 (license license:bsd-3)))
4230 (define-public kaiju
4237 (url "https://github.com/bioinformatics-centre/kaiju")
4238 (commit (string-append "v" version))))
4239 (file-name (git-file-name name version))
4242 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4243 (build-system gnu-build-system)
4245 `(#:tests? #f ; There are no tests.
4247 (modify-phases %standard-phases
4249 (add-before 'build 'move-to-src-dir
4250 (lambda _ (chdir "src") #t))
4252 (lambda* (#:key inputs outputs #:allow-other-keys)
4253 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4256 (copy-recursively "bin" bin))
4261 (home-page "http://kaiju.binf.ku.dk/")
4262 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4263 (description "Kaiju is a program for sensitive taxonomic classification
4264 of high-throughput sequencing reads from metagenomic whole genome sequencing
4266 (license license:gpl3+)))
4271 (version "2.1.1.20160309")
4274 (uri (pypi-uri "MACS2" version))
4277 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
4278 (build-system python-build-system)
4280 `(#:python ,python-2 ; only compatible with Python 2.7
4281 #:tests? #f)) ; no test target
4283 `(("python-numpy" ,python2-numpy)))
4284 (home-page "https://github.com/taoliu/MACS/")
4285 (synopsis "Model based analysis for ChIP-Seq data")
4287 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4288 identifying transcript factor binding sites named Model-based Analysis of
4289 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4290 the significance of enriched ChIP regions and it improves the spatial
4291 resolution of binding sites through combining the information of both
4292 sequencing tag position and orientation.")
4293 (license license:bsd-3)))
4295 (define-public mafft
4302 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4303 "-without-extensions-src.tgz"))
4304 (file-name (string-append name "-" version ".tgz"))
4307 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4308 (build-system gnu-build-system)
4310 `(#:tests? #f ; no automated tests, though there are tests in the read me
4311 #:make-flags (let ((out (assoc-ref %outputs "out")))
4312 (list (string-append "PREFIX=" out)
4313 (string-append "BINDIR="
4314 (string-append out "/bin"))))
4316 (modify-phases %standard-phases
4317 (add-after 'unpack 'enter-dir
4318 (lambda _ (chdir "core") #t))
4319 (add-after 'enter-dir 'patch-makefile
4321 ;; on advice from the MAFFT authors, there is no need to
4322 ;; distribute mafft-profile, mafft-distance, or
4323 ;; mafft-homologs.rb as they are too "specialised".
4324 (substitute* "Makefile"
4325 ;; remove mafft-homologs.rb from SCRIPTS
4326 (("^SCRIPTS = mafft mafft-homologs.rb")
4328 ;; remove mafft-homologs from MANPAGES
4329 (("^MANPAGES = mafft.1 mafft-homologs.1")
4330 "MANPAGES = mafft.1")
4331 ;; remove mafft-distance from PROGS
4332 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4333 "PROGS = dvtditr dndfast7 dndblast sextet5")
4334 ;; remove mafft-profile from PROGS
4335 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4336 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4337 (("^rm -f mafft-profile mafft-profile.exe") "#")
4338 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4339 ;; do not install MAN pages in libexec folder
4340 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4341 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4343 (add-after 'enter-dir 'patch-paths
4344 (lambda* (#:key inputs #:allow-other-keys)
4345 (substitute* '("pairash.c"
4347 (("perl") (which "perl"))
4348 (("([\"`| ])awk" _ prefix)
4349 (string-append prefix (which "awk")))
4350 (("grep") (which "grep")))
4353 (add-after 'install 'wrap-programs
4354 (lambda* (#:key outputs #:allow-other-keys)
4355 (let* ((out (assoc-ref outputs "out"))
4356 (bin (string-append out "/bin"))
4357 (path (string-append
4358 (assoc-ref %build-inputs "coreutils") "/bin:")))
4359 (for-each (lambda (file)
4361 `("PATH" ":" prefix (,path))))
4369 ("coreutils" ,coreutils)))
4370 (home-page "http://mafft.cbrc.jp/alignment/software/")
4371 (synopsis "Multiple sequence alignment program")
4373 "MAFFT offers a range of multiple alignment methods for nucleotide and
4374 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4375 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4377 (license (license:non-copyleft
4378 "http://mafft.cbrc.jp/alignment/software/license.txt"
4379 "BSD-3 with different formatting"))))
4388 (url "https://github.com/marbl/mash.git")
4389 (commit (string-append "v" version))))
4390 (file-name (git-file-name name version))
4393 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4394 (modules '((guix build utils)))
4397 ;; Delete bundled kseq.
4398 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4399 (delete-file "src/mash/kseq.h")
4401 (build-system gnu-build-system)
4403 `(#:tests? #f ; No tests.
4406 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4407 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4408 #:make-flags (list "CC=gcc")
4410 (modify-phases %standard-phases
4411 (add-after 'unpack 'fix-includes
4413 (substitute* '("src/mash/Sketch.cpp"
4414 "src/mash/CommandFind.cpp"
4415 "src/mash/CommandScreen.cpp")
4416 (("^#include \"kseq\\.h\"")
4417 "#include \"htslib/kseq.h\""))
4419 (add-after 'fix-includes 'use-c++14
4421 ;; capnproto 0.7 requires c++14 to build
4422 (substitute* "configure.ac"
4423 (("c\\+\\+11") "c++14"))
4424 (substitute* "Makefile.in"
4425 (("c\\+\\+11") "c++14"))
4428 `(("autoconf" ,autoconf)
4429 ;; Capnproto and htslib are statically embedded in the final
4430 ;; application. Therefore we also list their licenses, below.
4431 ("capnproto" ,capnproto)
4432 ("htslib" ,htslib)))
4436 (supported-systems '("x86_64-linux"))
4437 (home-page "https://mash.readthedocs.io")
4438 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4439 (description "Mash is a fast sequence distance estimator that uses the
4440 MinHash algorithm and is designed to work with genomes and metagenomes in the
4441 form of assemblies or reads.")
4442 (license (list license:bsd-3 ; Mash
4443 license:expat ; HTSlib and capnproto
4444 license:public-domain ; MurmurHash 3
4445 license:cpl1.0)))) ; Open Bloom Filter
4447 (define-public metabat
4455 (url "https://bitbucket.org/berkeleylab/metabat.git")
4456 (commit (string-append "v" version))))
4457 (file-name (git-file-name name version))
4460 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4461 (patches (search-patches "metabat-fix-compilation.patch"))))
4462 (build-system scons-build-system)
4464 `(#:scons ,scons-python2
4466 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4467 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4468 #:tests? #f ;; Tests are run during the build phase.
4470 (modify-phases %standard-phases
4471 (add-after 'unpack 'fix-includes
4473 (substitute* "src/BamUtils.h"
4474 (("^#include \"bam/bam\\.h\"")
4475 "#include \"samtools/bam.h\"")
4476 (("^#include \"bam/sam\\.h\"")
4477 "#include \"samtools/sam.h\""))
4478 (substitute* "src/KseqReader.h"
4479 (("^#include \"bam/kseq\\.h\"")
4480 "#include \"htslib/kseq.h\""))
4482 (add-after 'unpack 'fix-scons
4483 (lambda* (#:key inputs #:allow-other-keys)
4484 (substitute* "SConstruct"
4485 (("^htslib_dir += 'samtools'")
4486 (string-append "htslib_dir = '"
4487 (assoc-ref inputs "htslib")
4489 (("^samtools_dir = 'samtools'")
4490 (string-append "samtools_dir = '"
4491 (assoc-ref inputs "samtools")
4493 (("^findStaticOrShared\\('bam', hts_lib")
4494 (string-append "findStaticOrShared('bam', '"
4495 (assoc-ref inputs "samtools")
4497 ;; Do not distribute README.
4498 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4503 ("samtools" ,samtools)
4506 (home-page "https://bitbucket.org/berkeleylab/metabat")
4508 "Reconstruction of single genomes from complex microbial communities")
4510 "Grouping large genomic fragments assembled from shotgun metagenomic
4511 sequences to deconvolute complex microbial communities, or metagenome binning,
4512 enables the study of individual organisms and their interactions. MetaBAT is
4513 an automated metagenome binning software, which integrates empirical
4514 probabilistic distances of genome abundance and tetranucleotide frequency.")
4515 ;; The source code contains inline assembly.
4516 (supported-systems '("x86_64-linux" "i686-linux"))
4517 (license (license:non-copyleft "file://license.txt"
4518 "See license.txt in the distribution."))))
4520 (define-public minced
4527 (url "https://github.com/ctSkennerton/minced.git")
4529 (file-name (git-file-name name version))
4532 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4533 (build-system gnu-build-system)
4535 `(#:test-target "test"
4537 (modify-phases %standard-phases
4539 (add-before 'check 'fix-test
4541 ;; Fix test for latest version.
4542 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4543 (("minced:0.1.6") "minced:0.2.0"))
4545 (replace 'install ; No install target.
4546 (lambda* (#:key inputs outputs #:allow-other-keys)
4547 (let* ((out (assoc-ref outputs "out"))
4548 (bin (string-append out "/bin"))
4549 (wrapper (string-append bin "/minced")))
4550 ;; Minced comes with a wrapper script that tries to figure out where
4551 ;; it is located before running the JAR. Since these paths are known
4552 ;; to us, we build our own wrapper to avoid coreutils dependency.
4553 (install-file "minced.jar" bin)
4554 (with-output-to-file wrapper
4558 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4559 (assoc-ref inputs "jre") "/bin/java -jar "
4560 bin "/minced.jar \"$@\"\n"))))
4561 (chmod wrapper #o555))
4564 `(("jdk" ,icedtea "jdk")))
4567 ("jre" ,icedtea "out")))
4568 (home-page "https://github.com/ctSkennerton/minced")
4569 (synopsis "Mining CRISPRs in Environmental Datasets")
4571 "MinCED is a program to find Clustered Regularly Interspaced Short
4572 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4573 unassembled metagenomic reads, but is mainly designed for full genomes and
4574 assembled metagenomic sequence.")
4575 (license license:gpl3+)))
4583 (uri (pypi-uri "misopy" version))
4586 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4587 (modules '((guix build utils)))
4589 (substitute* "setup.py"
4590 ;; Use setuptools, or else the executables are not
4592 (("distutils.core") "setuptools")
4593 ;; use "gcc" instead of "cc" for compilation
4595 "cc.set_executables(
4599 linker_so='gcc -shared'); defines"))
4601 (build-system python-build-system)
4603 `(#:python ,python-2 ; only Python 2 is supported
4604 #:tests? #f)) ; no "test" target
4606 `(("samtools" ,samtools)
4607 ("python-numpy" ,python2-numpy)
4608 ("python-pysam" ,python2-pysam)
4609 ("python-scipy" ,python2-scipy)
4610 ("python-matplotlib" ,python2-matplotlib)))
4612 `(("python-mock" ,python2-mock) ;for tests
4613 ("python-pytz" ,python2-pytz))) ;for tests
4614 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4615 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4617 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4618 the expression level of alternatively spliced genes from RNA-Seq data, and
4619 identifies differentially regulated isoforms or exons across samples. By
4620 modeling the generative process by which reads are produced from isoforms in
4621 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4622 that a read originated from a particular isoform.")
4623 (license license:gpl2)))
4625 (define-public muscle
4628 (version "3.8.1551")
4630 (method url-fetch/tarbomb)
4632 "http://www.drive5.com/muscle/muscle_src_"
4636 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4637 (build-system gnu-build-system)
4639 `(#:make-flags (list "LDLIBS = -lm")
4641 (modify-phases %standard-phases
4644 ;; There are no tests, so just test if it runs.
4645 (lambda _ (invoke "./muscle" "-version") #t))
4647 (lambda* (#:key outputs #:allow-other-keys)
4648 (let* ((out (assoc-ref outputs "out"))
4649 (bin (string-append out "/bin")))
4650 (install-file "muscle" bin)
4652 (home-page "http://www.drive5.com/muscle")
4653 (synopsis "Multiple sequence alignment program")
4655 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4656 program for nucleotide and protein sequences.")
4657 ;; License information found in 'muscle -h' and usage.cpp.
4658 (license license:public-domain)))
4660 (define-public newick-utils
4661 ;; There are no recent releases so we package from git.
4662 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4664 (name "newick-utils")
4665 (version (string-append "1.6-1." (string-take commit 8)))
4669 (url "https://github.com/tjunier/newick_utils.git")
4671 (file-name (string-append name "-" version "-checkout"))
4674 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4675 (build-system gnu-build-system)
4677 ;; XXX: TODO: Enable Lua and Guile bindings.
4678 ;; https://github.com/tjunier/newick_utils/issues/13
4679 `(("libxml2" ,libxml2)
4683 `(("autoconf" ,autoconf)
4684 ("automake" ,automake)
4685 ("libtool" ,libtool)))
4686 (synopsis "Programs for working with newick format phylogenetic trees")
4688 "Newick-utils is a suite of utilities for processing phylogenetic trees
4689 in Newick format. Functions include re-rooting, extracting subtrees,
4690 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4691 (home-page "https://github.com/tjunier/newick_utils")
4692 (license license:bsd-3))))
4701 "https://github.com/wwood/OrfM/releases/download/v"
4702 version "/orfm-" version ".tar.gz"))
4705 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4706 (build-system gnu-build-system)
4707 (inputs `(("zlib" ,zlib)))
4709 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4710 ("ruby-rspec" ,ruby-rspec)
4712 (synopsis "Simple and not slow open reading frame (ORF) caller")
4714 "An ORF caller finds stretches of DNA that, when translated, are not
4715 interrupted by stop codons. OrfM finds and prints these ORFs.")
4716 (home-page "https://github.com/wwood/OrfM")
4717 (license license:lgpl3+)))
4719 (define-public python2-pbcore
4721 (name "python2-pbcore")
4725 (uri (pypi-uri "pbcore" version))
4728 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4729 (build-system python-build-system)
4730 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4732 `(("python-cython" ,python2-cython)
4733 ("python-numpy" ,python2-numpy)
4734 ("python-pysam" ,python2-pysam)
4735 ("python-h5py" ,python2-h5py)))
4737 `(("python-nose" ,python2-nose)
4738 ("python-sphinx" ,python2-sphinx)
4739 ("python-pyxb" ,python2-pyxb)))
4740 (home-page "http://pacificbiosciences.github.io/pbcore/")
4741 (synopsis "Library for reading and writing PacBio data files")
4743 "The pbcore package provides Python APIs for interacting with PacBio data
4744 files and writing bioinformatics applications.")
4745 (license license:bsd-3)))
4747 (define-public python2-warpedlmm
4749 (name "python2-warpedlmm")
4754 (uri (pypi-uri "WarpedLMM" version ".zip"))
4757 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4758 (build-system python-build-system)
4760 `(#:python ,python-2)) ; requires Python 2.7
4762 `(("python-scipy" ,python2-scipy)
4763 ("python-numpy" ,python2-numpy)
4764 ("python-matplotlib" ,python2-matplotlib)
4765 ("python-fastlmm" ,python2-fastlmm)
4766 ("python-pandas" ,python2-pandas)
4767 ("python-pysnptools" ,python2-pysnptools)))
4769 `(("python-mock" ,python2-mock)
4770 ("python-nose" ,python2-nose)
4772 (home-page "https://github.com/PMBio/warpedLMM")
4773 (synopsis "Implementation of warped linear mixed models")
4775 "WarpedLMM is a Python implementation of the warped linear mixed model,
4776 which automatically learns an optimal warping function (or transformation) for
4777 the phenotype as it models the data.")
4778 (license license:asl2.0)))
4780 (define-public pbtranscript-tofu
4781 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4783 (name "pbtranscript-tofu")
4784 (version (string-append "2.2.3." (string-take commit 7)))
4788 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4790 (file-name (string-append name "-" version "-checkout"))
4793 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4794 (modules '((guix build utils)))
4797 ;; remove bundled Cython sources
4798 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4800 (build-system python-build-system)
4802 `(#:python ,python-2
4803 ;; FIXME: Tests fail with "No such file or directory:
4804 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4807 (modify-phases %standard-phases
4808 (add-after 'unpack 'enter-directory
4810 (chdir "pbtranscript-tofu/pbtranscript/")
4812 ;; With setuptools version 18.0 and later this setup.py hack causes
4813 ;; a build error, so we disable it.
4814 (add-after 'enter-directory 'patch-setuppy
4816 (substitute* "setup.py"
4817 (("if 'setuptools.extension' in sys.modules:")
4821 `(("python-numpy" ,python2-numpy)
4822 ("python-bx-python" ,python2-bx-python)
4823 ("python-networkx" ,python2-networkx)
4824 ("python-scipy" ,python2-scipy)
4825 ("python-pbcore" ,python2-pbcore)
4826 ("python-h5py" ,python2-h5py)))
4828 `(("python-cython" ,python2-cython)
4829 ("python-nose" ,python2-nose)))
4830 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4831 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4833 "pbtranscript-tofu contains scripts to analyze transcriptome data
4834 generated using the PacBio Iso-Seq protocol.")
4835 (license license:bsd-3))))
4837 (define-public prank
4844 "http://wasabiapp.org/download/prank/prank.source."
4848 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
4849 (build-system gnu-build-system)
4852 (modify-phases %standard-phases
4853 (add-after 'unpack 'enter-src-dir
4857 (add-after 'unpack 'remove-m64-flag
4858 ;; Prank will build with the correct 'bit-ness' without this flag
4859 ;; and this allows building on 32-bit machines.
4860 (lambda _ (substitute* "src/Makefile"
4865 (lambda* (#:key outputs #:allow-other-keys)
4866 (let* ((out (assoc-ref outputs "out"))
4867 (bin (string-append out "/bin"))
4868 (man (string-append out "/share/man/man1"))
4869 (path (string-append
4870 (assoc-ref %build-inputs "mafft") "/bin:"
4871 (assoc-ref %build-inputs "exonerate") "/bin:"
4872 (assoc-ref %build-inputs "bppsuite") "/bin")))
4873 (install-file "prank" bin)
4874 (wrap-program (string-append bin "/prank")
4875 `("PATH" ":" prefix (,path)))
4876 (install-file "prank.1" man))
4880 ("exonerate" ,exonerate)
4881 ("bppsuite" ,bppsuite)))
4882 (home-page "http://wasabiapp.org/software/prank/")
4883 (synopsis "Probabilistic multiple sequence alignment program")
4885 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4886 codon and amino-acid sequences. It is based on a novel algorithm that treats
4887 insertions correctly and avoids over-estimation of the number of deletion
4888 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4889 in phylogenetics and correctly takes into account the evolutionary distances
4890 between sequences. Lastly, PRANK allows for defining a potential structure
4891 for sequences to be aligned and then, simultaneously with the alignment,
4892 predicts the locations of structural units in the sequences.")
4893 (license license:gpl2+)))
4895 (define-public proteinortho
4897 (name "proteinortho")
4904 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4905 version "_src.tar.gz"))
4908 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4909 (build-system gnu-build-system)
4911 `(#:test-target "test"
4913 (modify-phases %standard-phases
4915 ;; There is no configure script, so we modify the Makefile directly.
4916 (lambda* (#:key outputs #:allow-other-keys)
4917 (substitute* "Makefile"
4920 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4922 (add-before 'install 'make-install-directory
4923 ;; The install directory is not created during 'make install'.
4924 (lambda* (#:key outputs #:allow-other-keys)
4925 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4927 (add-after 'install 'wrap-programs
4928 (lambda* (#:key inputs outputs #:allow-other-keys)
4929 (let* ((path (getenv "PATH"))
4930 (out (assoc-ref outputs "out"))
4931 (binary (string-append out "/bin/proteinortho5.pl")))
4932 (wrap-program binary `("PATH" ":" prefix (,path))))
4936 ("python" ,python-2)
4937 ("blast+" ,blast+)))
4938 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4939 (synopsis "Detect orthologous genes across species")
4941 "Proteinortho is a tool to detect orthologous genes across different
4942 species. For doing so, it compares similarities of given gene sequences and
4943 clusters them to find significant groups. The algorithm was designed to handle
4944 large-scale data and can be applied to hundreds of species at once.")
4945 (license license:gpl2+)))
4947 (define-public pyicoteo
4955 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4956 (commit (string-append "v" version))))
4957 (file-name (git-file-name name version))
4960 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4961 (build-system python-build-system)
4963 `(#:python ,python-2 ; does not work with Python 3
4964 #:tests? #f)) ; there are no tests
4966 `(("python2-matplotlib" ,python2-matplotlib)))
4967 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4968 (synopsis "Analyze high-throughput genetic sequencing data")
4970 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4971 sequencing data. It works with genomic coordinates. There are currently six
4972 different command-line tools:
4975 @item pyicoregion: for generating exploratory regions automatically;
4976 @item pyicoenrich: for differential enrichment between two conditions;
4977 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4978 @item pyicos: for genomic coordinates manipulation;
4979 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4980 @item pyicount: to count how many reads from N experiment files overlap in a
4982 @item pyicotrocol: to combine operations from pyicoteo.
4984 (license license:gpl3+)))
4986 (define-public prodigal
4993 (url "https://github.com/hyattpd/Prodigal.git")
4994 (commit (string-append "v" version))))
4995 (file-name (git-file-name name version))
4998 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4999 (build-system gnu-build-system)
5001 `(#:tests? #f ;no check target
5002 #:make-flags (list (string-append "INSTALLDIR="
5003 (assoc-ref %outputs "out")
5006 (modify-phases %standard-phases
5007 (delete 'configure))))
5008 (home-page "http://prodigal.ornl.gov")
5009 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5011 "Prodigal runs smoothly on finished genomes, draft genomes, and
5012 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5013 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5014 partial genes, and identifies translation initiation sites.")
5015 (license license:gpl3+)))
5017 (define-public roary
5025 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5029 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5030 (build-system perl-build-system)
5033 (modify-phases %standard-phases
5038 ;; The tests are not run by default, so we run each test file
5040 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5042 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5043 (getenv "PERL5LIB")))
5044 (for-each (lambda (file)
5045 (display file)(display "\n")
5046 (invoke "perl" file))
5047 (find-files "t" ".*\\.t$"))
5050 ;; There is no 'install' target in the Makefile.
5051 (lambda* (#:key outputs #:allow-other-keys)
5052 (let* ((out (assoc-ref outputs "out"))
5053 (bin (string-append out "/bin"))
5054 (perl (string-append out "/lib/perl5/site_perl"))
5055 (roary-plots "contrib/roary_plots"))
5058 (copy-recursively "bin" bin)
5059 (copy-recursively "lib" perl)
5061 (add-after 'install 'wrap-programs
5062 (lambda* (#:key inputs outputs #:allow-other-keys)
5063 (let* ((out (assoc-ref outputs "out"))
5064 (perl5lib (getenv "PERL5LIB"))
5065 (path (getenv "PATH")))
5066 (for-each (lambda (prog)
5067 (let ((binary (string-append out "/" prog)))
5068 (wrap-program binary
5069 `("PERL5LIB" ":" prefix
5070 (,(string-append perl5lib ":" out
5071 "/lib/perl5/site_perl"))))
5072 (wrap-program binary
5074 (,(string-append path ":" out "/bin"))))))
5075 (find-files "bin" ".*[^R]$"))
5077 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5078 (r-site-lib (getenv "R_LIBS_SITE"))
5080 (string-append (assoc-ref inputs "coreutils") "/bin")))
5082 `("R_LIBS_SITE" ":" prefix
5083 (,(string-append r-site-lib ":" out "/site-library/"))))
5086 (,(string-append coreutils-path ":" out "/bin"))))))
5089 `(("perl-env-path" ,perl-env-path)
5090 ("perl-test-files" ,perl-test-files)
5091 ("perl-test-most" ,perl-test-most)
5092 ("perl-test-output" ,perl-test-output)))
5094 `(("perl-array-utils" ,perl-array-utils)
5095 ("bioperl" ,bioperl-minimal)
5096 ("perl-digest-md5-file" ,perl-digest-md5-file)
5097 ("perl-exception-class" ,perl-exception-class)
5098 ("perl-file-find-rule" ,perl-file-find-rule)
5099 ("perl-file-grep" ,perl-file-grep)
5100 ("perl-file-slurper" ,perl-file-slurper)
5101 ("perl-file-which" ,perl-file-which)
5102 ("perl-graph" ,perl-graph)
5103 ("perl-graph-readwrite" ,perl-graph-readwrite)
5104 ("perl-log-log4perl" ,perl-log-log4perl)
5105 ("perl-moose" ,perl-moose)
5106 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5107 ("perl-text-csv" ,perl-text-csv)
5108 ("bedtools" ,bedtools)
5112 ("parallel" ,parallel)
5115 ("fasttree" ,fasttree)
5119 ("r-minimal" ,r-minimal)
5120 ("r-ggplot2" ,r-ggplot2)
5121 ("coreutils" ,coreutils)))
5122 (home-page "http://sanger-pathogens.github.io/Roary")
5123 (synopsis "High speed stand-alone pan genome pipeline")
5125 "Roary is a high speed stand alone pan genome pipeline, which takes
5126 annotated assemblies in GFF3 format (produced by the Prokka program) and
5127 calculates the pan genome. Using a standard desktop PC, it can analyse
5128 datasets with thousands of samples, without compromising the quality of the
5129 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5130 single processor. Roary is not intended for metagenomics or for comparing
5131 extremely diverse sets of genomes.")
5132 (license license:gpl3)))
5134 (define-public raxml
5142 (url "https://github.com/stamatak/standard-RAxML.git")
5143 (commit (string-append "v" version))))
5144 (file-name (git-file-name name version))
5147 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5148 (build-system gnu-build-system)
5150 `(#:tests? #f ; There are no tests.
5151 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5152 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5154 (modify-phases %standard-phases
5157 (lambda* (#:key outputs #:allow-other-keys)
5158 (let* ((out (assoc-ref outputs "out"))
5159 (bin (string-append out "/bin"))
5160 (executable "raxmlHPC-HYBRID"))
5161 (install-file executable bin)
5162 (symlink (string-append bin "/" executable) "raxml"))
5165 `(("openmpi" ,openmpi)))
5166 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
5167 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5169 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5171 ;; The source includes x86 specific code
5172 (supported-systems '("x86_64-linux" "i686-linux"))
5173 (license license:gpl2+)))
5183 (url "https://github.com/deweylab/RSEM.git")
5184 (commit (string-append "v" version))))
5186 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5187 (file-name (git-file-name name version))
5188 (modules '((guix build utils)))
5191 ;; remove bundled copy of boost and samtools
5192 (delete-file-recursively "boost")
5193 (delete-file-recursively "samtools-1.3")
5195 (build-system gnu-build-system)
5197 `(#:tests? #f ;no "check" target
5199 (list (string-append "BOOST="
5200 (assoc-ref %build-inputs "boost")
5202 (string-append "SAMHEADERS="
5203 (assoc-ref %build-inputs "htslib")
5204 "/include/htslib/sam.h")
5205 (string-append "SAMLIBS="
5206 (assoc-ref %build-inputs "htslib")
5209 (modify-phases %standard-phases
5210 ;; No "configure" script.
5211 ;; Do not build bundled samtools library.
5214 (substitute* "Makefile"
5215 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5216 (("^\\$\\(SAMLIBS\\).*") ""))
5219 (lambda* (#:key outputs #:allow-other-keys)
5220 (let* ((out (string-append (assoc-ref outputs "out")))
5221 (bin (string-append out "/bin/"))
5222 (perl (string-append out "/lib/perl5/site_perl")))
5225 (for-each (lambda (file)
5226 (install-file file bin))
5227 (find-files "." "rsem-.*"))
5228 (install-file "rsem_perl_utils.pm" perl))
5230 (add-after 'install 'wrap-program
5231 (lambda* (#:key outputs #:allow-other-keys)
5232 (let ((out (assoc-ref outputs "out")))
5233 (for-each (lambda (prog)
5234 (wrap-program (string-append out "/bin/" prog)
5235 `("PERL5LIB" ":" prefix
5236 (,(string-append out "/lib/perl5/site_perl")))))
5237 '("rsem-calculate-expression"
5239 "rsem-generate-data-matrix"
5240 "rsem-generate-ngvector"
5241 "rsem-plot-transcript-wiggles"
5242 "rsem-prepare-reference"
5244 "rsem-run-prsem-testing-procedure")))
5248 ("r-minimal" ,r-minimal)
5250 ("htslib" ,htslib-1.3)
5252 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5253 (synopsis "Estimate gene expression levels from RNA-Seq data")
5255 "RSEM is a software package for estimating gene and isoform expression
5256 levels from RNA-Seq data. The RSEM package provides a user-friendly
5257 interface, supports threads for parallel computation of the EM algorithm,
5258 single-end and paired-end read data, quality scores, variable-length reads and
5259 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5260 interval estimates for expression levels. For visualization, it can generate
5261 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5262 (license license:gpl3+)))
5264 (define-public rseqc
5272 (string-append "mirror://sourceforge/rseqc/"
5273 "RSeQC-" version ".tar.gz"))
5275 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5276 (modules '((guix build utils)))
5279 ;; remove bundled copy of pysam
5280 (delete-file-recursively "lib/pysam")
5281 (substitute* "setup.py"
5282 ;; remove dependency on outdated "distribute" module
5283 (("^from distribute_setup import use_setuptools") "")
5284 (("^use_setuptools\\(\\)") "")
5285 ;; do not use bundled copy of pysam
5286 (("^have_pysam = False") "have_pysam = True"))
5288 (build-system python-build-system)
5289 (arguments `(#:python ,python-2))
5291 `(("python-cython" ,python2-cython)
5292 ("python-pysam" ,python2-pysam)
5293 ("python-numpy" ,python2-numpy)
5296 `(("python-nose" ,python2-nose)))
5297 (home-page "http://rseqc.sourceforge.net/")
5298 (synopsis "RNA-seq quality control package")
5300 "RSeQC provides a number of modules that can comprehensively evaluate
5301 high throughput sequence data, especially RNA-seq data. Some basic modules
5302 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5303 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5304 distribution, coverage uniformity, strand specificity, etc.")
5305 (license license:gpl3+)))
5308 ;; There are no release tarballs. According to the installation
5309 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5310 ;; stable release is identified by this changeset ID.
5311 (let ((changeset "2329130")
5315 (version (string-append "0-" revision "." changeset))
5319 (url "https://bitbucket.org/libsleipnir/sleipnir")
5320 (changeset changeset)))
5321 (file-name (string-append name "-" version "-checkout"))
5324 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5325 (build-system gnu-build-system)
5327 `(#:modules ((srfi srfi-1)
5328 (guix build gnu-build-system)
5331 (let ((dirs '("SeekMiner"
5337 (modify-phases %standard-phases
5340 (substitute* "gen_tools_am"
5341 (("/usr/bin/env.*") (which "perl")))
5342 (invoke "bash" "gen_auto")
5344 (add-after 'build 'build-additional-tools
5345 (lambda* (#:key make-flags #:allow-other-keys)
5346 (for-each (lambda (dir)
5347 (with-directory-excursion (string-append "tools/" dir)
5348 (apply invoke "make" make-flags)))
5351 (add-after 'install 'install-additional-tools
5352 (lambda* (#:key make-flags #:allow-other-keys)
5353 (for-each (lambda (dir)
5354 (with-directory-excursion (string-append "tools/" dir)
5355 (apply invoke `("make" ,@make-flags "install"))))
5362 ("readline" ,readline)
5363 ("gengetopt" ,gengetopt)
5364 ("log4cpp" ,log4cpp)))
5366 `(("autoconf" ,autoconf)
5367 ("automake" ,automake)
5369 (home-page "http://seek.princeton.edu")
5370 (synopsis "Gene co-expression search engine")
5372 "SEEK is a computational gene co-expression search engine. SEEK provides
5373 biologists with a way to navigate the massive human expression compendium that
5374 now contains thousands of expression datasets. SEEK returns a robust ranking
5375 of co-expressed genes in the biological area of interest defined by the user's
5376 query genes. It also prioritizes thousands of expression datasets according
5377 to the user's query of interest.")
5378 (license license:cc-by3.0))))
5380 (define-public samtools
5388 (string-append "mirror://sourceforge/samtools/samtools/"
5389 version "/samtools-" version ".tar.bz2"))
5392 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5393 (modules '((guix build utils)))
5395 ;; Delete bundled htslib.
5396 (delete-file-recursively "htslib-1.9")
5398 (build-system gnu-build-system)
5400 `(#:modules ((ice-9 ftw)
5402 (guix build gnu-build-system)
5404 #:configure-flags (list "--with-ncurses")
5406 (modify-phases %standard-phases
5407 (add-after 'unpack 'patch-tests
5409 (substitute* "test/test.pl"
5410 ;; The test script calls out to /bin/bash
5411 (("/bin/bash") (which "bash")))
5413 (add-after 'install 'install-library
5414 (lambda* (#:key outputs #:allow-other-keys)
5415 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5416 (install-file "libbam.a" lib)
5418 (add-after 'install 'install-headers
5419 (lambda* (#:key outputs #:allow-other-keys)
5420 (let ((include (string-append (assoc-ref outputs "out")
5421 "/include/samtools/")))
5422 (for-each (lambda (file)
5423 (install-file file include))
5424 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5426 (native-inputs `(("pkg-config" ,pkg-config)))
5428 `(("htslib" ,htslib)
5429 ("ncurses" ,ncurses)
5433 (home-page "http://samtools.sourceforge.net")
5434 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5436 "Samtools implements various utilities for post-processing nucleotide
5437 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5438 variant calling (in conjunction with bcftools), and a simple alignment
5440 (license license:expat)))
5442 (define-public samtools-0.1
5443 ;; This is the most recent version of the 0.1 line of samtools. The input
5444 ;; and output formats differ greatly from that used and produced by samtools
5445 ;; 1.x and is still used in many bioinformatics pipelines.
5446 (package (inherit samtools)
5452 (string-append "mirror://sourceforge/samtools/samtools/"
5453 version "/samtools-" version ".tar.bz2"))
5455 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5457 `(#:tests? #f ;no "check" target
5459 (list "LIBCURSES=-lncurses")
5460 ,@(substitute-keyword-arguments (package-arguments samtools)
5462 `(modify-phases ,phases
5464 (lambda* (#:key outputs #:allow-other-keys)
5465 (let ((bin (string-append
5466 (assoc-ref outputs "out") "/bin")))
5468 (install-file "samtools" bin)
5470 (delete 'patch-tests)
5471 (delete 'configure))))))))
5473 (define-public mosaik
5474 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5479 ;; There are no release tarballs nor tags.
5482 (url "https://github.com/wanpinglee/MOSAIK.git")
5484 (file-name (string-append name "-" version))
5487 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5488 (build-system gnu-build-system)
5490 `(#:tests? #f ; no tests
5491 #:make-flags (list "CC=gcc")
5493 (modify-phases %standard-phases
5495 (lambda _ (chdir "src") #t))
5497 (lambda* (#:key outputs #:allow-other-keys)
5498 (let ((bin (string-append (assoc-ref outputs "out")
5501 (copy-recursively "../bin" bin)
5505 ("zlib:static" ,zlib "static")
5507 (supported-systems '("x86_64-linux"))
5508 (home-page "https://github.com/wanpinglee/MOSAIK")
5509 (synopsis "Map nucleotide sequence reads to reference genomes")
5511 "MOSAIK is a program for mapping second and third-generation sequencing
5512 reads to a reference genome. MOSAIK can align reads generated by all the
5513 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5514 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5515 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5516 ;; code released into the public domain:
5517 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5518 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5519 (license (list license:gpl2+ license:public-domain)))))
5521 (define-public ngs-sdk
5528 (url "https://github.com/ncbi/ngs.git")
5530 (file-name (git-file-name name version))
5533 "0d5k5kabgl15as37kj9x65xc92j4gcqms86hvihw3yb6wag0r0q3"))))
5534 (build-system gnu-build-system)
5536 `(#:parallel-build? #f ; not supported
5537 #:tests? #f ; no "check" target
5539 (modify-phases %standard-phases
5541 (lambda* (#:key outputs #:allow-other-keys)
5542 (let ((out (assoc-ref outputs "out")))
5543 ;; Allow 'konfigure.perl' to find 'package.prl'.
5545 (string-append ".:" (getenv "PERL5LIB")))
5547 ;; The 'configure' script doesn't recognize things like
5548 ;; '--enable-fast-install'.
5549 (invoke "./configure"
5550 (string-append "--build-prefix=" (getcwd) "/build")
5551 (string-append "--prefix=" out))
5553 (add-after 'unpack 'enter-dir
5554 (lambda _ (chdir "ngs-sdk") #t)))))
5555 (native-inputs `(("perl" ,perl)))
5556 ;; According to the test
5557 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5558 ;; in ngs-sdk/setup/konfigure.perl
5559 (supported-systems '("i686-linux" "x86_64-linux"))
5560 (home-page "https://github.com/ncbi/ngs")
5561 (synopsis "API for accessing Next Generation Sequencing data")
5563 "NGS is a domain-specific API for accessing reads, alignments and pileups
5564 produced from Next Generation Sequencing. The API itself is independent from
5565 any particular back-end implementation, and supports use of multiple back-ends
5567 (license license:public-domain)))
5569 (define-public java-ngs
5570 (package (inherit ngs-sdk)
5573 `(,@(substitute-keyword-arguments
5574 `(#:modules ((guix build gnu-build-system)
5578 ,@(package-arguments ngs-sdk))
5580 `(modify-phases ,phases
5581 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5583 `(("jdk" ,icedtea "jdk")
5584 ("ngs-sdk" ,ngs-sdk)))
5585 (synopsis "Java bindings for NGS SDK")))
5587 (define-public ncbi-vdb
5594 (url "https://github.com/ncbi/ncbi-vdb.git")
5596 (file-name (git-file-name name version))
5599 "0knkj1sq34hlivgv5qd6jlczqrs3ldmfgn6vbbw7p4mqxvb9mirk"))))
5600 (build-system gnu-build-system)
5602 `(#:parallel-build? #f ; not supported
5603 #:tests? #f ; no "check" target
5604 #:make-flags '("HAVE_HDF5=1")
5606 (modify-phases %standard-phases
5607 (add-after 'unpack 'make-files-writable
5608 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5609 (add-before 'configure 'set-perl-search-path
5611 ;; Work around "dotless @INC" build failure.
5613 (string-append (getcwd) "/setup:"
5614 (getenv "PERL5LIB")))
5616 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5617 (add-after 'unpack 'patch-krypto-flags
5619 (substitute* "libs/krypto/Makefile"
5620 (("-Wa,-march=generic64\\+aes") "")
5621 (("-Wa,-march=generic64\\+sse4") ""))
5624 (lambda* (#:key inputs outputs #:allow-other-keys)
5625 (let ((out (assoc-ref outputs "out")))
5626 ;; Override include path for libmagic
5627 (substitute* "setup/package.prl"
5628 (("name => 'magic', Include => '/usr/include'")
5629 (string-append "name=> 'magic', Include => '"
5630 (assoc-ref inputs "libmagic")
5633 ;; Install kdf5 library (needed by sra-tools)
5634 (substitute* "build/Makefile.install"
5635 (("LIBRARIES_TO_INSTALL =")
5636 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5638 (substitute* "build/Makefile.env"
5639 (("CFLAGS =" prefix)
5640 (string-append prefix "-msse2 ")))
5642 ;; Override search path for ngs-java
5643 (substitute* "setup/package.prl"
5644 (("/usr/local/ngs/ngs-java")
5645 (assoc-ref inputs "java-ngs")))
5647 ;; The 'configure' script doesn't recognize things like
5648 ;; '--enable-fast-install'.
5649 (invoke "./configure"
5650 (string-append "--build-prefix=" (getcwd) "/build")
5651 (string-append "--prefix=" (assoc-ref outputs "out"))
5652 (string-append "--debug")
5653 (string-append "--with-xml2-prefix="
5654 (assoc-ref inputs "libxml2"))
5655 (string-append "--with-ngs-sdk-prefix="
5656 (assoc-ref inputs "ngs-sdk"))
5657 (string-append "--with-hdf5-prefix="
5658 (assoc-ref inputs "hdf5")))
5660 (add-after 'install 'install-interfaces
5661 (lambda* (#:key outputs #:allow-other-keys)
5662 ;; Install interface libraries. On i686 the interface libraries
5663 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5664 ;; architecture name ("i386") instead of the target system prefix
5666 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5667 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5668 ,(system->linux-architecture
5669 (or (%current-target-system)
5672 (string-append (assoc-ref outputs "out")
5674 ;; Install interface headers
5675 (copy-recursively "interfaces"
5676 (string-append (assoc-ref outputs "out")
5679 ;; These files are needed by sra-tools.
5680 (add-after 'install 'install-configuration-files
5681 (lambda* (#:key outputs #:allow-other-keys)
5682 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5684 (install-file "libs/kfg/default.kfg" target)
5685 (install-file "libs/kfg/certs.kfg" target))
5688 `(("libxml2" ,libxml2)
5689 ("ngs-sdk" ,ngs-sdk)
5690 ("java-ngs" ,java-ngs)
5693 (native-inputs `(("perl" ,perl)))
5694 ;; NCBI-VDB requires SSE capability.
5695 (supported-systems '("i686-linux" "x86_64-linux"))
5696 (home-page "https://github.com/ncbi/ncbi-vdb")
5697 (synopsis "Database engine for genetic information")
5699 "The NCBI-VDB library implements a highly compressed columnar data
5700 warehousing engine that is most often used to store genetic information.
5701 Databases are stored in a portable image within the file system, and can be
5702 accessed/downloaded on demand across HTTP.")
5703 (license license:public-domain)))
5705 (define-public plink
5713 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5714 version "-src.zip"))
5716 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5717 (patches (search-patches "plink-1.07-unclobber-i.patch"
5718 "plink-endian-detection.patch"))))
5719 (build-system gnu-build-system)
5721 '(#:tests? #f ;no "check" target
5722 #:make-flags (list (string-append "LIB_LAPACK="
5723 (assoc-ref %build-inputs "lapack")
5724 "/lib/liblapack.so")
5727 ;; disable phoning home
5730 (modify-phases %standard-phases
5731 ;; no "configure" script
5734 (lambda* (#:key outputs #:allow-other-keys)
5735 (let ((bin (string-append (assoc-ref outputs "out")
5737 (install-file "plink" bin)
5741 ("lapack" ,lapack)))
5743 `(("unzip" ,unzip)))
5744 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5745 (synopsis "Whole genome association analysis toolset")
5747 "PLINK is a whole genome association analysis toolset, designed to
5748 perform a range of basic, large-scale analyses in a computationally efficient
5749 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5750 so there is no support for steps prior to this (e.g. study design and
5751 planning, generating genotype or CNV calls from raw data). Through
5752 integration with gPLINK and Haploview, there is some support for the
5753 subsequent visualization, annotation and storage of results.")
5754 ;; Code is released under GPLv2, except for fisher.h, which is under
5756 (license (list license:gpl2 license:lgpl2.1+))))
5758 (define-public plink-ng
5759 (package (inherit plink)
5766 (url "https://github.com/chrchang/plink-ng.git")
5767 (commit (string-append "v" version))))
5768 (file-name (git-file-name name version))
5770 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5771 (build-system gnu-build-system)
5773 '(#:tests? #f ;no "check" target
5774 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5775 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5777 "-f" "Makefile.std")
5779 (modify-phases %standard-phases
5780 (add-after 'unpack 'chdir
5781 (lambda _ (chdir "1.9") #t))
5782 (delete 'configure) ; no "configure" script
5784 (lambda* (#:key outputs #:allow-other-keys)
5785 (let ((bin (string-append (assoc-ref outputs "out")
5787 (install-file "plink" bin)
5792 ("openblas" ,openblas)))
5793 (home-page "https://www.cog-genomics.org/plink/")
5794 (license license:gpl3+)))
5796 (define-public smithlab-cpp
5797 (let ((revision "1")
5798 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5800 (name "smithlab-cpp")
5801 (version (string-append "0." revision "." (string-take commit 7)))
5805 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5807 (file-name (string-append name "-" version "-checkout"))
5810 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5811 (build-system gnu-build-system)
5813 `(#:modules ((guix build gnu-build-system)
5816 #:tests? #f ;no "check" target
5818 (modify-phases %standard-phases
5819 (add-after 'unpack 'use-samtools-headers
5821 (substitute* '("SAM.cpp"
5823 (("sam.h") "samtools/sam.h"))
5826 (lambda* (#:key outputs #:allow-other-keys)
5827 (let* ((out (assoc-ref outputs "out"))
5828 (lib (string-append out "/lib"))
5829 (include (string-append out "/include/smithlab-cpp")))
5832 (for-each (cut install-file <> lib)
5833 (find-files "." "\\.o$"))
5834 (for-each (cut install-file <> include)
5835 (find-files "." "\\.hpp$")))
5837 (delete 'configure))))
5839 `(("samtools" ,samtools-0.1)
5841 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5842 (synopsis "C++ helper library for functions used in Smith lab projects")
5844 "Smithlab CPP is a C++ library that includes functions used in many of
5845 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5846 structures, classes for genomic regions, mapped sequencing reads, etc.")
5847 (license license:gpl3+))))
5849 (define-public preseq
5855 (uri (string-append "https://github.com/smithlabcode/preseq/"
5856 "releases/download/v" version
5857 "/preseq_v" version ".tar.bz2"))
5859 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5860 (modules '((guix build utils)))
5862 ;; Remove bundled samtools.
5863 (delete-file-recursively "samtools")
5865 (build-system gnu-build-system)
5867 `(#:tests? #f ;no "check" target
5869 (modify-phases %standard-phases
5870 (delete 'configure))
5872 (list (string-append "PREFIX="
5873 (assoc-ref %outputs "out"))
5874 (string-append "LIBBAM="
5875 (assoc-ref %build-inputs "samtools")
5877 (string-append "SMITHLAB_CPP="
5878 (assoc-ref %build-inputs "smithlab-cpp")
5881 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5884 ("samtools" ,samtools-0.1)
5885 ("smithlab-cpp" ,smithlab-cpp)
5887 (home-page "http://smithlabresearch.org/software/preseq/")
5888 (synopsis "Program for analyzing library complexity")
5890 "The preseq package is aimed at predicting and estimating the complexity
5891 of a genomic sequencing library, equivalent to predicting and estimating the
5892 number of redundant reads from a given sequencing depth and how many will be
5893 expected from additional sequencing using an initial sequencing experiment.
5894 The estimates can then be used to examine the utility of further sequencing,
5895 optimize the sequencing depth, or to screen multiple libraries to avoid low
5896 complexity samples.")
5897 (license license:gpl3+)))
5899 (define-public python-screed
5901 (name "python-screed")
5906 (uri (pypi-uri "screed" version))
5909 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5910 (build-system python-build-system)
5913 (modify-phases %standard-phases
5914 ;; Tests must be run after installation, as the "screed" command does
5915 ;; not exist right after building.
5917 (add-after 'install 'check
5918 (lambda* (#:key inputs outputs #:allow-other-keys)
5919 (let ((out (assoc-ref outputs "out")))
5920 (setenv "PYTHONPATH"
5921 (string-append out "/lib/python"
5922 (string-take (string-take-right
5923 (assoc-ref inputs "python")
5926 (getenv "PYTHONPATH")))
5927 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5928 (invoke "python" "setup.py" "test")
5931 `(("python-pytest" ,python-pytest)
5932 ("python-pytest-cov" ,python-pytest-cov)
5933 ("python-pytest-runner" ,python-pytest-runner)))
5935 `(("python-bz2file" ,python-bz2file)))
5936 (home-page "https://github.com/dib-lab/screed/")
5937 (synopsis "Short read sequence database utilities")
5938 (description "Screed parses FASTA and FASTQ files and generates databases.
5939 Values such as sequence name, sequence description, sequence quality and the
5940 sequence itself can be retrieved from these databases.")
5941 (license license:bsd-3)))
5943 (define-public python2-screed
5944 (package-with-python2 python-screed))
5946 (define-public sra-tools
5954 (url "https://github.com/ncbi/sra-tools.git")
5956 (file-name (git-file-name name version))
5959 "0vqzap68v81k0zif2mnqfy8pnw2nrhsg87p6mgq8qk3nk2jv2rgy"))))
5960 (build-system gnu-build-system)
5962 `(#:parallel-build? #f ; not supported
5963 #:tests? #f ; no "check" target
5965 (list (string-append "DEFAULT_CRT="
5966 (assoc-ref %build-inputs "ncbi-vdb")
5968 (string-append "DEFAULT_KFG="
5969 (assoc-ref %build-inputs "ncbi-vdb")
5971 (string-append "VDB_LIBDIR="
5972 (assoc-ref %build-inputs "ncbi-vdb")
5973 ,(if (string-prefix? "x86_64"
5974 (or (%current-target-system)
5979 (modify-phases %standard-phases
5980 (add-before 'configure 'set-perl-search-path
5982 ;; Work around "dotless @INC" build failure.
5984 (string-append (getcwd) "/setup:"
5985 (getenv "PERL5LIB")))
5988 (lambda* (#:key inputs outputs #:allow-other-keys)
5989 ;; The build system expects a directory containing the sources and
5990 ;; raw build output of ncbi-vdb, including files that are not
5991 ;; installed. Since we are building against an installed version of
5992 ;; ncbi-vdb, the following modifications are needed.
5993 (substitute* "setup/konfigure.perl"
5994 ;; Make the configure script look for the "ilib" directory of
5995 ;; "ncbi-vdb" without first checking for the existence of a
5996 ;; matching library in its "lib" directory.
5997 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5998 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5999 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6000 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6001 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6004 (substitute* "tools/copycat/Makefile"
6005 (("smagic-static") "lmagic"))
6007 ;; The 'configure' script doesn't recognize things like
6008 ;; '--enable-fast-install'.
6009 (invoke "./configure"
6010 (string-append "--build-prefix=" (getcwd) "/build")
6011 (string-append "--prefix=" (assoc-ref outputs "out"))
6012 (string-append "--debug")
6013 (string-append "--with-fuse-prefix="
6014 (assoc-ref inputs "fuse"))
6015 (string-append "--with-magic-prefix="
6016 (assoc-ref inputs "libmagic"))
6017 ;; TODO: building with libxml2 fails with linker errors
6018 ;; (string-append "--with-xml2-prefix="
6019 ;; (assoc-ref inputs "libxml2"))
6020 (string-append "--with-ncbi-vdb-sources="
6021 (assoc-ref inputs "ncbi-vdb"))
6022 (string-append "--with-ncbi-vdb-build="
6023 (assoc-ref inputs "ncbi-vdb"))
6024 (string-append "--with-ngs-sdk-prefix="
6025 (assoc-ref inputs "ngs-sdk"))
6026 (string-append "--with-hdf5-prefix="
6027 (assoc-ref inputs "hdf5")))
6029 (native-inputs `(("perl" ,perl)))
6031 `(("ngs-sdk" ,ngs-sdk)
6032 ("ncbi-vdb" ,ncbi-vdb)
6037 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6038 (synopsis "Tools and libraries for reading and writing sequencing data")
6040 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6041 reading of sequencing files from the Sequence Read Archive (SRA) database and
6042 writing files into the .sra format.")
6043 (license license:public-domain)))
6045 (define-public seqan
6051 (uri (string-append "https://github.com/seqan/seqan/releases/"
6052 "download/seqan-v" version
6053 "/seqan-library-" version ".tar.xz"))
6056 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6057 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6058 ;; makes sense to split the outputs.
6059 (outputs '("out" "doc"))
6060 (build-system trivial-build-system)
6062 `(#:modules ((guix build utils))
6065 (use-modules (guix build utils))
6066 (let ((tar (assoc-ref %build-inputs "tar"))
6067 (xz (assoc-ref %build-inputs "xz"))
6068 (out (assoc-ref %outputs "out"))
6069 (doc (assoc-ref %outputs "doc")))
6070 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6071 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6072 (chdir (string-append "seqan-library-" ,version))
6073 (copy-recursively "include" (string-append out "/include"))
6074 (copy-recursively "share" (string-append doc "/share"))
6077 `(("source" ,source)
6080 (home-page "http://www.seqan.de")
6081 (synopsis "Library for nucleotide sequence analysis")
6083 "SeqAn is a C++ library of efficient algorithms and data structures for
6084 the analysis of sequences with the focus on biological data. It contains
6085 algorithms and data structures for string representation and their
6086 manipulation, online and indexed string search, efficient I/O of
6087 bioinformatics file formats, sequence alignment, and more.")
6088 (license license:bsd-3)))
6090 (define-public seqan-1
6091 (package (inherit seqan)
6096 (uri (string-append "http://packages.seqan.de/seqan-library/"
6097 "seqan-library-" version ".tar.bz2"))
6100 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6101 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6102 ;; makes sense to split the outputs.
6103 (outputs '("out" "doc"))
6104 (build-system trivial-build-system)
6106 `(#:modules ((guix build utils))
6109 (use-modules (guix build utils))
6110 (let ((tar (assoc-ref %build-inputs "tar"))
6111 (bzip (assoc-ref %build-inputs "bzip2"))
6112 (out (assoc-ref %outputs "out"))
6113 (doc (assoc-ref %outputs "doc")))
6114 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6115 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6116 (chdir (string-append "seqan-library-" ,version))
6117 (copy-recursively "include" (string-append out "/include"))
6118 (copy-recursively "share" (string-append doc "/share"))
6121 `(("source" ,source)
6123 ("bzip2" ,bzip2)))))
6125 (define-public seqmagick
6132 (uri (pypi-uri "seqmagick" version))
6135 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6136 (build-system python-build-system)
6138 `(("python-biopython" ,python-biopython)))
6140 `(("python-nose" ,python-nose)))
6141 (home-page "https://github.com/fhcrc/seqmagick")
6142 (synopsis "Tools for converting and modifying sequence files")
6144 "Bioinformaticians often have to convert sequence files between formats
6145 and do little manipulations on them, and it's not worth writing scripts for
6146 that. Seqmagick is a utility to expose the file format conversion in
6147 BioPython in a convenient way. Instead of having a big mess of scripts, there
6148 is one that takes arguments.")
6149 (license license:gpl3)))
6151 (define-public seqtk
6158 (url "https://github.com/lh3/seqtk.git")
6159 (commit (string-append "v" version))))
6160 (file-name (git-file-name name version))
6163 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6164 (build-system gnu-build-system)
6167 (modify-phases %standard-phases
6170 ;; There are no tests, so we just run a sanity check.
6171 (lambda _ (invoke "./seqtk" "seq") #t))
6173 (lambda* (#:key outputs #:allow-other-keys)
6174 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6175 (install-file "seqtk" bin)
6179 (home-page "https://github.com/lh3/seqtk")
6180 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6182 "Seqtk is a fast and lightweight tool for processing sequences in the
6183 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6184 optionally compressed by gzip.")
6185 (license license:expat)))
6187 (define-public snap-aligner
6189 (name "snap-aligner")
6190 (version "1.0beta.18")
6194 (url "https://github.com/amplab/snap.git")
6195 (commit (string-append "v" version))))
6196 (file-name (git-file-name name version))
6199 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6200 (build-system gnu-build-system)
6203 (modify-phases %standard-phases
6205 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6207 (lambda* (#:key outputs #:allow-other-keys)
6208 (let* ((out (assoc-ref outputs "out"))
6209 (bin (string-append out "/bin")))
6210 (install-file "snap-aligner" bin)
6211 (install-file "SNAPCommand" bin)
6215 (home-page "http://snap.cs.berkeley.edu/")
6216 (synopsis "Short read DNA sequence aligner")
6218 "SNAP is a fast and accurate aligner for short DNA reads. It is
6219 optimized for modern read lengths of 100 bases or higher, and takes advantage
6220 of these reads to align data quickly through a hash-based indexing scheme.")
6221 ;; 32-bit systems are not supported by the unpatched code.
6222 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6223 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6224 ;; systems without a lot of memory cannot make good use of this program.
6225 (supported-systems '("x86_64-linux"))
6226 (license license:asl2.0)))
6228 (define-public sortmerna
6236 (url "https://github.com/biocore/sortmerna.git")
6238 (file-name (git-file-name name version))
6241 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6242 (build-system gnu-build-system)
6243 (outputs '("out" ;for binaries
6244 "db")) ;for sequence databases
6247 (modify-phases %standard-phases
6249 (lambda* (#:key outputs #:allow-other-keys)
6250 (let* ((out (assoc-ref outputs "out"))
6251 (bin (string-append out "/bin"))
6252 (db (assoc-ref outputs "db"))
6254 (string-append db "/share/sortmerna/rRNA_databases")))
6255 (install-file "sortmerna" bin)
6256 (install-file "indexdb_rna" bin)
6257 (for-each (lambda (file)
6258 (install-file file share))
6259 (find-files "rRNA_databases" ".*fasta"))
6263 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6264 (synopsis "Biological sequence analysis tool for NGS reads")
6266 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6267 and operational taxonomic unit (OTU) picking of next generation
6268 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6269 allows for fast and sensitive analyses of nucleotide sequences. The main
6270 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6271 ;; The source includes x86 specific code
6272 (supported-systems '("x86_64-linux" "i686-linux"))
6273 (license license:lgpl3)))
6282 (url "https://github.com/alexdobin/STAR.git")
6284 (file-name (string-append name "-" version "-checkout"))
6287 "0n6g4s4hgw7qygs1z97j7a2dgz8gfaa4cv5pjvvvmarvk0x07hyg"))
6288 (modules '((guix build utils)))
6291 (substitute* "source/Makefile"
6293 ;; Remove pre-built binaries and bundled htslib sources.
6294 (delete-file-recursively "bin/MacOSX_x86_64")
6295 (delete-file-recursively "bin/Linux_x86_64")
6296 (delete-file-recursively "bin/Linux_x86_64_static")
6297 (delete-file-recursively "source/htslib")
6299 (build-system gnu-build-system)
6301 '(#:tests? #f ;no check target
6302 #:make-flags '("STAR")
6304 (modify-phases %standard-phases
6305 (add-after 'unpack 'enter-source-dir
6306 (lambda _ (chdir "source") #t))
6307 (add-after 'enter-source-dir 'make-reproducible
6309 (substitute* "Makefile"
6310 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6311 (string-append pre "Built with Guix" post)))
6313 ;; See https://github.com/alexdobin/STAR/pull/562
6314 (add-after 'enter-source-dir 'add-missing-header
6316 (substitute* "SoloReadFeature_inputRecords.cpp"
6317 (("#include \"binarySearch2.h\"" h)
6318 (string-append h "\n#include <math.h>")))
6320 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6322 (substitute* "Makefile"
6323 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6325 (substitute* '("BAMfunctions.cpp"
6330 "bamRemoveDuplicates.cpp")
6331 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6332 (string-append "#include <" header ">")))
6333 (substitute* "IncludeDefine.h"
6334 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6335 (string-append "<" header ">")))
6338 (lambda* (#:key outputs #:allow-other-keys)
6339 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6340 (install-file "STAR" bin))
6342 (delete 'configure))))
6346 `(("htslib" ,htslib)
6348 (home-page "https://github.com/alexdobin/STAR")
6349 (synopsis "Universal RNA-seq aligner")
6351 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6352 based on a previously undescribed RNA-seq alignment algorithm that uses
6353 sequential maximum mappable seed search in uncompressed suffix arrays followed
6354 by seed clustering and stitching procedure. In addition to unbiased de novo
6355 detection of canonical junctions, STAR can discover non-canonical splices and
6356 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6358 ;; Only 64-bit systems are supported according to the README.
6359 (supported-systems '("x86_64-linux" "mips64el-linux"))
6360 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6361 (license license:gpl3+)))
6363 (define-public starlong
6364 (package (inherit star)
6367 (substitute-keyword-arguments (package-arguments star)
6368 ((#:make-flags flags)
6371 `(modify-phases ,phases
6372 ;; Allow extra long sequence reads.
6373 (add-after 'unpack 'make-extra-long
6375 (substitute* "source/IncludeDefine.h"
6376 (("(#define DEF_readNameLengthMax ).*" _ match)
6377 (string-append match "900000\n")))
6380 (lambda* (#:key outputs #:allow-other-keys)
6381 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6382 (install-file "STARlong" bin))
6385 (define-public subread
6391 (uri (string-append "mirror://sourceforge/subread/subread-"
6392 version "/subread-" version "-source.tar.gz"))
6395 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6396 (build-system gnu-build-system)
6398 `(#:tests? #f ;no "check" target
6399 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6400 ;; optimizations by default, so we override these flags such that x86_64
6401 ;; flags are only added when the build target is an x86_64 system.
6403 (list (let ((system ,(or (%current-target-system)
6405 (flags '("-ggdb" "-fomit-frame-pointer"
6406 "-ffast-math" "-funroll-loops"
6407 "-fmessage-length=0"
6408 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6410 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6411 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6412 (if (string-prefix? "x86_64" system)
6413 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6414 (string-append "CCFLAGS=" (string-join flags))))
6415 "-f" "Makefile.Linux"
6416 "CC=gcc ${CCFLAGS}")
6418 (modify-phases %standard-phases
6419 (add-after 'unpack 'enter-dir
6420 (lambda _ (chdir "src") #t))
6422 (lambda* (#:key outputs #:allow-other-keys)
6423 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6425 (copy-recursively "../bin" bin))
6427 ;; no "configure" script
6428 (delete 'configure))))
6429 (inputs `(("zlib" ,zlib)))
6430 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6431 (synopsis "Tool kit for processing next-gen sequencing data")
6433 "The subread package contains the following tools: subread aligner, a
6434 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6435 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6436 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6437 against local background noises.")
6438 (license license:gpl3+)))
6440 (define-public stringtie
6446 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6447 "stringtie-" version ".tar.gz"))
6450 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6451 (modules '((guix build utils)))
6454 (delete-file-recursively "samtools-0.1.18")
6456 (build-system gnu-build-system)
6458 `(#:tests? #f ;no test suite
6460 (modify-phases %standard-phases
6461 ;; no configure script
6463 (add-before 'build 'use-system-samtools
6465 (substitute* "Makefile"
6466 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6468 (substitute* '("gclib/GBam.h"
6470 (("#include \"(bam|sam|kstring).h\"" _ header)
6471 (string-append "#include <samtools/" header ".h>")))
6473 (add-after 'unpack 'remove-duplicate-typedef
6475 ;; This typedef conflicts with the typedef in
6476 ;; glibc-2.25/include/bits/types.h
6477 (substitute* "gclib/GThreads.h"
6478 (("typedef long long __intmax_t;") ""))
6481 (lambda* (#:key outputs #:allow-other-keys)
6482 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6483 (install-file "stringtie" bin)
6486 `(("samtools" ,samtools-0.1)
6488 (home-page "http://ccb.jhu.edu/software/stringtie/")
6489 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6491 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6492 alignments into potential transcripts. It uses a novel network flow algorithm
6493 as well as an optional de novo assembly step to assemble and quantitate
6494 full-length transcripts representing multiple splice variants for each gene
6495 locus. Its input can include not only the alignments of raw reads used by
6496 other transcript assemblers, but also alignments of longer sequences that have
6497 been assembled from those reads. To identify differentially expressed genes
6498 between experiments, StringTie's output can be processed either by the
6499 Cuffdiff or Ballgown programs.")
6500 (license license:artistic2.0)))
6502 (define-public taxtastic
6508 (uri (pypi-uri "taxtastic" version))
6511 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6512 (build-system python-build-system)
6514 `(#:python ,python-2
6516 (modify-phases %standard-phases
6518 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6520 `(("python-sqlalchemy" ,python2-sqlalchemy)
6521 ("python-decorator" ,python2-decorator)
6522 ("python-biopython" ,python2-biopython)
6523 ("python-pandas" ,python2-pandas)
6524 ("python-psycopg2" ,python2-psycopg2)
6525 ("python-fastalite" ,python2-fastalite)
6526 ("python-pyyaml" ,python2-pyyaml)
6527 ("python-six" ,python2-six)
6528 ("python-jinja2" ,python2-jinja2)
6529 ("python-dendropy" ,python2-dendropy)))
6530 (home-page "https://github.com/fhcrc/taxtastic")
6531 (synopsis "Tools for taxonomic naming and annotation")
6533 "Taxtastic is software written in python used to build and maintain
6534 reference packages i.e. collections of reference trees, reference alignments,
6535 profiles, and associated taxonomic information.")
6536 (license license:gpl3+)))
6538 (define-public vcftools
6545 "https://github.com/vcftools/vcftools/releases/download/v"
6546 version "/vcftools-" version ".tar.gz"))
6549 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6550 (build-system gnu-build-system)
6552 `(#:tests? #f ; no "check" target
6554 "CFLAGS=-O2" ; override "-m64" flag
6555 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6556 (string-append "MANDIR=" (assoc-ref %outputs "out")
6557 "/share/man/man1"))))
6559 `(("pkg-config" ,pkg-config)))
6563 (home-page "https://vcftools.github.io/")
6564 (synopsis "Tools for working with VCF files")
6566 "VCFtools is a program package designed for working with VCF files, such
6567 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6568 provide easily accessible methods for working with complex genetic variation
6569 data in the form of VCF files.")
6570 ;; The license is declared as LGPLv3 in the README and
6571 ;; at https://vcftools.github.io/license.html
6572 (license license:lgpl3)))
6574 (define-public infernal
6580 (uri (string-append "http://eddylab.org/software/infernal/"
6581 "infernal-" version ".tar.gz"))
6584 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6585 (build-system gnu-build-system)
6587 `(("perl" ,perl))) ; for tests
6588 (home-page "http://eddylab.org/infernal/")
6589 (synopsis "Inference of RNA alignments")
6590 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6591 searching DNA sequence databases for RNA structure and sequence similarities.
6592 It is an implementation of a special case of profile stochastic context-free
6593 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6594 profile, but it scores a combination of sequence consensus and RNA secondary
6595 structure consensus, so in many cases, it is more capable of identifying RNA
6596 homologs that conserve their secondary structure more than their primary
6598 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6599 (supported-systems '("i686-linux" "x86_64-linux"))
6600 (license license:bsd-3)))
6602 (define-public r-scde
6609 (url "https://github.com/hms-dbmi/scde.git")
6611 (file-name (git-file-name name version))
6614 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6615 (build-system r-build-system)
6617 `(("r-rcpp" ,r-rcpp)
6618 ("r-rcpparmadillo" ,r-rcpparmadillo)
6621 ("r-rjson" ,r-rjson)
6622 ("r-cairo" ,r-cairo)
6623 ("r-rcolorbrewer" ,r-rcolorbrewer)
6624 ("r-edger" ,r-edger)
6625 ("r-quantreg" ,r-quantreg)
6627 ("r-rmtstat" ,r-rmtstat)
6628 ("r-extremes" ,r-extremes)
6629 ("r-pcamethods" ,r-pcamethods)
6630 ("r-biocparallel" ,r-biocparallel)
6631 ("r-flexmix" ,r-flexmix)))
6632 (home-page "https://hms-dbmi.github.io/scde/")
6633 (synopsis "R package for analyzing single-cell RNA-seq data")
6634 (description "The SCDE package implements a set of statistical methods for
6635 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6636 single-cell RNA-seq measurements. These models can then be used for
6637 assessment of differential expression between groups of cells, as well as
6638 other types of analysis. The SCDE package also contains the pagoda framework
6639 which applies pathway and gene set overdispersion analysis to identify aspects
6640 of transcriptional heterogeneity among single cells.")
6641 ;; See https://github.com/hms-dbmi/scde/issues/38
6642 (license license:gpl2)))
6644 (define-public r-centipede
6646 (name "r-centipede")
6650 (uri (string-append "http://download.r-forge.r-project.org/"
6651 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6654 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6655 (build-system r-build-system)
6656 (home-page "http://centipede.uchicago.edu/")
6657 (synopsis "Predict transcription factor binding sites")
6659 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6660 of the genome that are bound by particular transcription factors. It starts
6661 by identifying a set of candidate binding sites, and then aims to classify the
6662 sites according to whether each site is bound or not bound by a transcription
6663 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6664 between two different types of motif instances using as much relevant
6665 information as possible.")
6666 (license (list license:gpl2+ license:gpl3+))))
6668 (define-public r-genefilter
6670 (name "r-genefilter")
6675 (uri (bioconductor-uri "genefilter" version))
6678 "1jq7lam4dnbvz55lx93kcl9afl8xfjd6xs374d35m21bkay418kj"))))
6679 (build-system r-build-system)
6681 `(("gfortran" ,gfortran)))
6683 `(("r-annotate" ,r-annotate)
6684 ("r-annotationdbi" ,r-annotationdbi)
6685 ("r-biobase" ,r-biobase)
6686 ("r-s4vectors" ,r-s4vectors)
6687 ("r-survival" ,r-survival)))
6688 (home-page "https://bioconductor.org/packages/genefilter")
6689 (synopsis "Filter genes from high-throughput experiments")
6691 "This package provides basic functions for filtering genes from
6692 high-throughput sequencing experiments.")
6693 (license license:artistic2.0)))
6695 (define-public r-deseq2
6702 (uri (bioconductor-uri "DESeq2" version))
6705 "0fkk326addm2cw688gnmdzsmri5qx8j6ldnr4xin6kjnwicqhlqd"))))
6706 (properties `((upstream-name . "DESeq2")))
6707 (build-system r-build-system)
6709 `(("r-biobase" ,r-biobase)
6710 ("r-biocgenerics" ,r-biocgenerics)
6711 ("r-biocparallel" ,r-biocparallel)
6712 ("r-genefilter" ,r-genefilter)
6713 ("r-geneplotter" ,r-geneplotter)
6714 ("r-genomicranges" ,r-genomicranges)
6715 ("r-ggplot2" ,r-ggplot2)
6716 ("r-hmisc" ,r-hmisc)
6717 ("r-iranges" ,r-iranges)
6718 ("r-locfit" ,r-locfit)
6720 ("r-rcpparmadillo" ,r-rcpparmadillo)
6721 ("r-s4vectors" ,r-s4vectors)
6722 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6723 (home-page "https://bioconductor.org/packages/DESeq2")
6724 (synopsis "Differential gene expression analysis")
6726 "This package provides functions to estimate variance-mean dependence in
6727 count data from high-throughput nucleotide sequencing assays and test for
6728 differential expression based on a model using the negative binomial
6730 (license license:lgpl3+)))
6732 (define-public r-dexseq
6739 (uri (bioconductor-uri "DEXSeq" version))
6742 "1b2s0vwm97g0wgm4ms0f4pqkqiqmxscnhg700aybl5vx0m2fa8xm"))))
6743 (properties `((upstream-name . "DEXSeq")))
6744 (build-system r-build-system)
6746 `(("r-annotationdbi" ,r-annotationdbi)
6747 ("r-biobase" ,r-biobase)
6748 ("r-biocgenerics" ,r-biocgenerics)
6749 ("r-biocparallel" ,r-biocparallel)
6750 ("r-biomart" ,r-biomart)
6751 ("r-deseq2" ,r-deseq2)
6752 ("r-genefilter" ,r-genefilter)
6753 ("r-geneplotter" ,r-geneplotter)
6754 ("r-genomicranges" ,r-genomicranges)
6755 ("r-hwriter" ,r-hwriter)
6756 ("r-iranges" ,r-iranges)
6757 ("r-rcolorbrewer" ,r-rcolorbrewer)
6758 ("r-rsamtools" ,r-rsamtools)
6759 ("r-s4vectors" ,r-s4vectors)
6760 ("r-statmod" ,r-statmod)
6761 ("r-stringr" ,r-stringr)
6762 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6763 (home-page "https://bioconductor.org/packages/DEXSeq")
6764 (synopsis "Inference of differential exon usage in RNA-Seq")
6766 "This package is focused on finding differential exon usage using RNA-seq
6767 exon counts between samples with different experimental designs. It provides
6768 functions that allows the user to make the necessary statistical tests based
6769 on a model that uses the negative binomial distribution to estimate the
6770 variance between biological replicates and generalized linear models for
6771 testing. The package also provides functions for the visualization and
6772 exploration of the results.")
6773 (license license:gpl3+)))
6775 (define-public r-annotationforge
6777 (name "r-annotationforge")
6782 (uri (bioconductor-uri "AnnotationForge" version))
6785 "0m4w8n2711wr28znv646cfc7m5jqlr8friz334zdyjmhg7m2xkb7"))))
6787 `((upstream-name . "AnnotationForge")))
6788 (build-system r-build-system)
6790 `(("r-annotationdbi" ,r-annotationdbi)
6791 ("r-biobase" ,r-biobase)
6792 ("r-biocgenerics" ,r-biocgenerics)
6794 ("r-rcurl" ,r-rcurl)
6795 ("r-rsqlite" ,r-rsqlite)
6796 ("r-s4vectors" ,r-s4vectors)
6798 (home-page "https://bioconductor.org/packages/AnnotationForge")
6799 (synopsis "Code for building annotation database packages")
6801 "This package provides code for generating Annotation packages and their
6802 databases. Packages produced are intended to be used with AnnotationDbi.")
6803 (license license:artistic2.0)))
6805 (define-public r-rbgl
6812 (uri (bioconductor-uri "RBGL" version))
6815 "06brn9hl6lybx6hdfp1sycwj6wn1bjfi8xyhpy0v122v1z8d5mbz"))))
6816 (properties `((upstream-name . "RBGL")))
6817 (build-system r-build-system)
6820 ("r-graph" ,r-graph)))
6821 (home-page "https://www.bioconductor.org/packages/RBGL")
6822 (synopsis "Interface to the Boost graph library")
6824 "This package provides a fairly extensive and comprehensive interface to
6825 the graph algorithms contained in the Boost library.")
6826 (license license:artistic2.0)))
6828 (define-public r-gseabase
6835 (uri (bioconductor-uri "GSEABase" version))
6838 "0vh53xk2prjbdkbr3hwfiflx1gh7ilrqs3j1p3lyd6syy3rn9n83"))))
6839 (properties `((upstream-name . "GSEABase")))
6840 (build-system r-build-system)
6842 `(("r-annotate" ,r-annotate)
6843 ("r-annotationdbi" ,r-annotationdbi)
6844 ("r-biobase" ,r-biobase)
6845 ("r-biocgenerics" ,r-biocgenerics)
6846 ("r-graph" ,r-graph)
6848 (home-page "https://bioconductor.org/packages/GSEABase")
6849 (synopsis "Gene set enrichment data structures and methods")
6851 "This package provides classes and methods to support @dfn{Gene Set
6852 Enrichment Analysis} (GSEA).")
6853 (license license:artistic2.0)))
6855 (define-public r-category
6862 (uri (bioconductor-uri "Category" version))
6865 "1n36xfnwn2np5f0lix9abvv9w6jb25jqz3xzvqzklz9s1af4k6x4"))))
6866 (properties `((upstream-name . "Category")))
6867 (build-system r-build-system)
6869 `(("r-annotate" ,r-annotate)
6870 ("r-annotationdbi" ,r-annotationdbi)
6871 ("r-biobase" ,r-biobase)
6872 ("r-biocgenerics" ,r-biocgenerics)
6873 ("r-genefilter" ,r-genefilter)
6874 ("r-graph" ,r-graph)
6875 ("r-gseabase" ,r-gseabase)
6876 ("r-matrix" ,r-matrix)
6879 (home-page "https://bioconductor.org/packages/Category")
6880 (synopsis "Category analysis")
6882 "This package provides a collection of tools for performing category
6884 (license license:artistic2.0)))
6886 (define-public r-gostats
6893 (uri (bioconductor-uri "GOstats" version))
6896 "1a95i6awm2a8xv42fg2z3n29fg9z29i45kd80hxf6mvqqgzj80xp"))))
6897 (properties `((upstream-name . "GOstats")))
6898 (build-system r-build-system)
6900 `(("r-annotate" ,r-annotate)
6901 ("r-annotationdbi" ,r-annotationdbi)
6902 ("r-annotationforge" ,r-annotationforge)
6903 ("r-biobase" ,r-biobase)
6904 ("r-category" ,r-category)
6905 ("r-go-db" ,r-go-db)
6906 ("r-graph" ,r-graph)
6907 ("r-rgraphviz" ,r-rgraphviz)
6908 ("r-rbgl" ,r-rbgl)))
6909 (home-page "https://bioconductor.org/packages/GOstats")
6910 (synopsis "Tools for manipulating GO and microarrays")
6912 "This package provides a set of tools for interacting with GO and
6913 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6914 testing and other simple calculations.")
6915 (license license:artistic2.0)))
6917 (define-public r-shortread
6919 (name "r-shortread")
6924 (uri (bioconductor-uri "ShortRead" version))
6927 "1irqzdgsavjqsq0vva4966qh8qgn7xn9382dmhahm1hxb94qmi59"))))
6928 (properties `((upstream-name . "ShortRead")))
6929 (build-system r-build-system)
6933 `(("r-biobase" ,r-biobase)
6934 ("r-biocgenerics" ,r-biocgenerics)
6935 ("r-biocparallel" ,r-biocparallel)
6936 ("r-biostrings" ,r-biostrings)
6937 ("r-genomeinfodb" ,r-genomeinfodb)
6938 ("r-genomicalignments" ,r-genomicalignments)
6939 ("r-genomicranges" ,r-genomicranges)
6940 ("r-hwriter" ,r-hwriter)
6941 ("r-iranges" ,r-iranges)
6942 ("r-lattice" ,r-lattice)
6943 ("r-latticeextra" ,r-latticeextra)
6944 ("r-rsamtools" ,r-rsamtools)
6945 ("r-s4vectors" ,r-s4vectors)
6946 ("r-xvector" ,r-xvector)
6947 ("r-zlibbioc" ,r-zlibbioc)))
6948 (home-page "https://bioconductor.org/packages/ShortRead")
6949 (synopsis "FASTQ input and manipulation tools")
6951 "This package implements sampling, iteration, and input of FASTQ files.
6952 It includes functions for filtering and trimming reads, and for generating a
6953 quality assessment report. Data are represented as
6954 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6955 purposes. The package also contains legacy support for early single-end,
6956 ungapped alignment formats.")
6957 (license license:artistic2.0)))
6959 (define-public r-systempiper
6961 (name "r-systempiper")
6966 (uri (bioconductor-uri "systemPipeR" version))
6969 "18s5vpmw766pm64w7bwwfgpsv9yzhwclf0ya1rpqz8qslw7bbdjf"))))
6970 (properties `((upstream-name . "systemPipeR")))
6971 (build-system r-build-system)
6973 `(("r-annotate" ,r-annotate)
6974 ("r-batchtools" ,r-batchtools)
6975 ("r-biocgenerics" ,r-biocgenerics)
6976 ("r-biostrings" ,r-biostrings)
6977 ("r-deseq2" ,r-deseq2)
6978 ("r-edger" ,r-edger)
6979 ("r-genomicfeatures" ,r-genomicfeatures)
6980 ("r-genomicranges" ,r-genomicranges)
6981 ("r-ggplot2" ,r-ggplot2)
6982 ("r-go-db" ,r-go-db)
6983 ("r-gostats" ,r-gostats)
6984 ("r-limma" ,r-limma)
6985 ("r-pheatmap" ,r-pheatmap)
6986 ("r-rjson" ,r-rjson)
6987 ("r-rsamtools" ,r-rsamtools)
6988 ("r-shortread" ,r-shortread)
6989 ("r-summarizedexperiment" ,r-summarizedexperiment)
6991 ("r-variantannotation" ,r-variantannotation)))
6992 (home-page "https://github.com/tgirke/systemPipeR")
6993 (synopsis "Next generation sequencing workflow and reporting environment")
6995 "This R package provides tools for building and running automated
6996 end-to-end analysis workflows for a wide range of @dfn{next generation
6997 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6998 Important features include a uniform workflow interface across different NGS
6999 applications, automated report generation, and support for running both R and
7000 command-line software, such as NGS aligners or peak/variant callers, on local
7001 computers or compute clusters. Efficient handling of complex sample sets and
7002 experimental designs is facilitated by a consistently implemented sample
7003 annotation infrastructure.")
7004 (license license:artistic2.0)))
7006 (define-public r-grohmm
7013 (uri (bioconductor-uri "groHMM" version))
7016 "1p368qf8ab1vy8gl2j7rx0l7bvva4m7w06i364rqzs0sdyzlbm3y"))))
7017 (properties `((upstream-name . "groHMM")))
7018 (build-system r-build-system)
7020 `(("r-genomeinfodb" ,r-genomeinfodb)
7021 ("r-genomicalignments" ,r-genomicalignments)
7022 ("r-genomicranges" ,r-genomicranges)
7023 ("r-iranges" ,r-iranges)
7025 ("r-rtracklayer" ,r-rtracklayer)
7026 ("r-s4vectors" ,r-s4vectors)))
7027 (home-page "https://github.com/Kraus-Lab/groHMM")
7028 (synopsis "GRO-seq analysis pipeline")
7030 "This package provides a pipeline for the analysis of GRO-seq data.")
7031 (license license:gpl3+)))
7033 (define-public vsearch
7041 (url "https://github.com/torognes/vsearch.git")
7042 (commit (string-append "v" version))))
7043 (file-name (git-file-name name version))
7046 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7047 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7050 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7051 ;; for this in the patch.
7052 (delete-file "src/city.h")
7053 (delete-file "src/citycrc.h")
7054 (delete-file "src/city.cc")
7056 (build-system gnu-build-system)
7060 ("cityhash" ,cityhash)))
7062 `(("autoconf" ,autoconf)
7063 ("automake" ,automake)))
7064 (synopsis "Sequence search tools for metagenomics")
7066 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7067 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7068 masking. The tool takes advantage of parallelism in the form of SIMD
7069 vectorization as well as multiple threads to perform accurate alignments at
7070 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7071 Needleman-Wunsch).")
7072 (home-page "https://github.com/torognes/vsearch")
7073 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7075 (supported-systems '("x86_64-linux"))
7076 ;; Dual licensed; also includes public domain source.
7077 (license (list license:gpl3 license:bsd-2))))
7079 (define-public pardre
7082 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7087 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7091 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7092 (build-system gnu-build-system)
7094 `(#:tests? #f ; no tests included
7096 (modify-phases %standard-phases
7099 (lambda* (#:key outputs #:allow-other-keys)
7100 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7101 (install-file "ParDRe" bin)
7104 `(("openmpi" ,openmpi)
7106 (synopsis "Parallel tool to remove duplicate DNA reads")
7108 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7109 Duplicate reads can be seen as identical or nearly identical sequences with
7110 some mismatches. This tool lets users avoid the analysis of unnecessary
7111 reads, reducing the time of subsequent procedures with the
7112 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7113 in order to exploit the parallel capabilities of multicore clusters. It is
7114 faster than multithreaded counterparts (end of 2015) for the same number of
7115 cores and, thanks to the message-passing technology, it can be executed on
7117 (home-page "https://sourceforge.net/projects/pardre/")
7118 (license license:gpl3+)))
7120 (define-public ruby-bio-kseq
7122 (name "ruby-bio-kseq")
7127 (uri (rubygems-uri "bio-kseq" version))
7130 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7131 (build-system ruby-build-system)
7133 `(#:test-target "spec"))
7135 `(("bundler" ,bundler)
7136 ("ruby-rspec" ,ruby-rspec)
7137 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7140 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7142 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7143 FASTQ parsing code. It provides a fast iterator over sequences and their
7145 (home-page "https://github.com/gusevfe/bio-kseq")
7146 (license license:expat)))
7148 (define-public bio-locus
7155 (uri (rubygems-uri "bio-locus" version))
7158 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7159 (build-system ruby-build-system)
7161 `(("ruby-rspec" ,ruby-rspec)))
7162 (synopsis "Tool for fast querying of genome locations")
7164 "Bio-locus is a tabix-like tool for fast querying of genome
7165 locations. Many file formats in bioinformatics contain records that
7166 start with a chromosome name and a position for a SNP, or a start-end
7167 position for indels. Bio-locus allows users to store this chr+pos or
7168 chr+pos+alt information in a database.")
7169 (home-page "https://github.com/pjotrp/bio-locus")
7170 (license license:expat)))
7172 (define-public bio-blastxmlparser
7174 (name "bio-blastxmlparser")
7178 (uri (rubygems-uri "bio-blastxmlparser" version))
7181 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7182 (build-system ruby-build-system)
7184 `(("ruby-bio-logger" ,ruby-bio-logger)
7185 ("ruby-nokogiri" ,ruby-nokogiri)))
7187 `(("ruby-rspec" ,ruby-rspec)))
7188 (synopsis "Fast big data BLAST XML parser and library")
7190 "Very fast parallel big-data BLAST XML file parser which can be used as
7191 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7192 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7193 (home-page "https://github.com/pjotrp/blastxmlparser")
7194 (license license:expat)))
7196 (define-public bioruby
7203 (uri (rubygems-uri "bio" version))
7206 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7207 (build-system ruby-build-system)
7209 `(("ruby-libxml" ,ruby-libxml)))
7211 `(("which" ,which))) ; required for test phase
7214 (modify-phases %standard-phases
7215 (add-before 'build 'patch-test-command
7217 (substitute* '("test/functional/bio/test_command.rb")
7218 (("/bin/sh") (which "sh")))
7219 (substitute* '("test/functional/bio/test_command.rb")
7220 (("/bin/ls") (which "ls")))
7221 (substitute* '("test/functional/bio/test_command.rb")
7222 (("which") (which "which")))
7223 (substitute* '("test/functional/bio/test_command.rb",
7224 "test/data/command/echoarg2.sh")
7225 (("/bin/echo") (which "echo")))
7227 (synopsis "Ruby library, shell and utilities for bioinformatics")
7228 (description "BioRuby comes with a comprehensive set of Ruby development
7229 tools and libraries for bioinformatics and molecular biology. BioRuby has
7230 components for sequence analysis, pathway analysis, protein modelling and
7231 phylogenetic analysis; it supports many widely used data formats and provides
7232 easy access to databases, external programs and public web services, including
7233 BLAST, KEGG, GenBank, MEDLINE and GO.")
7234 (home-page "http://bioruby.org/")
7235 ;; Code is released under Ruby license, except for setup
7236 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7237 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7239 (define-public r-biocviews
7241 (name "r-biocviews")
7245 (uri (bioconductor-uri "biocViews" version))
7248 "0qwrsd9fcpkv7hhzy1scnj7ahdxi6cjary28kqk6b36gkzmnrw4r"))))
7250 `((upstream-name . "biocViews")))
7251 (build-system r-build-system)
7253 `(("r-biobase" ,r-biobase)
7254 ("r-biocmanager" ,r-biocmanager)
7255 ("r-graph" ,r-graph)
7257 ("r-rcurl" ,r-rcurl)
7259 ("r-runit" ,r-runit)))
7260 (home-page "https://bioconductor.org/packages/biocViews")
7261 (synopsis "Bioconductor package categorization helper")
7262 (description "The purpose of biocViews is to create HTML pages that
7263 categorize packages in a Bioconductor package repository according to keywords,
7264 also known as views, in a controlled vocabulary.")
7265 (license license:artistic2.0)))
7267 (define-public r-biocstyle
7269 (name "r-biocstyle")
7273 (uri (bioconductor-uri "BiocStyle" version))
7276 "029x8r9rcx6zy0xixdpwxai4jv4ynb161821fzac6z4r8k418398"))))
7278 `((upstream-name . "BiocStyle")))
7279 (build-system r-build-system)
7281 `(("r-biocmanager" ,r-biocmanager)
7282 ("r-bookdown" ,r-bookdown)
7283 ("r-knitr" ,r-knitr)
7284 ("r-rmarkdown" ,r-rmarkdown)
7285 ("r-yaml" ,r-yaml)))
7286 (home-page "https://bioconductor.org/packages/BiocStyle")
7287 (synopsis "Bioconductor formatting styles")
7288 (description "This package provides standard formatting styles for
7289 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7291 (license license:artistic2.0)))
7293 (define-public r-bioccheck
7295 (name "r-bioccheck")
7299 (uri (bioconductor-uri "BiocCheck" version))
7302 "1gkw9s6dhdryga9ap5yhvcqg9jsy4cn417ayqk1qiv6fy91fd124"))))
7304 `((upstream-name . "BiocCheck")))
7305 (build-system r-build-system)
7308 (modify-phases %standard-phases
7309 ;; This package can be used by calling BiocCheck(<package>) from
7310 ;; within R, or by running R CMD BiocCheck <package>. This phase
7311 ;; makes sure the latter works. For this to work, the BiocCheck
7312 ;; script must be somewhere on the PATH (not the R bin directory).
7313 (add-after 'install 'install-bioccheck-subcommand
7314 (lambda* (#:key outputs #:allow-other-keys)
7315 (let* ((out (assoc-ref outputs "out"))
7316 (dest-dir (string-append out "/bin"))
7318 (string-append out "/site-library/BiocCheck/script/")))
7320 (symlink (string-append script-dir "/checkBadDeps.R")
7321 (string-append dest-dir "/checkBadDeps.R"))
7322 (symlink (string-append script-dir "/BiocCheck")
7323 (string-append dest-dir "/BiocCheck")))
7326 `(("r-codetools" ,r-codetools)
7327 ("r-graph" ,r-graph)
7329 ("r-knitr" ,r-knitr)
7330 ("r-optparse" ,r-optparse)
7331 ("r-biocmanager" ,r-biocmanager)
7332 ("r-biocviews" ,r-biocviews)
7333 ("r-stringdist" ,r-stringdist)))
7334 (home-page "https://bioconductor.org/packages/BiocCheck")
7335 (synopsis "Executes Bioconductor-specific package checks")
7336 (description "This package contains tools to perform additional quality
7337 checks on R packages that are to be submitted to the Bioconductor repository.")
7338 (license license:artistic2.0)))
7340 (define-public r-s4vectors
7342 (name "r-s4vectors")
7346 (uri (bioconductor-uri "S4Vectors" version))
7349 "0cpxqb18wd3pjd7bi8lry13sm5ffqahcvvxpk5pwm5xcj30cdlm9"))))
7351 `((upstream-name . "S4Vectors")))
7352 (build-system r-build-system)
7354 `(("r-biocgenerics" ,r-biocgenerics)))
7355 (home-page "https://bioconductor.org/packages/S4Vectors")
7356 (synopsis "S4 implementation of vectors and lists")
7358 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7359 classes and a set of generic functions that extend the semantic of ordinary
7360 vectors and lists in R. Package developers can easily implement vector-like
7361 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7362 In addition, a few low-level concrete subclasses of general interest (e.g.
7363 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7364 S4Vectors package itself.")
7365 (license license:artistic2.0)))
7367 (define-public r-iranges
7373 (uri (bioconductor-uri "IRanges" version))
7376 "05rw2b2bwns443n7d6lf97zdv1jbqdii2nprhs6x852w73m2a2g3"))))
7378 `((upstream-name . "IRanges")))
7379 (build-system r-build-system)
7381 `(("r-biocgenerics" ,r-biocgenerics)
7382 ("r-s4vectors" ,r-s4vectors)))
7383 (home-page "https://bioconductor.org/packages/IRanges")
7384 (synopsis "Infrastructure for manipulating intervals on sequences")
7386 "This package provides efficient low-level and highly reusable S4 classes
7387 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7388 generally, data that can be organized sequentially (formally defined as
7389 @code{Vector} objects), as well as views on these @code{Vector} objects.
7390 Efficient list-like classes are also provided for storing big collections of
7391 instances of the basic classes. All classes in the package use consistent
7392 naming and share the same rich and consistent \"Vector API\" as much as
7394 (license license:artistic2.0)))
7396 (define-public r-genomeinfodbdata
7398 (name "r-genomeinfodbdata")
7402 ;; We cannot use bioconductor-uri here because this tarball is
7403 ;; located under "data/annotation/" instead of "bioc/".
7404 (uri (string-append "https://bioconductor.org/packages/release/"
7405 "data/annotation/src/contrib/GenomeInfoDbData_"
7409 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7411 `((upstream-name . "GenomeInfoDbData")))
7412 (build-system r-build-system)
7413 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7414 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7415 (description "This package contains data for mapping between NCBI taxonomy
7416 ID and species. It is used by functions in the GenomeInfoDb package.")
7417 (license license:artistic2.0)))
7419 (define-public r-genomeinfodb
7421 (name "r-genomeinfodb")
7425 (uri (bioconductor-uri "GenomeInfoDb" version))
7428 "0zkhms81b3jz30q7ag81a1mq1rgqg4izyfdvcni68gvn8gm7kdyk"))))
7430 `((upstream-name . "GenomeInfoDb")))
7431 (build-system r-build-system)
7433 `(("r-biocgenerics" ,r-biocgenerics)
7434 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7435 ("r-iranges" ,r-iranges)
7436 ("r-rcurl" ,r-rcurl)
7437 ("r-s4vectors" ,r-s4vectors)))
7438 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7439 (synopsis "Utilities for manipulating chromosome identifiers")
7441 "This package contains data and functions that define and allow
7442 translation between different chromosome sequence naming conventions (e.g.,
7443 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7444 names in their natural, rather than lexicographic, order.")
7445 (license license:artistic2.0)))
7447 (define-public r-edger
7453 (uri (bioconductor-uri "edgeR" version))
7456 "1wwimzviy2vklp80faz7sbbp74qcw2csbmlfgvzj7b785vwarpwg"))))
7457 (properties `((upstream-name . "edgeR")))
7458 (build-system r-build-system)
7460 `(("r-limma" ,r-limma)
7461 ("r-locfit" ,r-locfit)
7463 ("r-statmod" ,r-statmod))) ;for estimateDisp
7464 (home-page "http://bioinf.wehi.edu.au/edgeR")
7465 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7466 (description "This package can do differential expression analysis of
7467 RNA-seq expression profiles with biological replication. It implements a range
7468 of statistical methodology based on the negative binomial distributions,
7469 including empirical Bayes estimation, exact tests, generalized linear models
7470 and quasi-likelihood tests. It be applied to differential signal analysis of
7471 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7473 (license license:gpl2+)))
7475 (define-public r-variantannotation
7477 (name "r-variantannotation")
7481 (uri (bioconductor-uri "VariantAnnotation" version))
7484 "144x3d3b9a3q5jy4aqrk1nf2yavwjhwlf71s7qyr4x3ms3wmvf8i"))))
7486 `((upstream-name . "VariantAnnotation")))
7490 `(("r-annotationdbi" ,r-annotationdbi)
7491 ("r-biobase" ,r-biobase)
7492 ("r-biocgenerics" ,r-biocgenerics)
7493 ("r-biostrings" ,r-biostrings)
7494 ("r-bsgenome" ,r-bsgenome)
7496 ("r-genomeinfodb" ,r-genomeinfodb)
7497 ("r-genomicfeatures" ,r-genomicfeatures)
7498 ("r-genomicranges" ,r-genomicranges)
7499 ("r-iranges" ,r-iranges)
7500 ("r-summarizedexperiment" ,r-summarizedexperiment)
7501 ("r-rhtslib" ,r-rhtslib)
7502 ("r-rsamtools" ,r-rsamtools)
7503 ("r-rtracklayer" ,r-rtracklayer)
7504 ("r-s4vectors" ,r-s4vectors)
7505 ("r-xvector" ,r-xvector)
7506 ("r-zlibbioc" ,r-zlibbioc)))
7507 (build-system r-build-system)
7508 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7509 (synopsis "Package for annotation of genetic variants")
7510 (description "This R package can annotate variants, compute amino acid
7511 coding changes and predict coding outcomes.")
7512 (license license:artistic2.0)))
7514 (define-public r-limma
7520 (uri (bioconductor-uri "limma" version))
7523 "166z8cdh6w90rldqqaar7hyaskwiy4smawjfbn4sn58clv6q3mp8"))))
7524 (build-system r-build-system)
7525 (home-page "http://bioinf.wehi.edu.au/limma")
7526 (synopsis "Package for linear models for microarray and RNA-seq data")
7527 (description "This package can be used for the analysis of gene expression
7528 studies, especially the use of linear models for analysing designed experiments
7529 and the assessment of differential expression. The analysis methods apply to
7530 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7531 (license license:gpl2+)))
7533 (define-public r-xvector
7539 (uri (bioconductor-uri "XVector" version))
7542 "12y09pwy86h1za6cmaxs960r7fs0vjzhl0li8jn59vqq9liza1ap"))))
7544 `((upstream-name . "XVector")))
7545 (build-system r-build-system)
7548 (modify-phases %standard-phases
7549 (add-after 'unpack 'use-system-zlib
7551 (substitute* "DESCRIPTION"
7552 (("zlibbioc, ") ""))
7553 (substitute* "NAMESPACE"
7554 (("import\\(zlibbioc\\)") ""))
7559 `(("r-biocgenerics" ,r-biocgenerics)
7560 ("r-iranges" ,r-iranges)
7561 ("r-s4vectors" ,r-s4vectors)))
7562 (home-page "https://bioconductor.org/packages/XVector")
7563 (synopsis "Representation and manpulation of external sequences")
7565 "This package provides memory efficient S4 classes for storing sequences
7566 \"externally\" (behind an R external pointer, or on disk).")
7567 (license license:artistic2.0)))
7569 (define-public r-genomicranges
7571 (name "r-genomicranges")
7575 (uri (bioconductor-uri "GenomicRanges" version))
7578 "1yid84gn0052v52h84685lvk854grl1wl65psmlmxx9yyykgc0jn"))))
7580 `((upstream-name . "GenomicRanges")))
7581 (build-system r-build-system)
7583 `(("r-biocgenerics" ,r-biocgenerics)
7584 ("r-genomeinfodb" ,r-genomeinfodb)
7585 ("r-iranges" ,r-iranges)
7586 ("r-s4vectors" ,r-s4vectors)
7587 ("r-xvector" ,r-xvector)))
7588 (home-page "https://bioconductor.org/packages/GenomicRanges")
7589 (synopsis "Representation and manipulation of genomic intervals")
7591 "This package provides tools to efficiently represent and manipulate
7592 genomic annotations and alignments is playing a central role when it comes to
7593 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7594 GenomicRanges package defines general purpose containers for storing and
7595 manipulating genomic intervals and variables defined along a genome.")
7596 (license license:artistic2.0)))
7598 (define-public r-biobase
7604 (uri (bioconductor-uri "Biobase" version))
7607 "15yl92niqamx3lmwd11zlk0xniibqnh1gi280iadxicmchi83npc"))))
7609 `((upstream-name . "Biobase")))
7610 (build-system r-build-system)
7612 `(("r-biocgenerics" ,r-biocgenerics)))
7613 (home-page "https://bioconductor.org/packages/Biobase")
7614 (synopsis "Base functions for Bioconductor")
7616 "This package provides functions that are needed by many other packages
7617 on Bioconductor or which replace R functions.")
7618 (license license:artistic2.0)))
7620 (define-public r-annotationdbi
7622 (name "r-annotationdbi")
7626 (uri (bioconductor-uri "AnnotationDbi" version))
7629 "13nanz4nzy0mcda8ljz2g8d81hpqfz6jky7ydz5hpk0g2264b9ga"))))
7631 `((upstream-name . "AnnotationDbi")))
7632 (build-system r-build-system)
7634 `(("r-biobase" ,r-biobase)
7635 ("r-biocgenerics" ,r-biocgenerics)
7637 ("r-iranges" ,r-iranges)
7638 ("r-rsqlite" ,r-rsqlite)
7639 ("r-s4vectors" ,r-s4vectors)))
7640 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7641 (synopsis "Annotation database interface")
7643 "This package provides user interface and database connection code for
7644 annotation data packages using SQLite data storage.")
7645 (license license:artistic2.0)))
7647 (define-public r-biomart
7653 (uri (bioconductor-uri "biomaRt" version))
7656 "1kjvxnkpsx3j2hji3cg3ka2gv8a9mg117lzzxyqjb7qa4zw7dipx"))))
7658 `((upstream-name . "biomaRt")))
7659 (build-system r-build-system)
7661 `(("r-annotationdbi" ,r-annotationdbi)
7663 ("r-progress" ,r-progress)
7664 ("r-rcurl" ,r-rcurl)
7665 ("r-stringr" ,r-stringr)
7667 (home-page "https://bioconductor.org/packages/biomaRt")
7668 (synopsis "Interface to BioMart databases")
7670 "biomaRt provides an interface to a growing collection of databases
7671 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7672 package enables retrieval of large amounts of data in a uniform way without
7673 the need to know the underlying database schemas or write complex SQL queries.
7674 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7675 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7676 users direct access to a diverse set of data and enable a wide range of
7677 powerful online queries from gene annotation to database mining.")
7678 (license license:artistic2.0)))
7680 (define-public r-biocparallel
7682 (name "r-biocparallel")
7686 (uri (bioconductor-uri "BiocParallel" version))
7689 "1j6wbls4qgvi5gj99c51r00jhxrzxk3x3258wg7dcjzbfqypvyw3"))))
7691 `((upstream-name . "BiocParallel")))
7692 (build-system r-build-system)
7694 `(("r-futile-logger" ,r-futile-logger)
7697 (home-page "https://bioconductor.org/packages/BiocParallel")
7698 (synopsis "Bioconductor facilities for parallel evaluation")
7700 "This package provides modified versions and novel implementation of
7701 functions for parallel evaluation, tailored to use with Bioconductor
7703 (license (list license:gpl2+ license:gpl3+))))
7705 (define-public r-biostrings
7707 (name "r-biostrings")
7711 (uri (bioconductor-uri "Biostrings" version))
7714 "0inrl97hli3qz6cfxcikc4picmbrqc8phdgqi18ynlvxy5ql64h4"))))
7716 `((upstream-name . "Biostrings")))
7717 (build-system r-build-system)
7719 `(("r-biocgenerics" ,r-biocgenerics)
7720 ("r-iranges" ,r-iranges)
7721 ("r-s4vectors" ,r-s4vectors)
7722 ("r-xvector" ,r-xvector)))
7723 (home-page "https://bioconductor.org/packages/Biostrings")
7724 (synopsis "String objects and algorithms for biological sequences")
7726 "This package provides memory efficient string containers, string
7727 matching algorithms, and other utilities, for fast manipulation of large
7728 biological sequences or sets of sequences.")
7729 (license license:artistic2.0)))
7731 (define-public r-rsamtools
7733 (name "r-rsamtools")
7737 (uri (bioconductor-uri "Rsamtools" version))
7740 "03qfpaqbffirpnby88mv6h45njfapli28crdvg35h2zi2jkkmhvp"))))
7742 `((upstream-name . "Rsamtools")))
7743 (build-system r-build-system)
7746 (modify-phases %standard-phases
7747 (add-after 'unpack 'use-system-zlib
7749 (substitute* "DESCRIPTION"
7750 (("zlibbioc, ") ""))
7751 (substitute* "NAMESPACE"
7752 (("import\\(zlibbioc\\)") ""))
7757 `(("r-biocgenerics" ,r-biocgenerics)
7758 ("r-biocparallel" ,r-biocparallel)
7759 ("r-biostrings" ,r-biostrings)
7760 ("r-bitops" ,r-bitops)
7761 ("r-genomeinfodb" ,r-genomeinfodb)
7762 ("r-genomicranges" ,r-genomicranges)
7763 ("r-iranges" ,r-iranges)
7764 ("r-rhtslib" ,r-rhtslib)
7765 ("r-s4vectors" ,r-s4vectors)
7766 ("r-xvector" ,r-xvector)))
7767 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7768 (synopsis "Interface to samtools, bcftools, and tabix")
7770 "This package provides an interface to the @code{samtools},
7771 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7772 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7773 tab-delimited (tabix) files.")
7774 (license license:expat)))
7776 (define-public r-delayedarray
7778 (name "r-delayedarray")
7782 (uri (bioconductor-uri "DelayedArray" version))
7785 "0l907ggxndn3f29zvsd5pppmp4c31rb22r6zkhvgph7xdxahyy6z"))))
7787 `((upstream-name . "DelayedArray")))
7788 (build-system r-build-system)
7790 `(("r-biocgenerics" ,r-biocgenerics)
7791 ("r-biocparallel" ,r-biocparallel)
7792 ("r-s4vectors" ,r-s4vectors)
7793 ("r-iranges" ,r-iranges)
7794 ("r-matrix" ,r-matrix)
7795 ("r-matrixstats" ,r-matrixstats)))
7796 (home-page "https://bioconductor.org/packages/DelayedArray")
7797 (synopsis "Delayed operations on array-like objects")
7799 "Wrapping an array-like object (typically an on-disk object) in a
7800 @code{DelayedArray} object allows one to perform common array operations on it
7801 without loading the object in memory. In order to reduce memory usage and
7802 optimize performance, operations on the object are either delayed or executed
7803 using a block processing mechanism. Note that this also works on in-memory
7804 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7805 @code{Matrix} objects, and ordinary arrays and data frames.")
7806 (license license:artistic2.0)))
7808 (define-public r-summarizedexperiment
7810 (name "r-summarizedexperiment")
7814 (uri (bioconductor-uri "SummarizedExperiment" version))
7817 "0bhwgzrdipr0qjzc4j0qspqprx3v1rvshmx4j6506dv43pqlgp3f"))))
7819 `((upstream-name . "SummarizedExperiment")))
7820 (build-system r-build-system)
7822 `(("r-biobase" ,r-biobase)
7823 ("r-biocgenerics" ,r-biocgenerics)
7824 ("r-delayedarray" ,r-delayedarray)
7825 ("r-genomeinfodb" ,r-genomeinfodb)
7826 ("r-genomicranges" ,r-genomicranges)
7827 ("r-iranges" ,r-iranges)
7828 ("r-matrix" ,r-matrix)
7829 ("r-s4vectors" ,r-s4vectors)))
7830 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7831 (synopsis "Container for representing genomic ranges by sample")
7833 "The SummarizedExperiment container contains one or more assays, each
7834 represented by a matrix-like object of numeric or other mode. The rows
7835 typically represent genomic ranges of interest and the columns represent
7837 (license license:artistic2.0)))
7839 (define-public r-genomicalignments
7841 (name "r-genomicalignments")
7845 (uri (bioconductor-uri "GenomicAlignments" version))
7848 "0s3q97q4pgj5jwn4g95al44rahrwsncsf45v01v4071msx3xmjxq"))))
7850 `((upstream-name . "GenomicAlignments")))
7851 (build-system r-build-system)
7853 `(("r-biocgenerics" ,r-biocgenerics)
7854 ("r-biocparallel" ,r-biocparallel)
7855 ("r-biostrings" ,r-biostrings)
7856 ("r-genomeinfodb" ,r-genomeinfodb)
7857 ("r-genomicranges" ,r-genomicranges)
7858 ("r-iranges" ,r-iranges)
7859 ("r-rsamtools" ,r-rsamtools)
7860 ("r-s4vectors" ,r-s4vectors)
7861 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7862 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7863 (synopsis "Representation and manipulation of short genomic alignments")
7865 "This package provides efficient containers for storing and manipulating
7866 short genomic alignments (typically obtained by aligning short reads to a
7867 reference genome). This includes read counting, computing the coverage,
7868 junction detection, and working with the nucleotide content of the
7870 (license license:artistic2.0)))
7872 (define-public r-rtracklayer
7874 (name "r-rtracklayer")
7878 (uri (bioconductor-uri "rtracklayer" version))
7881 "0dnifr58j2si2qbnvap2wslz3xgjv3h4l7a6v7nmmc57hq6kdbym"))))
7882 (build-system r-build-system)
7885 (modify-phases %standard-phases
7886 (add-after 'unpack 'use-system-zlib
7888 (substitute* "DESCRIPTION"
7889 ((" zlibbioc,") ""))
7890 (substitute* "NAMESPACE"
7891 (("import\\(zlibbioc\\)") ""))
7894 `(("pkg-config" ,pkg-config)))
7898 `(("r-biocgenerics" ,r-biocgenerics)
7899 ("r-biostrings" ,r-biostrings)
7900 ("r-genomeinfodb" ,r-genomeinfodb)
7901 ("r-genomicalignments" ,r-genomicalignments)
7902 ("r-genomicranges" ,r-genomicranges)
7903 ("r-iranges" ,r-iranges)
7904 ("r-rcurl" ,r-rcurl)
7905 ("r-rsamtools" ,r-rsamtools)
7906 ("r-s4vectors" ,r-s4vectors)
7908 ("r-xvector" ,r-xvector)))
7909 (home-page "https://bioconductor.org/packages/rtracklayer")
7910 (synopsis "R interface to genome browsers and their annotation tracks")
7912 "rtracklayer is an extensible framework for interacting with multiple
7913 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7914 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7915 built-in). The user may export/import tracks to/from the supported browsers,
7916 as well as query and modify the browser state, such as the current viewport.")
7917 (license license:artistic2.0)))
7919 (define-public r-genomicfeatures
7921 (name "r-genomicfeatures")
7925 (uri (bioconductor-uri "GenomicFeatures" version))
7928 "0mzqv8pyxx5nwchyx3radym9ws2f9hb50xc9abjsjs4w4pv91j3k"))))
7930 `((upstream-name . "GenomicFeatures")))
7931 (build-system r-build-system)
7933 `(("r-annotationdbi" ,r-annotationdbi)
7934 ("r-biobase" ,r-biobase)
7935 ("r-biocgenerics" ,r-biocgenerics)
7936 ("r-biomart" ,r-biomart)
7937 ("r-biostrings" ,r-biostrings)
7939 ("r-genomeinfodb" ,r-genomeinfodb)
7940 ("r-genomicranges" ,r-genomicranges)
7941 ("r-iranges" ,r-iranges)
7942 ("r-rcurl" ,r-rcurl)
7943 ("r-rsqlite" ,r-rsqlite)
7944 ("r-rtracklayer" ,r-rtracklayer)
7945 ("r-s4vectors" ,r-s4vectors)
7946 ("r-xvector" ,r-xvector)))
7947 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7948 (synopsis "Tools for working with transcript centric annotations")
7950 "This package provides a set of tools and methods for making and
7951 manipulating transcript centric annotations. With these tools the user can
7952 easily download the genomic locations of the transcripts, exons and cds of a
7953 given organism, from either the UCSC Genome Browser or a BioMart
7954 database (more sources will be supported in the future). This information is
7955 then stored in a local database that keeps track of the relationship between
7956 transcripts, exons, cds and genes. Flexible methods are provided for
7957 extracting the desired features in a convenient format.")
7958 (license license:artistic2.0)))
7960 (define-public r-go-db
7966 (uri (string-append "https://www.bioconductor.org/packages/"
7967 "release/data/annotation/src/contrib/GO.db_"
7971 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7973 `((upstream-name . "GO.db")))
7974 (build-system r-build-system)
7976 `(("r-annotationdbi" ,r-annotationdbi)))
7977 (home-page "https://bioconductor.org/packages/GO.db")
7978 (synopsis "Annotation maps describing the entire Gene Ontology")
7980 "The purpose of this GO.db annotation package is to provide detailed
7981 information about the latest version of the Gene Ontologies.")
7982 (license license:artistic2.0)))
7984 (define-public r-topgo
7990 (uri (bioconductor-uri "topGO" version))
7993 "09z42jwz5vh289ijz3x68zv5vmgkgcbhlp73vvmna1gld5lh5kz1"))))
7995 `((upstream-name . "topGO")))
7996 (build-system r-build-system)
7998 `(("r-annotationdbi" ,r-annotationdbi)
8000 ("r-biobase" ,r-biobase)
8001 ("r-biocgenerics" ,r-biocgenerics)
8002 ("r-go-db" ,r-go-db)
8003 ("r-graph" ,r-graph)
8004 ("r-lattice" ,r-lattice)
8005 ("r-matrixstats" ,r-matrixstats)
8006 ("r-sparsem" ,r-sparsem)))
8007 (home-page "https://bioconductor.org/packages/topGO")
8008 (synopsis "Enrichment analysis for gene ontology")
8010 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8011 terms while accounting for the topology of the GO graph. Different test
8012 statistics and different methods for eliminating local similarities and
8013 dependencies between GO terms can be implemented and applied.")
8014 ;; Any version of the LGPL applies.
8015 (license license:lgpl2.1+)))
8017 (define-public r-bsgenome
8023 (uri (bioconductor-uri "BSgenome" version))
8026 "0zwx42s73hc1vhn0v82i67mcixdwwc6n6q5h5vpnhpxlm4qwgqzp"))))
8028 `((upstream-name . "BSgenome")))
8029 (build-system r-build-system)
8031 `(("r-biocgenerics" ,r-biocgenerics)
8032 ("r-biostrings" ,r-biostrings)
8033 ("r-genomeinfodb" ,r-genomeinfodb)
8034 ("r-genomicranges" ,r-genomicranges)
8035 ("r-iranges" ,r-iranges)
8036 ("r-rsamtools" ,r-rsamtools)
8037 ("r-rtracklayer" ,r-rtracklayer)
8038 ("r-s4vectors" ,r-s4vectors)
8039 ("r-xvector" ,r-xvector)))
8040 (home-page "https://bioconductor.org/packages/BSgenome")
8041 (synopsis "Infrastructure for Biostrings-based genome data packages")
8043 "This package provides infrastructure shared by all Biostrings-based
8044 genome data packages and support for efficient SNP representation.")
8045 (license license:artistic2.0)))
8047 (define-public r-impute
8053 (uri (bioconductor-uri "impute" version))
8056 "144jb889979cv3il2zxqk724v3sj1wnzjm3lkspxcvk29dbb9q8j"))))
8058 `(("gfortran" ,gfortran)))
8059 (build-system r-build-system)
8060 (home-page "https://bioconductor.org/packages/impute")
8061 (synopsis "Imputation for microarray data")
8063 "This package provides a function to impute missing gene expression
8064 microarray data, using nearest neighbor averaging.")
8065 (license license:gpl2+)))
8067 (define-public r-seqpattern
8069 (name "r-seqpattern")
8073 (uri (bioconductor-uri "seqPattern" version))
8076 "1ljqscbmrmi5d4lzzvg2d86sqzch26yxw57d33qyid300wm60db2"))))
8078 `((upstream-name . "seqPattern")))
8079 (build-system r-build-system)
8081 `(("r-biostrings" ,r-biostrings)
8082 ("r-genomicranges" ,r-genomicranges)
8083 ("r-iranges" ,r-iranges)
8084 ("r-kernsmooth" ,r-kernsmooth)
8085 ("r-plotrix" ,r-plotrix)))
8086 (home-page "https://bioconductor.org/packages/seqPattern")
8087 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8089 "This package provides tools to visualize oligonucleotide patterns and
8090 sequence motif occurrences across a large set of sequences centred at a common
8091 reference point and sorted by a user defined feature.")
8092 (license license:gpl3+)))
8094 (define-public r-genomation
8096 (name "r-genomation")
8100 (uri (bioconductor-uri "genomation" version))
8103 "06i711pwq9znd7plh0p25skxnnh5dyl61c33k9gma243wvlzmlkj"))))
8104 (build-system r-build-system)
8106 `(("r-biostrings" ,r-biostrings)
8107 ("r-bsgenome" ,r-bsgenome)
8108 ("r-data-table" ,r-data-table)
8109 ("r-genomeinfodb" ,r-genomeinfodb)
8110 ("r-genomicalignments" ,r-genomicalignments)
8111 ("r-genomicranges" ,r-genomicranges)
8112 ("r-ggplot2" ,r-ggplot2)
8113 ("r-gridbase" ,r-gridbase)
8114 ("r-impute" ,r-impute)
8115 ("r-iranges" ,r-iranges)
8116 ("r-matrixstats" ,r-matrixstats)
8117 ("r-plotrix" ,r-plotrix)
8120 ("r-readr" ,r-readr)
8121 ("r-reshape2" ,r-reshape2)
8122 ("r-rsamtools" ,r-rsamtools)
8123 ("r-rtracklayer" ,r-rtracklayer)
8124 ("r-runit" ,r-runit)
8125 ("r-s4vectors" ,r-s4vectors)
8126 ("r-seqpattern" ,r-seqpattern)))
8127 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8128 (synopsis "Summary, annotation and visualization of genomic data")
8130 "This package provides a package for summary and annotation of genomic
8131 intervals. Users can visualize and quantify genomic intervals over
8132 pre-defined functional regions, such as promoters, exons, introns, etc. The
8133 genomic intervals represent regions with a defined chromosome position, which
8134 may be associated with a score, such as aligned reads from HT-seq experiments,
8135 TF binding sites, methylation scores, etc. The package can use any tabular
8136 genomic feature data as long as it has minimal information on the locations of
8137 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8138 (license license:artistic2.0)))
8140 (define-public r-genomationdata
8142 (name "r-genomationdata")
8146 ;; We cannot use bioconductor-uri here because this tarball is
8147 ;; located under "data/annotation/" instead of "bioc/".
8148 (uri (string-append "https://bioconductor.org/packages/"
8149 "release/data/experiment/src/contrib/"
8150 "genomationData_" version ".tar.gz"))
8153 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8154 (build-system r-build-system)
8155 ;; As this package provides little more than large data files, it doesn't
8156 ;; make sense to build substitutes.
8157 (arguments `(#:substitutable? #f))
8159 `(("r-knitr" ,r-knitr)))
8160 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8161 (synopsis "Experimental data for use with the genomation package")
8163 "This package contains experimental genetic data for use with the
8164 genomation package. Included are Chip Seq, Methylation and Cage data,
8165 downloaded from Encode.")
8166 (license license:gpl3+)))
8168 (define-public r-seqlogo
8175 (uri (bioconductor-uri "seqLogo" version))
8178 "1z63imr1a24nqijpvxaxlakykcsadfqyxl2b3vlllncxnjjvb52b"))))
8179 (properties `((upstream-name . "seqLogo")))
8180 (build-system r-build-system)
8181 (home-page "https://bioconductor.org/packages/seqLogo")
8182 (synopsis "Sequence logos for DNA sequence alignments")
8184 "seqLogo takes the position weight matrix of a DNA sequence motif and
8185 plots the corresponding sequence logo as introduced by Schneider and
8187 (license license:lgpl2.0+)))
8189 (define-public r-motifrg
8196 (uri (bioconductor-uri "motifRG" version))
8199 "02c7fbjwdq7pk96bd2rn07l9r2hqy00s3hfpli5ybmwgvc9h9z4z"))))
8200 (properties `((upstream-name . "motifRG")))
8201 (build-system r-build-system)
8203 `(("r-biostrings" ,r-biostrings)
8204 ("r-bsgenome" ,r-bsgenome)
8205 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8206 ("r-iranges" ,r-iranges)
8207 ("r-seqlogo" ,r-seqlogo)
8208 ("r-xvector" ,r-xvector)))
8209 (home-page "https://bioconductor.org/packages/motifRG")
8210 (synopsis "Discover motifs in high throughput sequencing data")
8212 "This package provides tools for discriminative motif discovery in high
8213 throughput genetic sequencing data sets using regression methods.")
8214 (license license:artistic2.0)))
8216 (define-public r-qtl
8223 (uri (string-append "mirror://cran/src/contrib/qtl_"
8227 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8228 (build-system r-build-system)
8229 (home-page "http://rqtl.org/")
8230 (synopsis "R package for analyzing QTL experiments in genetics")
8231 (description "R/qtl is an extension library for the R statistics
8232 system. It is used to analyze experimental crosses for identifying
8233 genes contributing to variation in quantitative traits (so-called
8234 quantitative trait loci, QTLs).
8236 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8237 identify genotyping errors, and to perform single-QTL and two-QTL,
8238 two-dimensional genome scans.")
8239 (license license:gpl3)))
8241 (define-public r-zlibbioc
8247 (uri (bioconductor-uri "zlibbioc" version))
8250 "1h0a2ps2rfk9azzps7p23sxj5z1giv8gcx0ypzgyz7fkr4xi9z7k"))))
8252 `((upstream-name . "zlibbioc")))
8253 (build-system r-build-system)
8254 (home-page "https://bioconductor.org/packages/zlibbioc")
8255 (synopsis "Provider for zlib-1.2.5 to R packages")
8256 (description "This package uses the source code of zlib-1.2.5 to create
8257 libraries for systems that do not have these available via other means.")
8258 (license license:artistic2.0)))
8260 (define-public r-r4rna
8267 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8271 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8272 (build-system r-build-system)
8274 `(("r-optparse" ,r-optparse)
8275 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8276 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8277 (synopsis "Analysis framework for RNA secondary structure")
8279 "The R4RNA package aims to be a general framework for the analysis of RNA
8280 secondary structure and comparative analysis in R.")
8281 (license license:gpl3+)))
8283 (define-public r-rhtslib
8290 (uri (bioconductor-uri "Rhtslib" version))
8293 "07qaqj2hypmrg40m3pci082bzar6wi10dh77r4a8x74dfppcwdzf"))))
8294 (properties `((upstream-name . "Rhtslib")))
8295 (build-system r-build-system)
8296 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8297 ;; which makes R abort the build.
8298 (arguments '(#:configure-flags '("--no-staged-install")))
8300 `(("r-zlibbioc" ,r-zlibbioc)))
8304 `(("pkg-config" ,pkg-config)))
8305 (home-page "https://github.com/nhayden/Rhtslib")
8306 (synopsis "High-throughput sequencing library as an R package")
8308 "This package provides the HTSlib C library for high-throughput
8309 nucleotide sequence analysis. The package is primarily useful to developers
8310 of other R packages who wish to make use of HTSlib.")
8311 (license license:lgpl2.0+)))
8313 (define-public r-bamsignals
8315 (name "r-bamsignals")
8320 (uri (bioconductor-uri "bamsignals" version))
8323 "15q1q51dwl9qxfkf10yppw4m194ba03nq9plsrbj8fqj00v4729i"))))
8324 (build-system r-build-system)
8326 `(("r-biocgenerics" ,r-biocgenerics)
8327 ("r-genomicranges" ,r-genomicranges)
8328 ("r-iranges" ,r-iranges)
8330 ("r-rhtslib" ,r-rhtslib)
8331 ("r-zlibbioc" ,r-zlibbioc)))
8334 (home-page "https://bioconductor.org/packages/bamsignals")
8335 (synopsis "Extract read count signals from bam files")
8337 "This package allows to efficiently obtain count vectors from indexed bam
8338 files. It counts the number of nucleotide sequence reads in given genomic
8339 ranges and it computes reads profiles and coverage profiles. It also handles
8341 (license license:gpl2+)))
8343 (define-public r-rcas
8349 (uri (bioconductor-uri "RCAS" version))
8352 "06z5zmdi34jblw37z6ff8hb6lvvi0chwr37acwqfn8d27ax9lakz"))))
8353 (properties `((upstream-name . "RCAS")))
8354 (build-system r-build-system)
8356 `(("r-annotationdbi" ,r-annotationdbi)
8357 ("r-biocgenerics" ,r-biocgenerics)
8358 ("r-biomart" ,r-biomart)
8359 ("r-biostrings" ,r-biostrings)
8360 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8361 ("r-cowplot" ,r-cowplot)
8362 ("r-data-table" ,r-data-table)
8365 ("r-genomation" ,r-genomation)
8366 ("r-genomeinfodb" ,r-genomeinfodb)
8367 ("r-genomicfeatures" ,r-genomicfeatures)
8368 ("r-genomicranges" ,r-genomicranges)
8369 ("r-ggplot2" ,r-ggplot2)
8370 ("r-ggseqlogo" ,r-ggseqlogo)
8371 ("r-knitr" ,r-knitr)
8372 ("r-motifrg" ,r-motifrg)
8373 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8374 ("r-pbapply" ,r-pbapply)
8375 ("r-pheatmap" ,r-pheatmap)
8376 ("r-plotly" ,r-plotly)
8377 ("r-plotrix" ,r-plotrix)
8378 ("r-proxy" ,r-proxy)
8379 ("r-rsqlite" ,r-rsqlite)
8380 ("r-rtracklayer" ,r-rtracklayer)
8381 ("r-rmarkdown" ,r-rmarkdown)
8382 ("r-s4vectors" ,r-s4vectors)
8383 ("r-topgo" ,r-topgo)
8384 ("pandoc" ,ghc-pandoc)))
8385 (synopsis "RNA-centric annotation system")
8387 "RCAS aims to be a standalone RNA-centric annotation system that provides
8388 intuitive reports and publication-ready graphics. This package provides the R
8389 library implementing most of the pipeline's features.")
8390 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8391 (license license:artistic2.0)))
8393 (define-public rcas-web
8400 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8401 "releases/download/v" version
8402 "/rcas-web-" version ".tar.gz"))
8405 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8406 (build-system gnu-build-system)
8409 (modify-phases %standard-phases
8410 (add-before 'configure 'find-RCAS
8411 ;; The configure script can't find non-1.3.x versions of RCAS because
8412 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8414 (substitute* "configure"
8415 (("1\\.3\\.4") "0.0.0"))
8417 (add-after 'install 'wrap-executable
8418 (lambda* (#:key inputs outputs #:allow-other-keys)
8419 (let* ((out (assoc-ref outputs "out"))
8420 (json (assoc-ref inputs "guile-json"))
8421 (redis (assoc-ref inputs "guile-redis"))
8422 (path (string-append
8423 json "/share/guile/site/2.2:"
8424 redis "/share/guile/site/2.2")))
8425 (wrap-program (string-append out "/bin/rcas-web")
8426 `("GUILE_LOAD_PATH" ":" = (,path))
8427 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8428 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8431 `(("r-minimal" ,r-minimal)
8433 ("guile-next" ,guile-2.2)
8434 ("guile-json" ,guile-json-1)
8435 ("guile-redis" ,guile-redis)))
8437 `(("pkg-config" ,pkg-config)))
8438 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8439 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8440 (description "This package provides a simple web interface for the
8441 @dfn{RNA-centric annotation system} (RCAS).")
8442 (license license:agpl3+)))
8444 (define-public r-mutationalpatterns
8446 (name "r-mutationalpatterns")
8451 (uri (bioconductor-uri "MutationalPatterns" version))
8454 "1k3r06xj1nim1s8as1i7fykfa6fbb4x456kslbzdvbf83ppx34z3"))))
8455 (build-system r-build-system)
8457 `(("r-biocgenerics" ,r-biocgenerics)
8458 ("r-biostrings" ,r-biostrings)
8459 ;; These two packages are suggested packages
8460 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8461 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8462 ("r-genomicranges" ,r-genomicranges)
8463 ("r-genomeinfodb" ,r-genomeinfodb)
8464 ("r-ggplot2" ,r-ggplot2)
8465 ("r-iranges" ,r-iranges)
8468 ("r-pracma" ,r-pracma)
8469 ("r-reshape2" ,r-reshape2)
8470 ("r-cowplot" ,r-cowplot)
8471 ("r-ggdendro" ,r-ggdendro)
8472 ("r-s4vectors" ,r-s4vectors)
8473 ("r-summarizedexperiment" ,r-summarizedexperiment)
8474 ("r-variantannotation" ,r-variantannotation)))
8475 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8476 (synopsis "Extract and visualize mutational patterns in genomic data")
8477 (description "This package provides an extensive toolset for the
8478 characterization and visualization of a wide range of mutational patterns
8479 in SNV base substitution data.")
8480 (license license:expat)))
8482 (define-public r-chipkernels
8483 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8486 (name "r-chipkernels")
8487 (version (string-append "1.1-" revision "." (string-take commit 9)))
8492 (url "https://github.com/ManuSetty/ChIPKernels.git")
8494 (file-name (string-append name "-" version))
8497 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8498 (build-system r-build-system)
8500 `(("r-iranges" ,r-iranges)
8501 ("r-xvector" ,r-xvector)
8502 ("r-biostrings" ,r-biostrings)
8503 ("r-bsgenome" ,r-bsgenome)
8504 ("r-gtools" ,r-gtools)
8505 ("r-genomicranges" ,r-genomicranges)
8506 ("r-sfsmisc" ,r-sfsmisc)
8507 ("r-kernlab" ,r-kernlab)
8508 ("r-s4vectors" ,r-s4vectors)
8509 ("r-biocgenerics" ,r-biocgenerics)))
8510 (home-page "https://github.com/ManuSetty/ChIPKernels")
8511 (synopsis "Build string kernels for DNA Sequence analysis")
8512 (description "ChIPKernels is an R package for building different string
8513 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8514 must be built and this dictionary can be used for determining kernels for DNA
8516 (license license:gpl2+))))
8518 (define-public r-seqgl
8526 (url "https://github.com/ManuSetty/SeqGL.git")
8528 (file-name (git-file-name name version))
8531 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8532 (build-system r-build-system)
8534 `(("r-biostrings" ,r-biostrings)
8535 ("r-chipkernels" ,r-chipkernels)
8536 ("r-genomicranges" ,r-genomicranges)
8537 ("r-spams" ,r-spams)
8538 ("r-wgcna" ,r-wgcna)
8539 ("r-fastcluster" ,r-fastcluster)))
8540 (home-page "https://github.com/ManuSetty/SeqGL")
8541 (synopsis "Group lasso for Dnase/ChIP-seq data")
8542 (description "SeqGL is a group lasso based algorithm to extract
8543 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8544 This package presents a method which uses group lasso to discriminate between
8545 bound and non bound genomic regions to accurately identify transcription
8546 factors bound at the specific regions.")
8547 (license license:gpl2+)))
8549 (define-public r-tximport
8555 (uri (bioconductor-uri "tximport" version))
8558 "070nx0blvvfhsnkbb5j899wy7dgalrh4xfcciir9l2xl67lna1zf"))))
8559 (build-system r-build-system)
8560 (home-page "https://bioconductor.org/packages/tximport")
8561 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8563 "This package provides tools to import transcript-level abundance,
8564 estimated counts and transcript lengths, and to summarize them into matrices
8565 for use with downstream gene-level analysis packages. Average transcript
8566 length, weighted by sample-specific transcript abundance estimates, is
8567 provided as a matrix which can be used as an offset for different expression
8568 of gene-level counts.")
8569 (license license:gpl2+)))
8571 (define-public r-rhdf5
8577 (uri (bioconductor-uri "rhdf5" version))
8580 "0y1w3cs7wg2b3jlkd6wyyz6626xg011nrg36si8gg371iqck9a1i"))))
8581 (build-system r-build-system)
8583 `(("r-rhdf5lib" ,r-rhdf5lib)))
8586 (home-page "https://bioconductor.org/packages/rhdf5")
8587 (synopsis "HDF5 interface to R")
8589 "This R/Bioconductor package provides an interface between HDF5 and R.
8590 HDF5's main features are the ability to store and access very large and/or
8591 complex datasets and a wide variety of metadata on mass storage (disk) through
8592 a completely portable file format. The rhdf5 package is thus suited for the
8593 exchange of large and/or complex datasets between R and other software
8594 package, and for letting R applications work on datasets that are larger than
8595 the available RAM.")
8596 (license license:artistic2.0)))
8598 (define-public r-annotationfilter
8600 (name "r-annotationfilter")
8604 (uri (bioconductor-uri "AnnotationFilter" version))
8607 "15qh4jwxxqsnb308nxzj99gckfk18rhp8g26q1xwgkr57zc5kcrx"))))
8609 `((upstream-name . "AnnotationFilter")))
8610 (build-system r-build-system)
8612 `(("r-genomicranges" ,r-genomicranges)
8613 ("r-lazyeval" ,r-lazyeval)))
8614 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8615 (synopsis "Facilities for filtering Bioconductor annotation resources")
8617 "This package provides classes and other infrastructure to implement
8618 filters for manipulating Bioconductor annotation resources. The filters are
8619 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8620 (license license:artistic2.0)))
8622 (define-public emboss
8628 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8629 (version-major+minor version) ".0/"
8630 "EMBOSS-" version ".tar.gz"))
8633 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8634 (build-system gnu-build-system)
8637 (list (string-append "--with-hpdf="
8638 (assoc-ref %build-inputs "libharu")))
8640 (modify-phases %standard-phases
8641 (add-after 'unpack 'fix-checks
8643 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8644 ;; and zlib, but assume that they are all found at the same
8646 (substitute* "configure.in"
8647 (("CHECK_PNGDRIVER")
8648 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8649 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8650 AM_CONDITIONAL(AMPNG, true)"))
8652 (add-after 'fix-checks 'disable-update-check
8654 ;; At build time there is no connection to the Internet, so
8655 ;; looking for updates will not work.
8656 (substitute* "Makefile.am"
8657 (("\\$\\(bindir\\)/embossupdate") ""))
8659 (add-after 'disable-update-check 'autogen
8660 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8666 ("libharu" ,libharu)
8669 `(("autoconf" ,autoconf)
8670 ("automake" ,automake)
8671 ("libtool" ,libtool)
8672 ("pkg-config" ,pkg-config)))
8673 (home-page "http://emboss.sourceforge.net")
8674 (synopsis "Molecular biology analysis suite")
8675 (description "EMBOSS is the \"European Molecular Biology Open Software
8676 Suite\". EMBOSS is an analysis package specially developed for the needs of
8677 the molecular biology (e.g. EMBnet) user community. The software
8678 automatically copes with data in a variety of formats and even allows
8679 transparent retrieval of sequence data from the web. It also provides a
8680 number of libraries for the development of software in the field of molecular
8681 biology. EMBOSS also integrates a range of currently available packages and
8682 tools for sequence analysis into a seamless whole.")
8683 (license license:gpl2+)))
8686 (let ((revision "1")
8687 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8690 ;; The version is 2.13.0 even though no release archives have been
8691 ;; published as yet.
8692 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8696 (url "https://github.com/arq5x/bits.git")
8698 (file-name (string-append name "-" version "-checkout"))
8701 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8702 (build-system gnu-build-system)
8704 `(#:tests? #f ;no tests included
8706 (modify-phases %standard-phases
8708 (add-after 'unpack 'remove-cuda
8710 (substitute* "Makefile"
8712 (("(bits_test_intersections) \\\\" _ match) match))
8715 (lambda* (#:key outputs #:allow-other-keys)
8717 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8722 (home-page "https://github.com/arq5x/bits")
8723 (synopsis "Implementation of binary interval search algorithm")
8724 (description "This package provides an implementation of the
8725 BITS (Binary Interval Search) algorithm, an approach to interval set
8726 intersection. It is especially suited for the comparison of diverse genomic
8727 datasets and the exploration of large datasets of genome
8728 intervals (e.g. genes, sequence alignments).")
8729 (license license:gpl2))))
8731 (define-public piranha
8732 ;; There is no release tarball for the latest version. The latest commit is
8733 ;; older than one year at the time of this writing.
8734 (let ((revision "1")
8735 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8738 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8742 (url "https://github.com/smithlabcode/piranha.git")
8744 (file-name (git-file-name name version))
8747 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8748 (build-system gnu-build-system)
8750 `(#:test-target "test"
8752 (modify-phases %standard-phases
8753 (add-after 'unpack 'copy-smithlab-cpp
8754 (lambda* (#:key inputs #:allow-other-keys)
8755 (for-each (lambda (file)
8756 (install-file file "./src/smithlab_cpp/"))
8757 (find-files (assoc-ref inputs "smithlab-cpp")))
8759 (add-after 'install 'install-to-store
8760 (lambda* (#:key outputs #:allow-other-keys)
8761 (let* ((out (assoc-ref outputs "out"))
8762 (bin (string-append out "/bin")))
8763 (for-each (lambda (file)
8764 (install-file file bin))
8765 (find-files "bin" ".*")))
8768 (list (string-append "--with-bam_tools_headers="
8769 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8770 (string-append "--with-bam_tools_library="
8771 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8773 `(("bamtools" ,bamtools)
8774 ("samtools" ,samtools-0.1)
8777 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8781 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8783 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8786 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8788 `(("python" ,python-2)))
8789 (home-page "https://github.com/smithlabcode/piranha")
8790 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8792 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8793 RIP-seq experiments. It takes input in BED or BAM format and identifies
8794 regions of statistically significant read enrichment. Additional covariates
8795 may optionally be provided to further inform the peak-calling process.")
8796 (license license:gpl3+))))
8804 (uri (pypi-uri "PePr" version))
8807 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8808 (build-system python-build-system)
8810 `(#:python ,python-2 ; python2 only
8811 #:tests? #f)) ; no tests included
8813 `(("python2-numpy" ,python2-numpy)
8814 ("python2-scipy" ,python2-scipy)
8815 ("python2-pysam" ,python2-pysam)))
8816 (home-page "https://github.com/shawnzhangyx/PePr")
8817 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8819 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8820 that is primarily designed for data with biological replicates. It uses a
8821 negative binomial distribution to model the read counts among the samples in
8822 the same group, and look for consistent differences between ChIP and control
8823 group or two ChIP groups run under different conditions.")
8824 (license license:gpl3+)))
8826 (define-public filevercmp
8827 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8830 (version (string-append "0-1." (string-take commit 7)))
8834 (url "https://github.com/ekg/filevercmp.git")
8836 (file-name (git-file-name name commit))
8839 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8840 (build-system gnu-build-system)
8842 `(#:tests? #f ; There are no tests to run.
8844 (modify-phases %standard-phases
8845 (delete 'configure) ; There is no configure phase.
8847 (lambda* (#:key outputs #:allow-other-keys)
8848 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8849 (install-file "filevercmp" bin)
8851 (home-page "https://github.com/ekg/filevercmp")
8852 (synopsis "This program compares version strings")
8853 (description "This program compares version strings. It intends to be a
8854 replacement for strverscmp.")
8855 (license license:gpl3+))))
8857 (define-public multiqc
8864 (uri (pypi-uri "multiqc" version))
8867 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8868 (build-system python-build-system)
8870 `(("python-jinja2" ,python-jinja2)
8871 ("python-simplejson" ,python-simplejson)
8872 ("python-pyyaml" ,python-pyyaml)
8873 ("python-click" ,python-click)
8874 ("python-spectra" ,python-spectra)
8875 ("python-requests" ,python-requests)
8876 ("python-markdown" ,python-markdown)
8877 ("python-lzstring" ,python-lzstring)
8878 ("python-matplotlib" ,python-matplotlib)
8879 ("python-numpy" ,python-numpy)
8880 ;; MultQC checks for the presence of nose at runtime.
8881 ("python-nose" ,python-nose)))
8884 (modify-phases %standard-phases
8885 (add-after 'unpack 'relax-requirements
8887 (substitute* "setup.py"
8888 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8889 ;; than the one in Guix, but should work fine with 2.2.2.
8890 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8891 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8892 (("['\"]matplotlib.*?['\"]")
8895 (home-page "http://multiqc.info")
8896 (synopsis "Aggregate bioinformatics analysis reports")
8898 "MultiQC is a tool to aggregate bioinformatics results across many
8899 samples into a single report. It contains modules for a large number of
8900 common bioinformatics tools.")
8901 (license license:gpl3+)))
8903 (define-public r-chipseq
8910 (uri (bioconductor-uri "chipseq" version))
8913 "1835nhrxcaqpqf1kxrsk1js8bf7x33z1n3bqjvm8404091acqyma"))))
8914 (build-system r-build-system)
8916 `(("r-biocgenerics" ,r-biocgenerics)
8917 ("r-genomicranges" ,r-genomicranges)
8918 ("r-iranges" ,r-iranges)
8919 ("r-lattice" ,r-lattice)
8920 ("r-s4vectors" ,r-s4vectors)
8921 ("r-shortread" ,r-shortread)))
8922 (home-page "https://bioconductor.org/packages/chipseq")
8923 (synopsis "Package for analyzing ChIPseq data")
8925 "This package provides tools for processing short read data from ChIPseq
8927 (license license:artistic2.0)))
8929 (define-public r-copyhelper
8931 (name "r-copyhelper")
8936 (uri (string-append "https://bioconductor.org/packages/release/"
8937 "data/experiment/src/contrib/CopyhelpeR_"
8941 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8942 (properties `((upstream-name . "CopyhelpeR")))
8943 (build-system r-build-system)
8944 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8945 (synopsis "Helper files for CopywriteR")
8947 "This package contains the helper files that are required to run the
8948 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8949 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8950 mm10. In addition, it contains a blacklist filter to remove regions that
8951 display copy number variation. Files are stored as GRanges objects from the
8952 GenomicRanges Bioconductor package.")
8953 (license license:gpl2)))
8955 (define-public r-copywriter
8957 (name "r-copywriter")
8962 (uri (bioconductor-uri "CopywriteR" version))
8965 "0kv3k58wyyicq1hhq7bddh0v3b2ksz6fa47skvnp8f193csza9g6"))))
8966 (properties `((upstream-name . "CopywriteR")))
8967 (build-system r-build-system)
8969 `(("r-biocparallel" ,r-biocparallel)
8970 ("r-chipseq" ,r-chipseq)
8971 ("r-copyhelper" ,r-copyhelper)
8972 ("r-data-table" ,r-data-table)
8973 ("r-dnacopy" ,r-dnacopy)
8974 ("r-futile-logger" ,r-futile-logger)
8975 ("r-genomeinfodb" ,r-genomeinfodb)
8976 ("r-genomicalignments" ,r-genomicalignments)
8977 ("r-genomicranges" ,r-genomicranges)
8978 ("r-gtools" ,r-gtools)
8979 ("r-iranges" ,r-iranges)
8980 ("r-matrixstats" ,r-matrixstats)
8981 ("r-rsamtools" ,r-rsamtools)
8982 ("r-s4vectors" ,r-s4vectors)))
8983 (home-page "https://github.com/PeeperLab/CopywriteR")
8984 (synopsis "Copy number information from targeted sequencing")
8986 "CopywriteR extracts DNA copy number information from targeted sequencing
8987 by utilizing off-target reads. It allows for extracting uniformly distributed
8988 copy number information, can be used without reference, and can be applied to
8989 sequencing data obtained from various techniques including chromatin
8990 immunoprecipitation and target enrichment on small gene panels. Thereby,
8991 CopywriteR constitutes a widely applicable alternative to available copy
8992 number detection tools.")
8993 (license license:gpl2)))
8995 (define-public r-methylkit
8997 (name "r-methylkit")
9001 (uri (bioconductor-uri "methylKit" version))
9004 "1z687vpi5kwcqpnd6r74c5y72hcsbqlwg0bk95kksgpi81q710qj"))))
9005 (properties `((upstream-name . "methylKit")))
9006 (build-system r-build-system)
9008 `(("r-data-table" ,r-data-table)
9009 ("r-emdbook" ,r-emdbook)
9010 ("r-fastseg" ,r-fastseg)
9011 ("r-genomeinfodb" ,r-genomeinfodb)
9012 ("r-genomicranges" ,r-genomicranges)
9013 ("r-gtools" ,r-gtools)
9014 ("r-iranges" ,r-iranges)
9015 ("r-kernsmooth" ,r-kernsmooth)
9016 ("r-limma" ,r-limma)
9017 ("r-mclust" ,r-mclust)
9019 ("r-qvalue" ,r-qvalue)
9020 ("r-r-utils" ,r-r-utils)
9022 ("r-rhtslib" ,r-rhtslib)
9023 ("r-rsamtools" ,r-rsamtools)
9024 ("r-rtracklayer" ,r-rtracklayer)
9025 ("r-s4vectors" ,r-s4vectors)
9026 ("r-zlibbioc" ,r-zlibbioc)))
9029 (home-page "https://github.com/al2na/methylKit")
9031 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9033 "MethylKit is an R package for DNA methylation analysis and annotation
9034 from high-throughput bisulfite sequencing. The package is designed to deal
9035 with sequencing data from @dfn{Reduced representation bisulfite
9036 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9037 genome bisulfite sequencing. It also has functions to analyze base-pair
9038 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9040 (license license:artistic2.0)))
9042 (define-public r-sva
9049 (uri (bioconductor-uri "sva" version))
9052 "0jj6klfha5v5qmx2sjblf1an6s2zqd7mmgsp7sfmh4k2jpqi3jm9"))))
9053 (build-system r-build-system)
9055 `(("r-genefilter" ,r-genefilter)
9057 ("r-biocparallel" ,r-biocparallel)
9058 ("r-matrixstats" ,r-matrixstats)
9059 ("r-limma" ,r-limma)))
9060 (home-page "https://bioconductor.org/packages/sva")
9061 (synopsis "Surrogate variable analysis")
9063 "This package contains functions for removing batch effects and other
9064 unwanted variation in high-throughput experiment. It also contains functions
9065 for identifying and building surrogate variables for high-dimensional data
9066 sets. Surrogate variables are covariates constructed directly from
9067 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9068 imaging data that can be used in subsequent analyses to adjust for unknown,
9069 unmodeled, or latent sources of noise.")
9070 (license license:artistic2.0)))
9072 (define-public r-seqminer
9079 (uri (cran-uri "seqminer" version))
9082 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9083 (build-system r-build-system)
9086 (home-page "http://seqminer.genomic.codes")
9087 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9089 "This package provides tools to integrate nucleotide sequencing
9090 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9091 ;; Any version of the GPL is acceptable
9092 (license (list license:gpl2+ license:gpl3+))))
9094 (define-public r-raremetals2
9096 (name "r-raremetals2")
9101 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9102 "b/b7/RareMETALS2_" version ".tar.gz"))
9105 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9106 (properties `((upstream-name . "RareMETALS2")))
9107 (build-system r-build-system)
9109 `(("r-seqminer" ,r-seqminer)
9110 ("r-mvtnorm" ,r-mvtnorm)
9112 ("r-compquadform" ,r-compquadform)
9113 ("r-getopt" ,r-getopt)))
9114 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9115 (synopsis "Analyze gene-level association tests for binary trait")
9117 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9118 It was designed to meta-analyze gene-level association tests for binary trait.
9119 While rareMETALS offers a near-complete solution for meta-analysis of
9120 gene-level tests for quantitative trait, it does not offer the optimal
9121 solution for binary trait. The package rareMETALS2 offers improved features
9122 for analyzing gene-level association tests in meta-analyses for binary
9124 (license license:gpl3)))
9126 (define-public r-maldiquant
9128 (name "r-maldiquant")
9133 (uri (cran-uri "MALDIquant" version))
9136 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9137 (properties `((upstream-name . "MALDIquant")))
9138 (build-system r-build-system)
9139 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9140 (synopsis "Quantitative analysis of mass spectrometry data")
9142 "This package provides a complete analysis pipeline for matrix-assisted
9143 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9144 two-dimensional mass spectrometry data. In addition to commonly used plotting
9145 and processing methods it includes distinctive features, namely baseline
9146 subtraction methods such as morphological filters (TopHat) or the
9147 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9148 alignment using warping functions, handling of replicated measurements as well
9149 as allowing spectra with different resolutions.")
9150 (license license:gpl3+)))
9152 (define-public r-protgenerics
9154 (name "r-protgenerics")
9159 (uri (bioconductor-uri "ProtGenerics" version))
9162 "12jjwmg58b4xbivxlw4pffq0qfi2c1c5hyrci0sfyphrc99fvx0i"))))
9163 (properties `((upstream-name . "ProtGenerics")))
9164 (build-system r-build-system)
9165 (home-page "https://github.com/lgatto/ProtGenerics")
9166 (synopsis "S4 generic functions for proteomics infrastructure")
9168 "This package provides S4 generic functions needed by Bioconductor
9169 proteomics packages.")
9170 (license license:artistic2.0)))
9172 (define-public r-mzr
9179 (uri (bioconductor-uri "mzR" version))
9182 "1pr1pcrg3r3pccm5ag6l8ic6rpqbk9jnlb9mm7g4ak5jwrajbzjq"))
9183 (modules '((guix build utils)))
9186 (delete-file-recursively "src/boost")
9188 (properties `((upstream-name . "mzR")))
9189 (build-system r-build-system)
9192 (modify-phases %standard-phases
9193 (add-after 'unpack 'use-system-boost
9195 (substitute* "src/Makevars"
9196 (("\\./boost/libs.*") "")
9197 (("ARCH_OBJS=" line)
9199 "\nARCH_LIBS=-lboost_system -lboost_regex \
9200 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9203 `(;; Our default boost package won't work here, unfortunately, even with
9204 ;; mzR version 2.18.1.
9205 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9208 `(("r-biobase" ,r-biobase)
9209 ("r-biocgenerics" ,r-biocgenerics)
9210 ("r-ncdf4" ,r-ncdf4)
9211 ("r-protgenerics" ,r-protgenerics)
9213 ("r-rhdf5lib" ,r-rhdf5lib)
9214 ("r-zlibbioc" ,r-zlibbioc)))
9215 (home-page "https://github.com/sneumann/mzR/")
9216 (synopsis "Parser for mass spectrometry data files")
9218 "The mzR package provides a unified API to the common file formats and
9219 parsers available for mass spectrometry data. It comes with a wrapper for the
9220 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9221 The package contains the original code written by the ISB, and a subset of the
9222 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9223 previously been used in XCMS.")
9224 (license license:artistic2.0)))
9226 (define-public r-affyio
9233 (uri (bioconductor-uri "affyio" version))
9236 "1s78hm51fgac3i2j4bbdy0z6g14370154s6km8lldc9zpahx8b6p"))))
9237 (build-system r-build-system)
9239 `(("r-zlibbioc" ,r-zlibbioc)))
9242 (home-page "https://github.com/bmbolstad/affyio")
9243 (synopsis "Tools for parsing Affymetrix data files")
9245 "This package provides routines for parsing Affymetrix data files based
9246 upon file format information. The primary focus is on accessing the CEL and
9248 (license license:lgpl2.0+)))
9250 (define-public r-affy
9257 (uri (bioconductor-uri "affy" version))
9260 "05vz0vf3472s1ivfhc0gc8yz98y4rvvp7cf6kfbxhy1b23im1bgk"))))
9261 (build-system r-build-system)
9263 `(("r-affyio" ,r-affyio)
9264 ("r-biobase" ,r-biobase)
9265 ("r-biocgenerics" ,r-biocgenerics)
9266 ("r-biocmanager" ,r-biocmanager)
9267 ("r-preprocesscore" ,r-preprocesscore)
9268 ("r-zlibbioc" ,r-zlibbioc)))
9271 (home-page "https://bioconductor.org/packages/affy")
9272 (synopsis "Methods for affymetrix oligonucleotide arrays")
9274 "This package contains functions for exploratory oligonucleotide array
9276 (license license:lgpl2.0+)))
9278 (define-public r-vsn
9285 (uri (bioconductor-uri "vsn" version))
9288 "1vqmyxg06kgq9m3w6n0jykqm4jgsjw879r4s216wlcq4xc94dh1r"))))
9289 (build-system r-build-system)
9291 `(("r-affy" ,r-affy)
9292 ("r-biobase" ,r-biobase)
9293 ("r-ggplot2" ,r-ggplot2)
9294 ("r-lattice" ,r-lattice)
9295 ("r-limma" ,r-limma)))
9296 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9297 (synopsis "Variance stabilization and calibration for microarray data")
9299 "The package implements a method for normalising microarray intensities,
9300 and works for single- and multiple-color arrays. It can also be used for data
9301 from other technologies, as long as they have similar format. The method uses
9302 a robust variant of the maximum-likelihood estimator for an
9303 additive-multiplicative error model and affine calibration. The model
9304 incorporates data calibration step (a.k.a. normalization), a model for the
9305 dependence of the variance on the mean intensity and a variance stabilizing
9306 data transformation. Differences between transformed intensities are
9307 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9308 their variance is independent of the mean, and they are usually more sensitive
9309 and specific in detecting differential transcription.")
9310 (license license:artistic2.0)))
9312 (define-public r-mzid
9319 (uri (bioconductor-uri "mzID" version))
9322 "0vnyg7jlmy7ain7gmjwhqyqr664znrvrdlh7zd63563vhb87qarn"))))
9323 (properties `((upstream-name . "mzID")))
9324 (build-system r-build-system)
9326 `(("r-doparallel" ,r-doparallel)
9327 ("r-foreach" ,r-foreach)
9328 ("r-iterators" ,r-iterators)
9330 ("r-protgenerics" ,r-protgenerics)
9333 (home-page "https://bioconductor.org/packages/mzID")
9334 (synopsis "Parser for mzIdentML files")
9336 "This package provides a parser for mzIdentML files implemented using the
9337 XML package. The parser tries to be general and able to handle all types of
9338 mzIdentML files with the drawback of having less pretty output than a vendor
9340 (license license:gpl2+)))
9342 (define-public r-pcamethods
9344 (name "r-pcamethods")
9349 (uri (bioconductor-uri "pcaMethods" version))
9352 "0svf4n7l0afy4wwgs6x8x4dm330r3311l5vmsxw2f0r4axkh3bzk"))))
9353 (properties `((upstream-name . "pcaMethods")))
9354 (build-system r-build-system)
9356 `(("r-biobase" ,r-biobase)
9357 ("r-biocgenerics" ,r-biocgenerics)
9359 ("r-rcpp" ,r-rcpp)))
9360 (home-page "https://github.com/hredestig/pcamethods")
9361 (synopsis "Collection of PCA methods")
9363 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9364 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9365 for missing value estimation is included for comparison. BPCA, PPCA and
9366 NipalsPCA may be used to perform PCA on incomplete data as well as for
9367 accurate missing value estimation. A set of methods for printing and plotting
9368 the results is also provided. All PCA methods make use of the same data
9369 structure (pcaRes) to provide a common interface to the PCA results.")
9370 (license license:gpl3+)))
9372 (define-public r-msnbase
9379 (uri (bioconductor-uri "MSnbase" version))
9382 "0z63yqazkycq0zbbarq9ida6al35hv3g7g9g7s7bss4gh0hk7lhd"))))
9383 (properties `((upstream-name . "MSnbase")))
9384 (build-system r-build-system)
9386 `(("r-affy" ,r-affy)
9387 ("r-biobase" ,r-biobase)
9388 ("r-biocgenerics" ,r-biocgenerics)
9389 ("r-biocparallel" ,r-biocparallel)
9390 ("r-digest" ,r-digest)
9391 ("r-ggplot2" ,r-ggplot2)
9392 ("r-impute" ,r-impute)
9393 ("r-iranges" ,r-iranges)
9394 ("r-lattice" ,r-lattice)
9395 ("r-maldiquant" ,r-maldiquant)
9399 ("r-pcamethods" ,r-pcamethods)
9401 ("r-preprocesscore" ,r-preprocesscore)
9402 ("r-protgenerics" ,r-protgenerics)
9404 ("r-s4vectors" ,r-s4vectors)
9405 ("r-scales" ,r-scales)
9408 (home-page "https://github.com/lgatto/MSnbase")
9409 (synopsis "Base functions and classes for MS-based proteomics")
9411 "This package provides basic plotting, data manipulation and processing
9412 of mass spectrometry based proteomics data.")
9413 (license license:artistic2.0)))
9415 (define-public r-msnid
9422 (uri (bioconductor-uri "MSnID" version))
9425 "1n49l5mjdz7p4g2nwsbhm1jcj42sv6lsriq77n2imvacsvk0qfmb"))))
9426 (properties `((upstream-name . "MSnID")))
9427 (build-system r-build-system)
9429 `(("r-biobase" ,r-biobase)
9430 ("r-data-table" ,r-data-table)
9431 ("r-doparallel" ,r-doparallel)
9432 ("r-dplyr" ,r-dplyr)
9433 ("r-foreach" ,r-foreach)
9434 ("r-iterators" ,r-iterators)
9435 ("r-msnbase" ,r-msnbase)
9438 ("r-protgenerics" ,r-protgenerics)
9439 ("r-r-cache" ,r-r-cache)
9441 ("r-reshape2" ,r-reshape2)))
9442 (home-page "https://bioconductor.org/packages/MSnID")
9443 (synopsis "Utilities for LC-MSn proteomics identifications")
9445 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9446 from mzIdentML (leveraging the mzID package) or text files. After collating
9447 the search results from multiple datasets it assesses their identification
9448 quality and optimize filtering criteria to achieve the maximum number of
9449 identifications while not exceeding a specified false discovery rate. It also
9450 contains a number of utilities to explore the MS/MS results and assess missed
9451 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9452 (license license:artistic2.0)))
9454 (define-public r-seurat
9460 (uri (cran-uri "Seurat" version))
9463 "084lr2fjdksshsmv1ww82bgn3a9mml7kswsidjrs89snabgvn360"))))
9464 (properties `((upstream-name . "Seurat")))
9465 (build-system r-build-system)
9468 ("r-cluster" ,r-cluster)
9469 ("r-cowplot" ,r-cowplot)
9470 ("r-fitdistrplus" ,r-fitdistrplus)
9471 ("r-future" ,r-future)
9472 ("r-future-apply" ,r-future-apply)
9473 ("r-ggplot2" ,r-ggplot2)
9474 ("r-ggrepel" ,r-ggrepel)
9475 ("r-ggridges" ,r-ggridges)
9478 ("r-igraph" ,r-igraph)
9479 ("r-irlba" ,r-irlba)
9480 ("r-kernsmooth" ,r-kernsmooth)
9481 ("r-leiden" ,r-leiden)
9482 ("r-lmtest" ,r-lmtest)
9484 ("r-matrix" ,r-matrix)
9485 ("r-metap" ,r-metap)
9486 ("r-pbapply" ,r-pbapply)
9487 ("r-plotly" ,r-plotly)
9490 ("r-rcolorbrewer" ,r-rcolorbrewer)
9492 ("r-rcppannoy" ,r-rcppannoy)
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)
9504 ("r-uwot" ,r-uwot)))
9505 (home-page "http://www.satijalab.org/seurat")
9506 (synopsis "Seurat is an R toolkit for single cell genomics")
9508 "This package is an R package designed for QC, analysis, and
9509 exploration of single cell RNA-seq data. It easily enables widely-used
9510 analytical techniques, including the identification of highly variable genes,
9511 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9512 algorithms; density clustering, hierarchical clustering, k-means, and the
9513 discovery of differentially expressed genes and markers.")
9514 (license license:gpl3)))
9516 (define-public r-aroma-light
9518 (name "r-aroma-light")
9523 (uri (bioconductor-uri "aroma.light" version))
9526 "0a1prl4jhbqpa85i2vyia1ks9iippzl8np50fvm9wx8kbjxna5l6"))))
9527 (properties `((upstream-name . "aroma.light")))
9528 (build-system r-build-system)
9530 `(("r-matrixstats" ,r-matrixstats)
9531 ("r-r-methodss3" ,r-r-methodss3)
9533 ("r-r-utils" ,r-r-utils)))
9534 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9535 (synopsis "Methods for normalization and visualization of microarray data")
9537 "This package provides methods for microarray analysis that take basic
9538 data types such as matrices and lists of vectors. These methods can be used
9539 standalone, be utilized in other packages, or be wrapped up in higher-level
9541 (license license:gpl2+)))
9543 (define-public r-deseq
9550 (uri (bioconductor-uri "DESeq" version))
9553 "0jppqrikg9qfqcfw5qd3m5c7bag9g23bc0kcpk5zfkk1wv09mnlm"))))
9554 (properties `((upstream-name . "DESeq")))
9555 (build-system r-build-system)
9557 `(("r-biobase" ,r-biobase)
9558 ("r-biocgenerics" ,r-biocgenerics)
9559 ("r-genefilter" ,r-genefilter)
9560 ("r-geneplotter" ,r-geneplotter)
9561 ("r-lattice" ,r-lattice)
9562 ("r-locfit" ,r-locfit)
9564 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9565 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9566 (synopsis "Differential gene expression analysis")
9568 "This package provides tools for estimating variance-mean dependence in
9569 count data from high-throughput genetic sequencing assays and for testing for
9570 differential expression based on a model using the negative binomial
9572 (license license:gpl3+)))
9574 (define-public r-edaseq
9581 (uri (bioconductor-uri "EDASeq" version))
9584 "0mmc9bij17w4mfwcc566zbj5fvqgl8gfqs0qvj6ri4mbcql9jxb3"))))
9585 (properties `((upstream-name . "EDASeq")))
9586 (build-system r-build-system)
9588 `(("r-annotationdbi" ,r-annotationdbi)
9589 ("r-aroma-light" ,r-aroma-light)
9590 ("r-biobase" ,r-biobase)
9591 ("r-biocgenerics" ,r-biocgenerics)
9592 ("r-biocmanager" ,r-biocmanager)
9593 ("r-biomart" ,r-biomart)
9594 ("r-biostrings" ,r-biostrings)
9595 ("r-deseq" ,r-deseq)
9596 ("r-genomicfeatures" ,r-genomicfeatures)
9597 ("r-genomicranges" ,r-genomicranges)
9598 ("r-iranges" ,r-iranges)
9599 ("r-rsamtools" ,r-rsamtools)
9600 ("r-shortread" ,r-shortread)))
9601 (home-page "https://github.com/drisso/EDASeq")
9602 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9604 "This package provides support for numerical and graphical summaries of
9605 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9606 adjust for GC-content effect (or other gene-level effects) on read counts:
9607 loess robust local regression, global-scaling, and full-quantile
9608 normalization. Between-lane normalization procedures to adjust for
9609 distributional differences between lanes (e.g., sequencing depth):
9610 global-scaling and full-quantile normalization.")
9611 (license license:artistic2.0)))
9613 (define-public r-interactivedisplaybase
9615 (name "r-interactivedisplaybase")
9620 (uri (bioconductor-uri "interactiveDisplayBase" version))
9623 "1kkyv7hkygacmksvld9gs3ycf6wlblqcwi11nny0hq3l0ha265v5"))))
9625 `((upstream-name . "interactiveDisplayBase")))
9626 (build-system r-build-system)
9628 `(("r-biocgenerics" ,r-biocgenerics)
9629 ("r-shiny" ,r-shiny)))
9630 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9631 (synopsis "Base package for web displays of Bioconductor objects")
9633 "This package contains the basic methods needed to generate interactive
9634 Shiny-based display methods for Bioconductor objects.")
9635 (license license:artistic2.0)))
9637 (define-public r-annotationhub
9639 (name "r-annotationhub")
9644 (uri (bioconductor-uri "AnnotationHub" version))
9647 "0c773cmhng907839f0bq161jky7362lxxny36ac55qxiz1giqi8j"))))
9648 (properties `((upstream-name . "AnnotationHub")))
9649 (build-system r-build-system)
9651 `(("r-annotationdbi" ,r-annotationdbi)
9652 ("r-biocfilecache" ,r-biocfilecache)
9653 ("r-biocgenerics" ,r-biocgenerics)
9654 ("r-biocmanager" ,r-biocmanager)
9656 ("r-dplyr" ,r-dplyr)
9658 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9659 ("r-rappdirs" ,r-rappdirs)
9660 ("r-rsqlite" ,r-rsqlite)
9661 ("r-s4vectors" ,r-s4vectors)
9662 ("r-yaml" ,r-yaml)))
9663 (home-page "https://bioconductor.org/packages/AnnotationHub")
9664 (synopsis "Client to access AnnotationHub resources")
9666 "This package provides a client for the Bioconductor AnnotationHub web
9667 resource. The AnnotationHub web resource provides a central location where
9668 genomic files (e.g. VCF, bed, wig) and other resources from standard
9669 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9670 metadata about each resource, e.g., a textual description, tags, and date of
9671 modification. The client creates and manages a local cache of files retrieved
9672 by the user, helping with quick and reproducible access.")
9673 (license license:artistic2.0)))
9675 (define-public r-fastseg
9682 (uri (bioconductor-uri "fastseg" version))
9685 "03gggz29nf8kyy9clkifqr0xm8v0yb0kl0gjfb5c0vrjmwkfqvdf"))))
9686 (build-system r-build-system)
9688 `(("r-biobase" ,r-biobase)
9689 ("r-biocgenerics" ,r-biocgenerics)
9690 ("r-genomicranges" ,r-genomicranges)
9691 ("r-iranges" ,r-iranges)
9692 ("r-s4vectors" ,r-s4vectors)))
9693 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9694 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9696 "Fastseg implements a very fast and efficient segmentation algorithm.
9697 It can segment data from DNA microarrays and data from next generation
9698 sequencing for example to detect copy number segments. Further it can segment
9699 data from RNA microarrays like tiling arrays to identify transcripts. Most
9700 generally, it can segment data given as a matrix or as a vector. Various data
9701 formats can be used as input to fastseg like expression set objects for
9702 microarrays or GRanges for sequencing data.")
9703 (license license:lgpl2.0+)))
9705 (define-public r-keggrest
9712 (uri (bioconductor-uri "KEGGREST" version))
9715 "1yjrpbm5zfg0h3nb5gg06q2f19ydbhjqwi0jb6q3p8dyrgww9mqp"))))
9716 (properties `((upstream-name . "KEGGREST")))
9717 (build-system r-build-system)
9719 `(("r-biostrings" ,r-biostrings)
9722 (home-page "https://bioconductor.org/packages/KEGGREST")
9723 (synopsis "Client-side REST access to KEGG")
9725 "This package provides a package that provides a client interface to the
9726 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9727 (license license:artistic2.0)))
9729 (define-public r-gage
9736 (uri (bioconductor-uri "gage" version))
9739 "08d5yg7n4rx4xsginc8bx0sycpj06pi1k7i44ff757444p20srwq"))))
9740 (build-system r-build-system)
9742 `(("r-annotationdbi" ,r-annotationdbi)
9743 ("r-graph" ,r-graph)
9744 ("r-keggrest" ,r-keggrest)))
9745 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9746 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9748 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9749 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9750 data attributes including sample sizes, experimental designs, assay platforms,
9751 and other types of heterogeneity. The gage package provides functions for
9752 basic GAGE analysis, result processing and presentation. In addition, it
9753 provides demo microarray data and commonly used gene set data based on KEGG
9754 pathways and GO terms. These functions and data are also useful for gene set
9755 analysis using other methods.")
9756 (license license:gpl2+)))
9758 (define-public r-genomicfiles
9760 (name "r-genomicfiles")
9765 (uri (bioconductor-uri "GenomicFiles" version))
9768 "122g0yhpsm6fyvv38agp57clagl13h324rk06mlgb2xz104a1j4i"))))
9769 (properties `((upstream-name . "GenomicFiles")))
9770 (build-system r-build-system)
9772 `(("r-biocgenerics" ,r-biocgenerics)
9773 ("r-biocparallel" ,r-biocparallel)
9774 ("r-genomeinfodb" ,r-genomeinfodb)
9775 ("r-genomicalignments" ,r-genomicalignments)
9776 ("r-genomicranges" ,r-genomicranges)
9777 ("r-iranges" ,r-iranges)
9778 ("r-rsamtools" ,r-rsamtools)
9779 ("r-rtracklayer" ,r-rtracklayer)
9780 ("r-s4vectors" ,r-s4vectors)
9781 ("r-summarizedexperiment" ,r-summarizedexperiment)
9782 ("r-variantannotation" ,r-variantannotation)))
9783 (home-page "https://bioconductor.org/packages/GenomicFiles")
9784 (synopsis "Distributed computing by file or by range")
9786 "This package provides infrastructure for parallel computations
9787 distributed by file or by range. User defined mapper and reducer functions
9788 provide added flexibility for data combination and manipulation.")
9789 (license license:artistic2.0)))
9791 (define-public r-complexheatmap
9793 (name "r-complexheatmap")
9798 (uri (bioconductor-uri "ComplexHeatmap" version))
9801 "1imnb72r10csl2h12sckic7hcsb8v2z0y3dyw1ax2fpykmsmq776"))))
9803 `((upstream-name . "ComplexHeatmap")))
9804 (build-system r-build-system)
9806 `(("r-circlize" ,r-circlize)
9808 ("r-colorspace" ,r-colorspace)
9809 ("r-getoptlong" ,r-getoptlong)
9810 ("r-globaloptions" ,r-globaloptions)
9812 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9814 "https://github.com/jokergoo/ComplexHeatmap")
9815 (synopsis "Making Complex Heatmaps")
9817 "Complex heatmaps are efficient to visualize associations between
9818 different sources of data sets and reveal potential structures. This package
9819 provides a highly flexible way to arrange multiple heatmaps and supports
9820 self-defined annotation graphics.")
9821 (license license:gpl2+)))
9823 (define-public r-dirichletmultinomial
9825 (name "r-dirichletmultinomial")
9830 (uri (bioconductor-uri "DirichletMultinomial" version))
9833 "0qirvhnbv4wd50ln4pqbk4dj6h2935ipf9p4sw1x62qqhwxidqk4"))))
9835 `((upstream-name . "DirichletMultinomial")))
9836 (build-system r-build-system)
9840 `(("r-biocgenerics" ,r-biocgenerics)
9841 ("r-iranges" ,r-iranges)
9842 ("r-s4vectors" ,r-s4vectors)))
9843 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9844 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9846 "Dirichlet-multinomial mixture models can be used to describe variability
9847 in microbial metagenomic data. This package is an interface to code
9848 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9850 (license license:lgpl3)))
9852 (define-public r-ensembldb
9854 (name "r-ensembldb")
9859 (uri (bioconductor-uri "ensembldb" version))
9862 "09s5g9xm9m8mqvzk6pkp9fyhx3zyb4p8yziz49mhfji5n35nydjr"))))
9863 (build-system r-build-system)
9865 `(("r-annotationdbi" ,r-annotationdbi)
9866 ("r-annotationfilter" ,r-annotationfilter)
9867 ("r-biobase" ,r-biobase)
9868 ("r-biocgenerics" ,r-biocgenerics)
9869 ("r-biostrings" ,r-biostrings)
9872 ("r-genomeinfodb" ,r-genomeinfodb)
9873 ("r-genomicfeatures" ,r-genomicfeatures)
9874 ("r-genomicranges" ,r-genomicranges)
9875 ("r-iranges" ,r-iranges)
9876 ("r-protgenerics" ,r-protgenerics)
9877 ("r-rsamtools" ,r-rsamtools)
9878 ("r-rsqlite" ,r-rsqlite)
9879 ("r-rtracklayer" ,r-rtracklayer)
9880 ("r-s4vectors" ,r-s4vectors)))
9881 (home-page "https://github.com/jotsetung/ensembldb")
9882 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9884 "The package provides functions to create and use transcript-centric
9885 annotation databases/packages. The annotation for the databases are directly
9886 fetched from Ensembl using their Perl API. The functionality and data is
9887 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9888 but, in addition to retrieve all gene/transcript models and annotations from
9889 the database, the @code{ensembldb} package also provides a filter framework
9890 allowing to retrieve annotations for specific entries like genes encoded on a
9891 chromosome region or transcript models of lincRNA genes.")
9892 ;; No version specified
9893 (license license:lgpl3+)))
9895 (define-public r-organismdbi
9897 (name "r-organismdbi")
9902 (uri (bioconductor-uri "OrganismDbi" version))
9905 "14azk69pmwlhza0mhsxigsg127w3mgsx9hhrbdcdqmy3vzfbfaqq"))))
9906 (properties `((upstream-name . "OrganismDbi")))
9907 (build-system r-build-system)
9909 `(("r-annotationdbi" ,r-annotationdbi)
9910 ("r-biobase" ,r-biobase)
9911 ("r-biocgenerics" ,r-biocgenerics)
9912 ("r-biocmanager" ,r-biocmanager)
9914 ("r-genomicfeatures" ,r-genomicfeatures)
9915 ("r-genomicranges" ,r-genomicranges)
9916 ("r-graph" ,r-graph)
9917 ("r-iranges" ,r-iranges)
9919 ("r-s4vectors" ,r-s4vectors)))
9920 (home-page "https://bioconductor.org/packages/OrganismDbi")
9921 (synopsis "Software to enable the smooth interfacing of database packages")
9922 (description "The package enables a simple unified interface to several
9923 annotation packages each of which has its own schema by taking advantage of
9924 the fact that each of these packages implements a select methods.")
9925 (license license:artistic2.0)))
9927 (define-public r-biovizbase
9929 (name "r-biovizbase")
9934 (uri (bioconductor-uri "biovizBase" version))
9937 "1lba1801ak0a4vz6f8jffp9d525q27p0dhi2bp4f68mvdwwl2994"))))
9938 (properties `((upstream-name . "biovizBase")))
9939 (build-system r-build-system)
9941 `(("r-annotationdbi" ,r-annotationdbi)
9942 ("r-annotationfilter" ,r-annotationfilter)
9943 ("r-biocgenerics" ,r-biocgenerics)
9944 ("r-biostrings" ,r-biostrings)
9945 ("r-dichromat" ,r-dichromat)
9946 ("r-ensembldb" ,r-ensembldb)
9947 ("r-genomeinfodb" ,r-genomeinfodb)
9948 ("r-genomicalignments" ,r-genomicalignments)
9949 ("r-genomicfeatures" ,r-genomicfeatures)
9950 ("r-genomicranges" ,r-genomicranges)
9951 ("r-hmisc" ,r-hmisc)
9952 ("r-iranges" ,r-iranges)
9953 ("r-rcolorbrewer" ,r-rcolorbrewer)
9954 ("r-rlang" ,r-rlang)
9955 ("r-rsamtools" ,r-rsamtools)
9956 ("r-s4vectors" ,r-s4vectors)
9957 ("r-scales" ,r-scales)
9958 ("r-summarizedexperiment" ,r-summarizedexperiment)
9959 ("r-variantannotation" ,r-variantannotation)))
9960 (home-page "https://bioconductor.org/packages/biovizBase")
9961 (synopsis "Basic graphic utilities for visualization of genomic data")
9963 "The biovizBase package is designed to provide a set of utilities, color
9964 schemes and conventions for genomic data. It serves as the base for various
9965 high-level packages for biological data visualization. This saves development
9966 effort and encourages consistency.")
9967 (license license:artistic2.0)))
9969 (define-public r-ggbio
9976 (uri (bioconductor-uri "ggbio" version))
9979 "10s6hnffnrrsx3896adqdc5g55fzd5y6qhnp1mq0c641nw833rwd"))))
9980 (build-system r-build-system)
9983 (modify-phases %standard-phases
9984 ;; See https://github.com/tengfei/ggbio/issues/117
9985 ;; This fix will be included in the next release.
9986 (add-after 'unpack 'fix-typo
9988 (substitute* "R/GGbio-class.R"
9989 (("fechable") "fetchable"))
9992 `(("r-annotationdbi" ,r-annotationdbi)
9993 ("r-annotationfilter" ,r-annotationfilter)
9994 ("r-biobase" ,r-biobase)
9995 ("r-biocgenerics" ,r-biocgenerics)
9996 ("r-biostrings" ,r-biostrings)
9997 ("r-biovizbase" ,r-biovizbase)
9998 ("r-bsgenome" ,r-bsgenome)
9999 ("r-ensembldb" ,r-ensembldb)
10000 ("r-genomeinfodb" ,r-genomeinfodb)
10001 ("r-genomicalignments" ,r-genomicalignments)
10002 ("r-genomicfeatures" ,r-genomicfeatures)
10003 ("r-genomicranges" ,r-genomicranges)
10004 ("r-ggally" ,r-ggally)
10005 ("r-ggplot2" ,r-ggplot2)
10006 ("r-gridextra" ,r-gridextra)
10007 ("r-gtable" ,r-gtable)
10008 ("r-hmisc" ,r-hmisc)
10009 ("r-iranges" ,r-iranges)
10010 ("r-organismdbi" ,r-organismdbi)
10011 ("r-reshape2" ,r-reshape2)
10012 ("r-rlang" ,r-rlang)
10013 ("r-rsamtools" ,r-rsamtools)
10014 ("r-rtracklayer" ,r-rtracklayer)
10015 ("r-s4vectors" ,r-s4vectors)
10016 ("r-scales" ,r-scales)
10017 ("r-summarizedexperiment" ,r-summarizedexperiment)
10018 ("r-variantannotation" ,r-variantannotation)))
10019 (home-page "http://www.tengfei.name/ggbio/")
10020 (synopsis "Visualization tools for genomic data")
10022 "The ggbio package extends and specializes the grammar of graphics for
10023 biological data. The graphics are designed to answer common scientific
10024 questions, in particular those often asked of high throughput genomics data.
10025 All core Bioconductor data structures are supported, where appropriate. The
10026 package supports detailed views of particular genomic regions, as well as
10027 genome-wide overviews. Supported overviews include ideograms and grand linear
10028 views. High-level plots include sequence fragment length, edge-linked
10029 interval to data view, mismatch pileup, and several splicing summaries.")
10030 (license license:artistic2.0)))
10032 (define-public r-gprofiler
10034 (name "r-gprofiler")
10039 (uri (cran-uri "gProfileR" version))
10042 "05d6y6b7vkkzp2qhs1cwlvp02djij1b28dbwxnrms08f8qi35iaj"))))
10043 (properties `((upstream-name . "gProfileR")))
10044 (build-system r-build-system)
10046 `(("r-plyr" ,r-plyr)
10047 ("r-rcurl" ,r-rcurl)))
10048 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10049 (synopsis "Interface to the g:Profiler toolkit")
10051 "This package provides tools for functional enrichment analysis,
10052 gene identifier conversion and mapping homologous genes across related
10053 organisms via the @code{g:Profiler} toolkit.")
10054 (license license:gpl2+)))
10056 (define-public r-gqtlbase
10058 (name "r-gqtlbase")
10063 (uri (bioconductor-uri "gQTLBase" version))
10066 "1n2cizb88g2ankngvhxv377gizg80y3fhlx67sgm0z4ilm6a30ql"))))
10067 (properties `((upstream-name . "gQTLBase")))
10068 (build-system r-build-system)
10070 `(("r-batchjobs" ,r-batchjobs)
10071 ("r-bbmisc" ,r-bbmisc)
10072 ("r-biocgenerics" ,r-biocgenerics)
10074 ("r-doparallel" ,r-doparallel)
10076 ("r-ffbase" ,r-ffbase)
10077 ("r-foreach" ,r-foreach)
10078 ("r-genomicfiles" ,r-genomicfiles)
10079 ("r-genomicranges" ,r-genomicranges)
10080 ("r-rtracklayer" ,r-rtracklayer)
10081 ("r-s4vectors" ,r-s4vectors)
10082 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10083 (home-page "https://bioconductor.org/packages/gQTLBase")
10084 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10086 "The purpose of this package is to simplify the storage and interrogation
10087 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10089 (license license:artistic2.0)))
10091 (define-public r-snpstats
10093 (name "r-snpstats")
10098 (uri (bioconductor-uri "snpStats" version))
10101 "0drfd24a5pkrhzmpidlh717bgh2dm68mpn6vj1vlpkilfbkifl34"))))
10102 (properties `((upstream-name . "snpStats")))
10103 (build-system r-build-system)
10104 (inputs `(("zlib" ,zlib)))
10106 `(("r-biocgenerics" ,r-biocgenerics)
10107 ("r-matrix" ,r-matrix)
10108 ("r-survival" ,r-survival)
10109 ("r-zlibbioc" ,r-zlibbioc)))
10110 (home-page "https://bioconductor.org/packages/snpStats")
10111 (synopsis "Methods for SNP association studies")
10113 "This package provides classes and statistical methods for large
10114 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10115 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10116 (license license:gpl3)))
10118 (define-public r-homo-sapiens
10120 (name "r-homo-sapiens")
10124 ;; We cannot use bioconductor-uri here because this tarball is
10125 ;; located under "data/annotation/" instead of "bioc/".
10126 (uri (string-append "http://www.bioconductor.org/packages/"
10127 "release/data/annotation/src/contrib/"
10129 version ".tar.gz"))
10132 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10134 `((upstream-name . "Homo.sapiens")))
10135 (build-system r-build-system)
10137 `(("r-genomicfeatures" ,r-genomicfeatures)
10138 ("r-go-db" ,r-go-db)
10139 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10140 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10141 ("r-organismdbi" ,r-organismdbi)
10142 ("r-annotationdbi" ,r-annotationdbi)))
10143 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10144 (synopsis "Annotation package for the Homo.sapiens object")
10146 "This package contains the Homo.sapiens object to access data from
10147 several related annotation packages.")
10148 (license license:artistic2.0)))
10150 (define-public r-erma
10157 (uri (bioconductor-uri "erma" version))
10160 "0j7ggp63m5y88cxgi49vcql1s1avzifwvvd2hydj4lj3yrmzib48"))))
10161 (build-system r-build-system)
10163 `(("r-annotationdbi" ,r-annotationdbi)
10164 ("r-biobase" ,r-biobase)
10165 ("r-biocgenerics" ,r-biocgenerics)
10166 ("r-biocparallel" ,r-biocparallel)
10167 ("r-genomeinfodb" ,r-genomeinfodb)
10168 ("r-genomicfiles" ,r-genomicfiles)
10169 ("r-genomicranges" ,r-genomicranges)
10170 ("r-ggplot2" ,r-ggplot2)
10171 ("r-homo-sapiens" ,r-homo-sapiens)
10172 ("r-iranges" ,r-iranges)
10173 ("r-rtracklayer" ,r-rtracklayer)
10174 ("r-s4vectors" ,r-s4vectors)
10175 ("r-shiny" ,r-shiny)
10176 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10177 (home-page "https://bioconductor.org/packages/erma")
10178 (synopsis "Epigenomic road map adventures")
10180 "The epigenomics road map describes locations of epigenetic marks in DNA
10181 from a variety of cell types. Of interest are locations of histone
10182 modifications, sites of DNA methylation, and regions of accessible chromatin.
10183 This package presents a selection of elements of the road map including
10184 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10185 by Ernst and Kellis.")
10186 (license license:artistic2.0)))
10188 (define-public r-ldblock
10195 (uri (bioconductor-uri "ldblock" version))
10198 "0xx04cghx6ads1ackwnw3z0gf72qv461nznzmcnkgmp7w5n9m2af"))))
10199 (build-system r-build-system)
10201 `(("r-biocgenerics" ,r-biocgenerics)
10202 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10203 ("r-ensembldb" ,r-ensembldb)
10204 ("r-genomeinfodb" ,r-genomeinfodb)
10205 ("r-genomicfiles" ,r-genomicfiles)
10206 ("r-go-db" ,r-go-db)
10207 ("r-homo-sapiens" ,r-homo-sapiens)
10209 ("r-matrix" ,r-matrix)
10210 ("r-rsamtools" ,r-rsamtools)
10211 ("r-snpstats" ,r-snpstats)
10212 ("r-variantannotation" ,r-variantannotation)))
10213 (home-page "https://bioconductor.org/packages/ldblock")
10214 (synopsis "Data structures for linkage disequilibrium measures in populations")
10216 "This package defines data structures for @dfn{linkage
10217 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10218 handling of existing population-level data for the purpose of flexibly
10219 defining LD blocks.")
10220 (license license:artistic2.0)))
10222 (define-public r-gqtlstats
10224 (name "r-gqtlstats")
10229 (uri (bioconductor-uri "gQTLstats" version))
10232 "17xadfn8qh1pwzlpcbds5wrjr9bzhsnmv90wffxmp02hq20qkrh5"))))
10233 (properties `((upstream-name . "gQTLstats")))
10234 (build-system r-build-system)
10236 `(("r-annotationdbi" ,r-annotationdbi)
10237 ("r-batchjobs" ,r-batchjobs)
10238 ("r-bbmisc" ,r-bbmisc)
10239 ("r-beeswarm" ,r-beeswarm)
10240 ("r-biobase" ,r-biobase)
10241 ("r-biocgenerics" ,r-biocgenerics)
10242 ("r-doparallel" ,r-doparallel)
10243 ("r-dplyr" ,r-dplyr)
10245 ("r-ffbase" ,r-ffbase)
10246 ("r-foreach" ,r-foreach)
10247 ("r-genomeinfodb" ,r-genomeinfodb)
10248 ("r-genomicfeatures" ,r-genomicfeatures)
10249 ("r-genomicfiles" ,r-genomicfiles)
10250 ("r-genomicranges" ,r-genomicranges)
10251 ("r-ggbeeswarm" ,r-ggbeeswarm)
10252 ("r-ggplot2" ,r-ggplot2)
10253 ("r-gqtlbase" ,r-gqtlbase)
10254 ("r-hardyweinberg" ,r-hardyweinberg)
10255 ("r-homo-sapiens" ,r-homo-sapiens)
10256 ("r-iranges" ,r-iranges)
10257 ("r-limma" ,r-limma)
10259 ("r-plotly" ,r-plotly)
10260 ("r-reshape2" ,r-reshape2)
10261 ("r-s4vectors" ,r-s4vectors)
10262 ("r-shiny" ,r-shiny)
10263 ("r-snpstats" ,r-snpstats)
10264 ("r-summarizedexperiment" ,r-summarizedexperiment)
10265 ("r-variantannotation" ,r-variantannotation)))
10266 (home-page "https://bioconductor.org/packages/gQTLstats")
10267 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10269 "This package provides tools for the computationally efficient analysis
10270 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10271 The software in this package aims to support refinements and functional
10272 interpretation of members of a collection of association statistics on a
10273 family of feature/genome hypotheses.")
10274 (license license:artistic2.0)))
10276 (define-public r-gviz
10283 (uri (bioconductor-uri "Gviz" version))
10286 "0347r1ly0vzpilflzbyzsjdf4cday294lw3fxzx61clblrmws1ki"))))
10287 (properties `((upstream-name . "Gviz")))
10288 (build-system r-build-system)
10290 `(("r-annotationdbi" ,r-annotationdbi)
10291 ("r-biobase" ,r-biobase)
10292 ("r-biocgenerics" ,r-biocgenerics)
10293 ("r-biomart" ,r-biomart)
10294 ("r-biostrings" ,r-biostrings)
10295 ("r-biovizbase" ,r-biovizbase)
10296 ("r-bsgenome" ,r-bsgenome)
10297 ("r-digest" ,r-digest)
10298 ("r-genomeinfodb" ,r-genomeinfodb)
10299 ("r-genomicalignments" ,r-genomicalignments)
10300 ("r-genomicfeatures" ,r-genomicfeatures)
10301 ("r-genomicranges" ,r-genomicranges)
10302 ("r-iranges" ,r-iranges)
10303 ("r-lattice" ,r-lattice)
10304 ("r-latticeextra" ,r-latticeextra)
10305 ("r-matrixstats" ,r-matrixstats)
10306 ("r-rcolorbrewer" ,r-rcolorbrewer)
10307 ("r-rsamtools" ,r-rsamtools)
10308 ("r-rtracklayer" ,r-rtracklayer)
10309 ("r-s4vectors" ,r-s4vectors)
10310 ("r-xvector" ,r-xvector)))
10311 (home-page "https://bioconductor.org/packages/Gviz")
10312 (synopsis "Plotting data and annotation information along genomic coordinates")
10314 "Genomic data analyses requires integrated visualization of known genomic
10315 information and new experimental data. Gviz uses the biomaRt and the
10316 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10317 and translates this to e.g. gene/transcript structures in viewports of the
10318 grid graphics package. This results in genomic information plotted together
10320 (license license:artistic2.0)))
10322 (define-public r-gwascat
10329 (uri (bioconductor-uri "gwascat" version))
10332 "0akb36mrybmxbb1bc9kgxbnj3cdypfylj3yzrmhjwqxml03mg61i"))))
10333 (build-system r-build-system)
10335 `(("r-annotationdbi" ,r-annotationdbi)
10336 ("r-biocgenerics" ,r-biocgenerics)
10337 ("r-biostrings" ,r-biostrings)
10338 ("r-genomeinfodb" ,r-genomeinfodb)
10339 ("r-genomicfeatures" ,r-genomicfeatures)
10340 ("r-genomicranges" ,r-genomicranges)
10341 ("r-homo-sapiens" ,r-homo-sapiens)
10342 ("r-iranges" ,r-iranges)
10343 ("r-rsamtools" ,r-rsamtools)
10344 ("r-rtracklayer" ,r-rtracklayer)
10345 ("r-s4vectors" ,r-s4vectors)))
10346 (home-page "https://bioconductor.org/packages/gwascat")
10347 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10349 "This package provides tools for representing and modeling data in the
10350 EMBL-EBI GWAS catalog.")
10351 (license license:artistic2.0)))
10353 (define-public r-sushi
10359 (uri (bioconductor-uri "Sushi" version))
10362 "1hgh3jfcx0bh3fyvp85v7435hvsk3ah1hxx5117ss93v03iwjf1g"))))
10363 (properties `((upstream-name . "Sushi")))
10364 (build-system r-build-system)
10366 `(("r-biomart" ,r-biomart)
10368 (home-page "https://bioconductor.org/packages/Sushi")
10369 (synopsis "Tools for visualizing genomics data")
10371 "This package provides flexible, quantitative, and integrative genomic
10372 visualizations for publication-quality multi-panel figures.")
10373 (license license:gpl2+)))
10375 (define-public r-fithic
10381 (uri (bioconductor-uri "FitHiC" version))
10384 "1qrxy4v8vmykrk8y6g3bs5wh5xhbs6pxyydbxy3vnj2mjirnxr6d"))))
10385 (properties `((upstream-name . "FitHiC")))
10386 (build-system r-build-system)
10388 `(("r-data-table" ,r-data-table)
10389 ("r-fdrtool" ,r-fdrtool)
10390 ("r-rcpp" ,r-rcpp)))
10391 (home-page "https://bioconductor.org/packages/FitHiC")
10392 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10394 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10395 intra-chromosomal contact maps produced by genome-wide genome architecture
10396 assays such as Hi-C.")
10397 (license license:gpl2+)))
10399 (define-public r-hitc
10405 (uri (bioconductor-uri "HiTC" version))
10408 "059a1xxv2kb0bb32flymg2s8ylhavnv3j8l4125rfidagcgxgzjq"))))
10409 (properties `((upstream-name . "HiTC")))
10410 (build-system r-build-system)
10412 `(("r-biostrings" ,r-biostrings)
10413 ("r-genomeinfodb" ,r-genomeinfodb)
10414 ("r-genomicranges" ,r-genomicranges)
10415 ("r-iranges" ,r-iranges)
10416 ("r-matrix" ,r-matrix)
10417 ("r-rcolorbrewer" ,r-rcolorbrewer)
10418 ("r-rtracklayer" ,r-rtracklayer)))
10419 (home-page "https://bioconductor.org/packages/HiTC")
10420 (synopsis "High throughput chromosome conformation capture analysis")
10422 "The HiTC package was developed to explore high-throughput \"C\" data
10423 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10424 quality controls, normalization, visualization, and further analysis are also
10426 (license license:artistic2.0)))
10428 (define-public r-hdf5array
10430 (name "r-hdf5array")
10435 (uri (bioconductor-uri "HDF5Array" version))
10438 "0afradisrr5gn0lf2kxjw55vdm3lm9mlgx53qlr9r40c1hrydpf5"))))
10439 (properties `((upstream-name . "HDF5Array")))
10440 (build-system r-build-system)
10444 `(("r-biocgenerics" ,r-biocgenerics)
10445 ("r-delayedarray" ,r-delayedarray)
10446 ("r-iranges" ,r-iranges)
10447 ("r-rhdf5" ,r-rhdf5)
10448 ("r-rhdf5lib" ,r-rhdf5lib)
10449 ("r-s4vectors" ,r-s4vectors)))
10450 (home-page "https://bioconductor.org/packages/HDF5Array")
10451 (synopsis "HDF5 back end for DelayedArray objects")
10452 (description "This package provides an array-like container for convenient
10453 access and manipulation of HDF5 datasets. It supports delayed operations and
10454 block processing.")
10455 (license license:artistic2.0)))
10457 (define-public r-rhdf5lib
10459 (name "r-rhdf5lib")
10464 (uri (bioconductor-uri "Rhdf5lib" version))
10467 "0niz9dh66fcwbvqpkpsdlz9d06kwi3kfh45dhk3qz9g9qqyiakr1"))
10468 (modules '((guix build utils)))
10471 ;; Delete bundled binaries
10472 (delete-file-recursively "src/winlib/")
10474 (properties `((upstream-name . "Rhdf5lib")))
10475 (build-system r-build-system)
10478 (modify-phases %standard-phases
10479 (add-after 'unpack 'do-not-use-bundled-hdf5
10480 (lambda* (#:key inputs #:allow-other-keys)
10481 (for-each delete-file '("configure" "configure.ac"))
10482 ;; Do not make other packages link with the proprietary libsz.
10483 (substitute* "R/zzz.R"
10484 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10485 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10486 (("'%s/libhdf5.a %s/libsz.a -lz'")
10487 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10488 (with-directory-excursion "src"
10489 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10490 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10492 ;; Remove timestamp and host system information to make
10493 ;; the build reproducible.
10494 (substitute* "hdf5/src/libhdf5.settings.in"
10495 (("Configured on: @CONFIG_DATE@")
10496 "Configured on: Guix")
10497 (("Uname information:.*")
10498 "Uname information: Linux\n")
10499 ;; Remove unnecessary store reference.
10501 "C Compiler: GCC\n"))
10502 (rename-file "Makevars.in" "Makevars")
10503 (substitute* "Makevars"
10504 (("HDF5_CXX_LIB=.*")
10505 (string-append "HDF5_CXX_LIB="
10506 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10508 (string-append "HDF5_LIB="
10509 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10510 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10511 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10512 ;; szip is non-free software
10513 (("cp \\$\\{SZIP_LIB\\}.*") "")
10514 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10519 `(("hdf5" ,hdf5-1.10)))
10521 `(("hdf5-source" ,(package-source hdf5-1.10))))
10522 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10523 (synopsis "HDF5 library as an R package")
10524 (description "This package provides C and C++ HDF5 libraries for use in R
10526 (license license:artistic2.0)))
10528 (define-public r-beachmat
10530 (name "r-beachmat")
10535 (uri (bioconductor-uri "beachmat" version))
10538 "14cz19fw97s8mhm9r2n5li44vckx069k8nqsyy64c3lkfm4vy4zx"))))
10539 (build-system r-build-system)
10541 `(("r-biocgenerics" ,r-biocgenerics)
10542 ("r-delayedarray" ,r-delayedarray)))
10543 (home-page "https://bioconductor.org/packages/beachmat")
10544 (synopsis "Compiling Bioconductor to handle each matrix type")
10545 (description "This package provides a consistent C++ class interface for a
10546 variety of commonly used matrix types, including sparse and HDF5-backed
10548 (license license:gpl3)))
10550 (define-public r-singlecellexperiment
10552 (name "r-singlecellexperiment")
10557 (uri (bioconductor-uri "SingleCellExperiment" version))
10560 "0m3yjnv1njb4gyzcjfk7a0lz2vgggp2wjz382gqrb0qhhwcgfkj5"))))
10562 `((upstream-name . "SingleCellExperiment")))
10563 (build-system r-build-system)
10565 `(("r-biocgenerics" ,r-biocgenerics)
10566 ("r-s4vectors" ,r-s4vectors)
10567 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10568 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10569 (synopsis "S4 classes for single cell data")
10570 (description "This package defines an S4 class for storing data from
10571 single-cell experiments. This includes specialized methods to store and
10572 retrieve spike-in information, dimensionality reduction coordinates and size
10573 factors for each cell, along with the usual metadata for genes and
10575 (license license:gpl3)))
10577 (define-public r-scater
10583 (uri (bioconductor-uri "scater" version))
10586 "16a17161xlhh6qpna9qxph3anlc7ydgyrczmy4alfiw8si7pzmxa"))))
10587 (build-system r-build-system)
10589 `(("r-beachmat" ,r-beachmat)
10590 ("r-biocgenerics" ,r-biocgenerics)
10591 ("r-biocneighbors" ,r-biocneighbors)
10592 ("r-biocparallel" ,r-biocparallel)
10593 ("r-biocsingular" ,r-biocsingular)
10594 ("r-delayedarray" ,r-delayedarray)
10595 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10596 ("r-dplyr" ,r-dplyr)
10597 ("r-ggbeeswarm" ,r-ggbeeswarm)
10598 ("r-ggplot2" ,r-ggplot2)
10599 ("r-matrix" ,r-matrix)
10601 ("r-s4vectors" ,r-s4vectors)
10602 ("r-singlecellexperiment" ,r-singlecellexperiment)
10603 ("r-summarizedexperiment" ,r-summarizedexperiment)
10604 ("r-viridis" ,r-viridis)))
10605 (home-page "https://github.com/davismcc/scater")
10606 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10607 (description "This package provides a collection of tools for doing
10608 various analyses of single-cell RNA-seq gene expression data, with a focus on
10610 (license license:gpl2+)))
10612 (define-public r-scran
10619 (uri (bioconductor-uri "scran" version))
10622 "17mknpkvs7mgnlbf2hv9k7rwbx2vlg60yrwfyb8nn3nxsb6vm7yn"))))
10623 (build-system r-build-system)
10625 `(("r-beachmat" ,r-beachmat)
10627 ("r-biocgenerics" ,r-biocgenerics)
10628 ("r-biocneighbors" ,r-biocneighbors)
10629 ("r-biocparallel" ,r-biocparallel)
10630 ("r-biocsingular" ,r-biocsingular)
10631 ("r-delayedarray" ,r-delayedarray)
10632 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10633 ("r-dqrng" ,r-dqrng)
10634 ("r-dynamictreecut" ,r-dynamictreecut)
10635 ("r-edger" ,r-edger)
10636 ("r-igraph" ,r-igraph)
10637 ("r-limma" ,r-limma)
10638 ("r-matrix" ,r-matrix)
10640 ("r-s4vectors" ,r-s4vectors)
10641 ("r-scater" ,r-scater)
10642 ("r-singlecellexperiment" ,r-singlecellexperiment)
10643 ("r-statmod" ,r-statmod)
10644 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10645 (home-page "https://bioconductor.org/packages/scran")
10646 (synopsis "Methods for single-cell RNA-Seq data analysis")
10647 (description "This package implements a variety of low-level analyses of
10648 single-cell RNA-seq data. Methods are provided for normalization of
10649 cell-specific biases, assignment of cell cycle phase, and detection of highly
10650 variable and significantly correlated genes.")
10651 (license license:gpl3)))
10653 (define-public r-delayedmatrixstats
10655 (name "r-delayedmatrixstats")
10660 (uri (bioconductor-uri "DelayedMatrixStats" version))
10663 "1riyzfsq4bd513hidkw3cfkx3jywk3x87j89q70v459xsdfdc95b"))))
10665 `((upstream-name . "DelayedMatrixStats")))
10666 (build-system r-build-system)
10668 `(("r-biocparallel" ,r-biocparallel)
10669 ("r-delayedarray" ,r-delayedarray)
10670 ("r-hdf5array" ,r-hdf5array)
10671 ("r-iranges" ,r-iranges)
10672 ("r-matrix" ,r-matrix)
10673 ("r-matrixstats" ,r-matrixstats)
10674 ("r-s4vectors" ,r-s4vectors)))
10675 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10676 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10678 "This package provides a port of the @code{matrixStats} API for use with
10679 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10680 contains high-performing functions operating on rows and columns of
10681 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10682 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10683 are optimized per data type and for subsetted calculations such that both
10684 memory usage and processing time is minimized.")
10685 (license license:expat)))
10687 (define-public r-phangorn
10689 (name "r-phangorn")
10694 (uri (cran-uri "phangorn" version))
10697 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
10698 (build-system r-build-system)
10701 ("r-fastmatch" ,r-fastmatch)
10702 ("r-igraph" ,r-igraph)
10703 ("r-magrittr" ,r-magrittr)
10704 ("r-matrix" ,r-matrix)
10705 ("r-quadprog" ,r-quadprog)
10706 ("r-rcpp" ,r-rcpp)))
10707 (home-page "https://github.com/KlausVigo/phangorn")
10708 (synopsis "Phylogenetic analysis in R")
10710 "Phangorn is a package for phylogenetic analysis in R. It supports
10711 estimation of phylogenetic trees and networks using Maximum Likelihood,
10712 Maximum Parsimony, distance methods and Hadamard conjugation.")
10713 (license license:gpl2+)))
10715 (define-public r-dropbead
10716 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10719 (name "r-dropbead")
10720 (version (string-append "0-" revision "." (string-take commit 7)))
10724 (uri (git-reference
10725 (url "https://github.com/rajewsky-lab/dropbead.git")
10727 (file-name (git-file-name name version))
10730 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10731 (build-system r-build-system)
10733 `(("r-ggplot2" ,r-ggplot2)
10734 ("r-rcolorbrewer" ,r-rcolorbrewer)
10735 ("r-gridextra" ,r-gridextra)
10736 ("r-gplots" ,r-gplots)
10737 ("r-plyr" ,r-plyr)))
10738 (home-page "https://github.com/rajewsky-lab/dropbead")
10739 (synopsis "Basic exploration and analysis of Drop-seq data")
10740 (description "This package offers a quick and straight-forward way to
10741 explore and perform basic analysis of single cell sequencing data coming from
10742 droplet sequencing. It has been particularly tailored for Drop-seq.")
10743 (license license:gpl3))))
10745 (define htslib-for-sambamba
10746 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10749 (name "htslib-for-sambamba")
10750 (version (string-append "1.3.1-1." (string-take commit 9)))
10754 (uri (git-reference
10755 (url "https://github.com/lomereiter/htslib.git")
10757 (file-name (string-append "htslib-" version "-checkout"))
10760 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10762 `(("autoconf" ,autoconf)
10763 ("automake" ,automake)
10764 ,@(package-native-inputs htslib))))))
10766 (define-public sambamba
10773 (uri (git-reference
10774 (url "https://github.com/lomereiter/sambamba.git")
10775 (commit (string-append "v" version))))
10776 (file-name (string-append name "-" version "-checkout"))
10779 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10780 (build-system gnu-build-system)
10782 `(#:tests? #f ; there is no test target
10783 #:parallel-build? #f ; not supported
10785 (modify-phases %standard-phases
10786 (delete 'configure)
10787 (add-after 'unpack 'fix-ldc-version
10789 (substitute* "gen_ldc_version_info.py"
10790 (("/usr/bin/env.*") (which "python3")))
10791 (substitute* "Makefile"
10792 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10793 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10795 (add-after 'unpack 'place-biod-and-undead
10796 (lambda* (#:key inputs #:allow-other-keys)
10797 (copy-recursively (assoc-ref inputs "biod") "BioD")
10798 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10800 (add-after 'unpack 'unbundle-prerequisites
10802 (substitute* "Makefile"
10803 (("htslib/libhts.a lz4/lib/liblz4.a")
10805 ((" lz4-static htslib-static") ""))
10808 (lambda* (#:key outputs #:allow-other-keys)
10809 (let* ((out (assoc-ref outputs "out"))
10810 (bin (string-append out "/bin")))
10812 (install-file "bin/sambamba" bin)
10819 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10822 (uri (git-reference
10823 (url "https://github.com/biod/BioD.git")
10825 (file-name (string-append "biod-"
10826 (string-take commit 9)
10830 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10832 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10835 (uri (git-reference
10836 (url "https://github.com/biod/undeaD.git")
10838 (file-name (string-append "undead-"
10839 (string-take commit 9)
10843 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10846 ("htslib" ,htslib-for-sambamba)))
10847 (home-page "http://lomereiter.github.io/sambamba")
10848 (synopsis "Tools for working with SAM/BAM data")
10849 (description "Sambamba is a high performance modern robust and
10850 fast tool (and library), written in the D programming language, for
10851 working with SAM and BAM files. Current parallelised functionality is
10852 an important subset of samtools functionality, including view, index,
10853 sort, markdup, and depth.")
10854 (license license:gpl2+)))
10856 (define-public ritornello
10858 (name "ritornello")
10862 (uri (git-reference
10863 (url "https://github.com/KlugerLab/Ritornello.git")
10864 (commit (string-append "v" version))))
10865 (file-name (git-file-name name version))
10868 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10869 (build-system gnu-build-system)
10871 `(#:tests? #f ; there are no tests
10873 (modify-phases %standard-phases
10874 (add-after 'unpack 'patch-samtools-references
10875 (lambda* (#:key inputs #:allow-other-keys)
10876 (substitute* '("src/SamStream.h"
10878 (("<sam.h>") "<samtools/sam.h>"))
10880 (delete 'configure)
10882 (lambda* (#:key inputs outputs #:allow-other-keys)
10883 (let* ((out (assoc-ref outputs "out"))
10884 (bin (string-append out "/bin/")))
10886 (install-file "bin/Ritornello" bin)
10889 `(("samtools" ,samtools-0.1)
10893 (home-page "https://github.com/KlugerLab/Ritornello")
10894 (synopsis "Control-free peak caller for ChIP-seq data")
10895 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10896 signal processing that can accurately call binding events without the need to
10897 do a pair total DNA input or IgG control sample. It has been tested for use
10898 with narrow binding events such as transcription factor ChIP-seq.")
10899 (license license:gpl3+)))
10901 (define-public trim-galore
10903 (name "trim-galore")
10908 (uri (git-reference
10909 (url "https://github.com/FelixKrueger/TrimGalore.git")
10911 (file-name (git-file-name name version))
10914 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
10915 (build-system gnu-build-system)
10917 `(#:tests? #f ; no tests
10919 (modify-phases %standard-phases
10920 (replace 'configure
10922 ;; Trim Galore tries to figure out what version of Python
10923 ;; cutadapt is using by looking at the shebang. Of course that
10924 ;; doesn't work, because cutadapt is wrapped in a shell script.
10925 (substitute* "trim_galore"
10926 (("my \\$python_return.*")
10927 "my $python_return = \"Python 3.999\";\n"))
10930 (add-after 'unpack 'hardcode-tool-references
10931 (lambda* (#:key inputs #:allow-other-keys)
10932 (substitute* "trim_galore"
10933 (("\\$path_to_cutadapt = 'cutadapt'")
10934 (string-append "$path_to_cutadapt = '"
10935 (assoc-ref inputs "cutadapt")
10937 (("\\$compression_path = \"gzip\"")
10938 (string-append "$compression_path = \""
10939 (assoc-ref inputs "gzip")
10942 (string-append "\""
10943 (assoc-ref inputs "gzip")
10946 (string-append "\""
10947 (assoc-ref inputs "pigz")
10951 (lambda* (#:key outputs #:allow-other-keys)
10952 (let ((bin (string-append (assoc-ref outputs "out")
10955 (install-file "trim_galore" bin)
10961 ("cutadapt" ,cutadapt)))
10963 `(("unzip" ,unzip)))
10964 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10965 (synopsis "Wrapper around Cutadapt and FastQC")
10966 (description "Trim Galore! is a wrapper script to automate quality and
10967 adapter trimming as well as quality control, with some added functionality to
10968 remove biased methylation positions for RRBS sequence files.")
10969 (license license:gpl3+)))
10971 (define-public gess
10977 (uri (string-append "http://compbio.uthscsa.edu/"
10979 "gess-" version ".src.tar.gz"))
10982 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10983 (build-system gnu-build-system)
10985 `(#:tests? #f ; no tests
10987 (modify-phases %standard-phases
10988 (delete 'configure)
10991 (lambda* (#:key inputs outputs #:allow-other-keys)
10992 (let* ((python (assoc-ref inputs "python"))
10993 (out (assoc-ref outputs "out"))
10994 (bin (string-append out "/bin/"))
10995 (target (string-append
10997 ,(version-major+minor
10998 (package-version python))
10999 "/site-packages/gess/")))
11001 (copy-recursively "." target)
11002 ;; Make GESS.py executable
11003 (chmod (string-append target "GESS.py") #o555)
11004 ;; Add Python shebang to the top and make Matplotlib
11006 (substitute* (string-append target "GESS.py")
11007 (("\"\"\"Description:" line)
11008 (string-append "#!" (which "python") "
11010 matplotlib.use('Agg')
11012 ;; Make sure GESS has all modules in its path
11013 (wrap-program (string-append target "GESS.py")
11014 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11016 (symlink (string-append target "GESS.py")
11017 (string-append bin "GESS.py"))
11020 `(("python" ,python-2)
11021 ("python2-pysam" ,python2-pysam)
11022 ("python2-scipy" ,python2-scipy)
11023 ("python2-numpy" ,python2-numpy)
11024 ("python2-networkx" ,python2-networkx)
11025 ("python2-biopython" ,python2-biopython)))
11026 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11027 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11029 "GESS is an implementation of a novel computational method to detect de
11030 novo exon-skipping events directly from raw RNA-seq data without the prior
11031 knowledge of gene annotation information. GESS stands for the graph-based
11032 exon-skipping scanner detection scheme.")
11033 (license license:bsd-3)))
11035 (define-public phylip
11042 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11043 "download/phylip-" version ".tar.gz"))
11046 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11047 (build-system gnu-build-system)
11049 `(#:tests? #f ; no check target
11050 #:make-flags (list "-f" "Makefile.unx" "install")
11051 #:parallel-build? #f ; not supported
11053 (modify-phases %standard-phases
11054 (add-after 'unpack 'enter-dir
11055 (lambda _ (chdir "src") #t))
11056 (delete 'configure)
11058 (lambda* (#:key inputs outputs #:allow-other-keys)
11059 (let ((target (string-append (assoc-ref outputs "out")
11062 (for-each (lambda (file)
11063 (install-file file target))
11064 (find-files "../exe" ".*")))
11066 (home-page "http://evolution.genetics.washington.edu/phylip/")
11067 (synopsis "Tools for inferring phylogenies")
11068 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11069 programs for inferring phylogenies (evolutionary trees).")
11070 (license license:bsd-2)))
11079 (uri (string-append "https://integrativemodeling.org/"
11080 version "/download/imp-" version ".tar.gz"))
11083 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11084 (build-system cmake-build-system)
11086 `(;; FIXME: Some tests fail because they produce warnings, others fail
11087 ;; because the PYTHONPATH does not include the modeller's directory.
11095 ("python" ,python-2)))
11097 `(("python2-numpy" ,python2-numpy)
11098 ("python2-scipy" ,python2-scipy)
11099 ("python2-pandas" ,python2-pandas)
11100 ("python2-scikit-learn" ,python2-scikit-learn)
11101 ("python2-networkx" ,python2-networkx)))
11102 (home-page "https://integrativemodeling.org")
11103 (synopsis "Integrative modeling platform")
11104 (description "IMP's broad goal is to contribute to a comprehensive
11105 structural characterization of biomolecules ranging in size and complexity
11106 from small peptides to large macromolecular assemblies, by integrating data
11107 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11108 Python toolbox for solving complex modeling problems, and a number of
11109 applications for tackling some common problems in a user-friendly way.")
11110 ;; IMP is largely available under the GNU Lesser GPL; see the file
11111 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11112 ;; available under the GNU GPL (see the file COPYING.GPL).
11113 (license (list license:lgpl2.1+
11116 (define-public tadbit
11122 (uri (git-reference
11123 (url "https://github.com/3DGenomes/TADbit.git")
11124 (commit (string-append "v" version))))
11125 (file-name (git-file-name name version))
11128 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11129 (build-system python-build-system)
11131 `(;; Tests are included and must be run after installation, but
11132 ;; they are incomplete and thus cannot be run.
11136 (modify-phases %standard-phases
11137 (add-after 'unpack 'fix-problems-with-setup.py
11138 (lambda* (#:key outputs #:allow-other-keys)
11139 ;; setup.py opens these files for writing
11140 (chmod "_pytadbit/_version.py" #o664)
11141 (chmod "README.rst" #o664)
11143 ;; Don't attempt to install the bash completions to
11144 ;; the home directory.
11145 (rename-file "extras/.bash_completion"
11147 (substitute* "setup.py"
11148 (("\\(path.expanduser\\('~'\\)")
11149 (string-append "(\""
11150 (assoc-ref outputs "out")
11151 "/etc/bash_completion.d\""))
11152 (("extras/\\.bash_completion")
11156 ;; TODO: add Chimera for visualization
11159 ("python2-scipy" ,python2-scipy)
11160 ("python2-numpy" ,python2-numpy)
11161 ("python2-matplotlib" ,python2-matplotlib)
11162 ("python2-pysam" ,python2-pysam)))
11163 (home-page "https://3dgenomes.github.io/TADbit/")
11164 (synopsis "Analyze, model, and explore 3C-based data")
11166 "TADbit is a complete Python library to deal with all steps to analyze,
11167 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11168 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11169 correct interaction matrices, identify and compare the so-called
11170 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11171 interaction matrices, and finally, extract structural properties from the
11172 models. TADbit is complemented by TADkit for visualizing 3D models.")
11173 (license license:gpl3+)))
11175 (define-public kentutils
11178 ;; 302.1.0 is out, but the only difference is the inclusion of
11179 ;; pre-built binaries.
11180 (version "302.0.0")
11184 (uri (git-reference
11185 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11186 (commit (string-append "v" version))))
11187 (file-name (git-file-name name version))
11190 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11191 (modules '((guix build utils)
11196 ;; Only the contents of the specified directories are free
11197 ;; for all uses, so we remove the rest. "hg/autoSql" and
11198 ;; "hg/autoXml" are nominally free, but they depend on a
11199 ;; library that is built from the sources in "hg/lib",
11200 ;; which is nonfree.
11201 (let ((free (list "." ".."
11202 "utils" "lib" "inc" "tagStorm"
11203 "parasol" "htslib"))
11204 (directory? (lambda (file)
11205 (eq? 'directory (stat:type (stat file))))))
11206 (for-each (lambda (file)
11207 (and (directory? file)
11208 (delete-file-recursively file)))
11209 (map (cut string-append "src/" <>)
11212 (not (member file free)))))))
11213 ;; Only make the utils target, not the userApps target,
11214 ;; because that requires libraries we won't build.
11215 (substitute* "Makefile"
11216 ((" userApps") " utils"))
11217 ;; Only build libraries that are free.
11218 (substitute* "src/makefile"
11219 (("DIRS =.*") "DIRS =\n")
11220 (("cd jkOwnLib.*") "")
11223 (substitute* "src/utils/makefile"
11224 ;; These tools depend on "jkhgap.a", which is part of the
11225 ;; nonfree "src/hg/lib" directory.
11226 (("raSqlQuery") "")
11227 (("pslLiftSubrangeBlat") "")
11229 ;; Do not build UCSC tools, which may require nonfree
11231 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11233 (build-system gnu-build-system)
11235 `( ;; There is no global test target and the test target for
11236 ;; individual tools depends on input files that are not
11240 (modify-phases %standard-phases
11241 (add-after 'unpack 'fix-permissions
11242 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11243 (add-after 'unpack 'fix-paths
11245 (substitute* "Makefile"
11246 (("/bin/echo") (which "echo")))
11248 (add-after 'unpack 'prepare-samtabix
11249 (lambda* (#:key inputs #:allow-other-keys)
11250 (copy-recursively (assoc-ref inputs "samtabix")
11253 (delete 'configure)
11255 (lambda* (#:key outputs #:allow-other-keys)
11256 (let ((bin (string-append (assoc-ref outputs "out")
11258 (copy-recursively "bin" bin))
11264 (uri (git-reference
11265 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11266 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11269 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11275 ("mariadb" ,mariadb)
11276 ("openssl" ,openssl)))
11277 (home-page "http://genome.cse.ucsc.edu/index.html")
11278 (synopsis "Assorted bioinformatics utilities")
11279 (description "This package provides the kentUtils, a selection of
11280 bioinformatics utilities used in combination with the UCSC genome
11282 ;; Only a subset of the sources are released under a non-copyleft
11283 ;; free software license. All other sources are removed in a
11284 ;; snippet. See this bug report for an explanation of how the
11285 ;; license statements apply:
11286 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11287 (license (license:non-copyleft
11288 "http://genome.ucsc.edu/license/"
11289 "The contents of this package are free for all uses."))))
11291 (define-public f-seq
11292 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11296 (version (string-append "1.1-" revision "." (string-take commit 7)))
11299 (uri (git-reference
11300 (url "https://github.com/aboyle/F-seq.git")
11302 (file-name (string-append name "-" version))
11305 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11306 (modules '((guix build utils)))
11307 ;; Remove bundled Java library archives.
11310 (for-each delete-file (find-files "lib" ".*"))
11312 (build-system ant-build-system)
11314 `(#:tests? #f ; no tests included
11316 (modify-phases %standard-phases
11318 (lambda* (#:key inputs outputs #:allow-other-keys)
11319 (let* ((target (assoc-ref outputs "out"))
11320 (bin (string-append target "/bin"))
11321 (doc (string-append target "/share/doc/f-seq"))
11322 (lib (string-append target "/lib")))
11325 (substitute* "bin/linux/fseq"
11326 (("java") (which "java"))
11327 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11328 (string-append (assoc-ref inputs "java-commons-cli")
11329 "/share/java/commons-cli.jar"))
11331 (string-append "REALDIR=" bin "\n")))
11332 (install-file "README.txt" doc)
11333 (install-file "bin/linux/fseq" bin)
11334 (install-file "build~/fseq.jar" lib)
11335 (copy-recursively "lib" lib)
11339 ("java-commons-cli" ,java-commons-cli)))
11340 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11341 (synopsis "Feature density estimator for high-throughput sequence tags")
11343 "F-Seq is a software package that generates a continuous tag sequence
11344 density estimation allowing identification of biologically meaningful sites
11345 such as transcription factor binding sites (ChIP-seq) or regions of open
11346 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11348 (license license:gpl3+))))
11350 (define-public bismark
11357 (uri (git-reference
11358 (url "https://github.com/FelixKrueger/Bismark.git")
11360 (file-name (string-append name "-" version "-checkout"))
11363 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11364 (build-system perl-build-system)
11366 `(#:tests? #f ; there are no tests
11367 #:modules ((guix build utils)
11370 (guix build perl-build-system))
11372 (modify-phases %standard-phases
11373 ;; The bundled plotly.js is minified.
11374 (add-after 'unpack 'replace-plotly.js
11375 (lambda* (#:key inputs #:allow-other-keys)
11376 (let* ((file (assoc-ref inputs "plotly.js"))
11377 (installed "plotly/plotly.js"))
11378 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11379 (call-with-output-file installed
11380 (cut dump-port minified <>))))
11382 (delete 'configure)
11385 (lambda* (#:key inputs outputs #:allow-other-keys)
11386 (let* ((out (assoc-ref outputs "out"))
11387 (bin (string-append out "/bin"))
11388 (share (string-append out "/share/bismark"))
11389 (docdir (string-append out "/share/doc/bismark"))
11390 (docs '("Docs/Bismark_User_Guide.html"))
11391 (scripts '("bismark"
11392 "bismark_genome_preparation"
11393 "bismark_methylation_extractor"
11396 "coverage2cytosine"
11397 "deduplicate_bismark"
11398 "filter_non_conversion"
11401 "NOMe_filtering")))
11402 (substitute* "bismark2report"
11403 (("\\$RealBin/plotly")
11404 (string-append share "/plotly")))
11408 (for-each (lambda (file) (install-file file bin))
11410 (for-each (lambda (file) (install-file file docdir))
11412 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11413 (copy-recursively "plotly"
11414 (string-append share "/plotly"))
11416 ;; Fix references to gunzip
11417 (substitute* (map (lambda (file)
11418 (string-append bin "/" file))
11421 (string-append "\"" (assoc-ref inputs "gzip")
11422 "/bin/gunzip -c")))
11426 ("perl-carp" ,perl-carp)
11427 ("perl-getopt-long" ,perl-getopt-long)))
11432 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11433 "v1.39.4/dist/plotly.js"))
11435 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11436 ("uglify-js" ,uglify-js)))
11437 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11438 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11439 (description "Bismark is a program to map bisulfite treated sequencing
11440 reads to a genome of interest and perform methylation calls in a single step.
11441 The output can be easily imported into a genome viewer, such as SeqMonk, and
11442 enables a researcher to analyse the methylation levels of their samples
11443 straight away. Its main features are:
11446 @item Bisulfite mapping and methylation calling in one single step
11447 @item Supports single-end and paired-end read alignments
11448 @item Supports ungapped and gapped alignments
11449 @item Alignment seed length, number of mismatches etc are adjustable
11450 @item Output discriminates between cytosine methylation in CpG, CHG
11453 (license license:gpl3+)))
11455 (define-public paml
11461 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11462 "paml" version ".tgz"))
11465 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11466 (modules '((guix build utils)))
11467 ;; Remove Windows binaries
11470 (for-each delete-file (find-files "." "\\.exe$"))
11472 (build-system gnu-build-system)
11474 `(#:tests? #f ; there are no tests
11475 #:make-flags '("CC=gcc")
11477 (modify-phases %standard-phases
11478 (replace 'configure
11480 (substitute* "src/BFdriver.c"
11481 (("/bin/bash") (which "bash")))
11485 (lambda* (#:key outputs #:allow-other-keys)
11486 (let ((tools '("baseml" "basemlg" "codeml"
11487 "pamp" "evolver" "yn00" "chi2"))
11488 (bin (string-append (assoc-ref outputs "out") "/bin"))
11489 (docdir (string-append (assoc-ref outputs "out")
11490 "/share/doc/paml")))
11492 (for-each (lambda (file) (install-file file bin)) tools)
11493 (copy-recursively "../doc" docdir)
11495 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11496 (synopsis "Phylogentic analysis by maximum likelihood")
11497 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11498 contains a few programs for model fitting and phylogenetic tree reconstruction
11499 using nucleotide or amino-acid sequence data.")
11501 (license license:gpl3)))
11503 (define-public kallisto
11509 (uri (git-reference
11510 (url "https://github.com/pachterlab/kallisto.git")
11511 (commit (string-append "v" version))))
11512 (file-name (git-file-name name version))
11515 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11516 (build-system cmake-build-system)
11518 `(#:tests? #f ; no "check" target
11520 (modify-phases %standard-phases
11521 (add-after 'unpack 'do-not-use-bundled-htslib
11523 (substitute* "CMakeLists.txt"
11524 (("^ExternalProject_Add" m)
11525 (string-append "if (NEVER)\n" m))
11527 (string-append ")\nendif(NEVER)"))
11528 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11529 (string-append "# " m)))
11530 (substitute* "src/CMakeLists.txt"
11531 (("target_link_libraries\\(kallisto kallisto_core pthread \
11532 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11533 "target_link_libraries(kallisto kallisto_core pthread hts)")
11534 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11540 (home-page "http://pachterlab.github.io/kallisto/")
11541 (synopsis "Near-optimal RNA-Seq quantification")
11543 "Kallisto is a program for quantifying abundances of transcripts from
11544 RNA-Seq data, or more generally of target sequences using high-throughput
11545 sequencing reads. It is based on the novel idea of pseudoalignment for
11546 rapidly determining the compatibility of reads with targets, without the need
11547 for alignment. Pseudoalignment of reads preserves the key information needed
11548 for quantification, and kallisto is therefore not only fast, but also as
11549 accurate as existing quantification tools.")
11550 (license license:bsd-2)))
11552 (define-public libgff
11558 (uri (git-reference
11559 (url "https://github.com/Kingsford-Group/libgff.git")
11560 (commit (string-append "v" version))))
11561 (file-name (git-file-name name version))
11564 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11565 (build-system cmake-build-system)
11566 (arguments `(#:tests? #f)) ; no tests included
11567 (home-page "https://github.com/Kingsford-Group/libgff")
11568 (synopsis "Parser library for reading/writing GFF files")
11569 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11570 code that is used in the Cufflinks codebase. The goal of this library is to
11571 provide this functionality without the necessity of drawing in a heavy-weight
11572 dependency like SeqAn.")
11573 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11575 (define-public libdivsufsort
11577 (name "libdivsufsort")
11581 (uri (git-reference
11582 (url "https://github.com/y-256/libdivsufsort.git")
11584 (file-name (git-file-name name version))
11587 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11588 (build-system cmake-build-system)
11590 '(#:tests? #f ; there are no tests
11592 ;; Needed for rapmap and sailfish.
11593 '("-DBUILD_DIVSUFSORT64=ON")))
11594 (home-page "https://github.com/y-256/libdivsufsort")
11595 (synopsis "Lightweight suffix-sorting library")
11596 (description "libdivsufsort is a software library that implements a
11597 lightweight suffix array construction algorithm. This library provides a
11598 simple and an efficient C API to construct a suffix array and a
11599 Burrows-Wheeler transformed string from a given string over a constant-size
11600 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11601 bytes of memory space, where n is the length of the string.")
11602 (license license:expat)))
11604 (define-public sailfish
11610 (uri (git-reference
11611 (url "https://github.com/kingsfordgroup/sailfish.git")
11612 (commit (string-append "v" version))))
11613 (file-name (git-file-name name version))
11616 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11617 (modules '((guix build utils)))
11620 ;; Delete bundled headers for eigen3.
11621 (delete-file-recursively "include/eigen3/")
11623 (build-system cmake-build-system)
11625 `(#:configure-flags
11626 (list (string-append "-DBOOST_INCLUDEDIR="
11627 (assoc-ref %build-inputs "boost")
11629 (string-append "-DBOOST_LIBRARYDIR="
11630 (assoc-ref %build-inputs "boost")
11632 (string-append "-DBoost_LIBRARIES="
11633 "-lboost_iostreams "
11634 "-lboost_filesystem "
11639 "-lboost_program_options")
11640 "-DBoost_FOUND=TRUE"
11641 ;; Don't download RapMap---we already have it!
11642 "-DFETCHED_RAPMAP=1")
11643 ;; Tests must be run after installation and the location of the test
11644 ;; data file must be overridden. But the tests fail. It looks like
11645 ;; they are not really meant to be run.
11648 (modify-phases %standard-phases
11649 ;; Boost cannot be found, even though it's right there.
11650 (add-after 'unpack 'do-not-look-for-boost
11651 (lambda* (#:key inputs #:allow-other-keys)
11652 (substitute* "CMakeLists.txt"
11653 (("find_package\\(Boost 1\\.53\\.0") "#"))
11655 (add-after 'unpack 'do-not-assign-to-macro
11657 (substitute* "include/spdlog/details/format.cc"
11658 (("const unsigned CHAR_WIDTH = 1;") ""))
11660 (add-after 'unpack 'prepare-rapmap
11661 (lambda* (#:key inputs #:allow-other-keys)
11662 (let ((src "external/install/src/rapmap/")
11663 (include "external/install/include/rapmap/")
11664 (rapmap (assoc-ref inputs "rapmap")))
11665 (mkdir-p "/tmp/rapmap")
11667 (assoc-ref inputs "rapmap")
11669 "--strip-components=1")
11672 (for-each (lambda (file)
11673 (install-file file src))
11674 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11675 (copy-recursively "/tmp/rapmap/include" include))
11677 (add-after 'unpack 'use-system-libraries
11678 (lambda* (#:key inputs #:allow-other-keys)
11679 (substitute* '("src/SailfishIndexer.cpp"
11680 "src/SailfishUtils.cpp"
11681 "src/SailfishQuantify.cpp"
11682 "src/FASTAParser.cpp"
11684 "include/SailfishUtils.hpp"
11685 "include/SailfishIndex.hpp"
11686 "include/CollapsedEMOptimizer.hpp"
11687 "src/CollapsedEMOptimizer.cpp")
11688 (("#include \"jellyfish/config.h\"") ""))
11689 (substitute* "src/CMakeLists.txt"
11690 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11691 (string-append (assoc-ref inputs "jellyfish")
11692 "/include/jellyfish-" ,(package-version jellyfish)))
11693 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11694 (string-append (assoc-ref inputs "jellyfish")
11695 "/lib/libjellyfish-2.0.a"))
11696 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11697 (string-append (assoc-ref inputs "libdivsufsort")
11698 "/lib/libdivsufsort.so"))
11699 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11700 (string-append (assoc-ref inputs "libdivsufsort")
11701 "/lib/libdivsufsort64.so")))
11702 (substitute* "CMakeLists.txt"
11703 ;; Don't prefer static libs
11704 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11705 (("find_package\\(Jellyfish.*") "")
11706 (("ExternalProject_Add\\(libjellyfish") "message(")
11707 (("ExternalProject_Add\\(libgff") "message(")
11708 (("ExternalProject_Add\\(libsparsehash") "message(")
11709 (("ExternalProject_Add\\(libdivsufsort") "message("))
11711 ;; Ensure that Eigen headers can be found
11712 (setenv "CPLUS_INCLUDE_PATH"
11713 (string-append (assoc-ref inputs "eigen")
11714 "/include/eigen3"))
11719 ("jemalloc" ,jemalloc)
11720 ("jellyfish" ,jellyfish)
11721 ("sparsehash" ,sparsehash)
11724 (uri (git-reference
11725 (url "https://github.com/COMBINE-lab/RapMap.git")
11726 (commit (string-append "sf-v" version))))
11727 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11730 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11731 (modules '((guix build utils)))
11732 ;; These files are expected to be excluded.
11734 '(begin (delete-file-recursively "include/spdlog")
11735 (for-each delete-file '("include/xxhash.h"
11738 ("libdivsufsort" ,libdivsufsort)
11743 `(("pkg-config" ,pkg-config)))
11744 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11745 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11746 (description "Sailfish is a tool for genomic transcript quantification
11747 from RNA-seq data. It requires a set of target transcripts (either from a
11748 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11749 fasta file containing your reference transcripts and a (set of) fasta/fastq
11750 file(s) containing your reads.")
11751 (license license:gpl3+)))
11753 (define libstadenio-for-salmon
11755 (name "libstadenio")
11759 (uri (git-reference
11760 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11761 (commit (string-append "v" version))))
11762 (file-name (string-append name "-" version "-checkout"))
11765 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11766 (build-system gnu-build-system)
11767 (arguments '(#:parallel-tests? #f)) ; not supported
11771 `(("perl" ,perl))) ; for tests
11772 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11773 (synopsis "General purpose trace and experiment file library")
11774 (description "This package provides a library of file reading and writing
11775 code to provide a general purpose Trace file (and Experiment File) reading
11778 The following file formats are supported:
11781 @item SCF trace files
11782 @item ABI trace files
11783 @item ALF trace files
11784 @item ZTR trace files
11785 @item SFF trace archives
11786 @item SRF trace archives
11787 @item Experiment files
11788 @item Plain text files
11789 @item SAM/BAM sequence files
11790 @item CRAM sequence files
11792 (license license:bsd-3)))
11794 (define-public salmon
11800 (uri (git-reference
11801 (url "https://github.com/COMBINE-lab/salmon.git")
11802 (commit (string-append "v" version))))
11803 (file-name (git-file-name name version))
11806 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11807 (modules '((guix build utils)))
11810 ;; Delete bundled headers for eigen3.
11811 (delete-file-recursively "include/eigen3/")
11813 (build-system cmake-build-system)
11815 `(#:configure-flags
11816 (list (string-append "-DBOOST_INCLUDEDIR="
11817 (assoc-ref %build-inputs "boost")
11819 (string-append "-DBOOST_LIBRARYDIR="
11820 (assoc-ref %build-inputs "boost")
11822 (string-append "-DBoost_LIBRARIES="
11823 "-lboost_iostreams "
11824 "-lboost_filesystem "
11829 "-lboost_program_options")
11830 "-DBoost_FOUND=TRUE"
11831 "-DTBB_LIBRARIES=tbb tbbmalloc"
11832 ;; Don't download RapMap---we already have it!
11833 "-DFETCHED_RAPMAP=1")
11835 (modify-phases %standard-phases
11836 ;; Boost cannot be found, even though it's right there.
11837 (add-after 'unpack 'do-not-look-for-boost
11838 (lambda* (#:key inputs #:allow-other-keys)
11839 (substitute* "CMakeLists.txt"
11840 (("find_package\\(Boost 1\\.59\\.0") "#"))
11842 (add-after 'unpack 'do-not-phone-home
11844 (substitute* "src/Salmon.cpp"
11845 (("getVersionMessage\\(\\)") "\"\""))
11847 (add-after 'unpack 'prepare-rapmap
11848 (lambda* (#:key inputs #:allow-other-keys)
11849 (let ((src "external/install/src/rapmap/")
11850 (include "external/install/include/rapmap/")
11851 (rapmap (assoc-ref inputs "rapmap")))
11854 (copy-recursively (string-append rapmap "/src") src)
11855 (copy-recursively (string-append rapmap "/include") include)
11856 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11857 "external/install/include/rapmap/FastxParser.hpp"
11858 "external/install/include/rapmap/concurrentqueue.h"
11859 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11860 "external/install/src/rapmap/FastxParser.cpp"
11861 "external/install/src/rapmap/xxhash.c"))
11862 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11864 (add-after 'unpack 'use-system-libraries
11865 (lambda* (#:key inputs #:allow-other-keys)
11866 (substitute* "CMakeLists.txt"
11867 ;; Don't prefer static libs
11868 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11869 (("set\\(TBB_LIBRARIES") "message(")
11870 ;; Don't download anything
11871 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11872 (("externalproject_add\\(libcereal") "message(")
11873 (("externalproject_add\\(libgff") "message(")
11874 (("externalproject_add\\(libtbb") "message(")
11875 (("externalproject_add\\(libdivsufsort") "message(")
11876 (("externalproject_add\\(libstadenio") "message(")
11877 (("externalproject_add_step\\(") "message("))
11878 (substitute* "src/CMakeLists.txt"
11879 (("add_dependencies") "#")
11880 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11881 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11882 "/lib/libstaden-read.so"))
11883 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11884 (string-append (assoc-ref inputs "libdivsufsort")
11885 "/lib/libdivsufsort.so"))
11886 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11887 (string-append (assoc-ref inputs "libdivsufsort")
11888 "/lib/libdivsufsort64.so"))
11889 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11891 ;; Ensure that all headers can be found
11893 (string-append (getenv "CPATH")
11895 (assoc-ref inputs "eigen")
11896 "/include/eigen3"))
11898 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11899 ;; run. It only exists after the install phase.
11900 (add-after 'unpack 'fix-tests
11902 (substitute* "src/CMakeLists.txt"
11903 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11904 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11913 (uri (git-reference
11914 (url "https://github.com/COMBINE-lab/RapMap.git")
11915 (commit (string-append "salmon-v" version))))
11916 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11919 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
11920 ("jemalloc" ,jemalloc)
11923 ("libdivsufsort" ,libdivsufsort)
11924 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11928 `(("pkg-config" ,pkg-config)))
11929 (home-page "https://github.com/COMBINE-lab/salmon")
11930 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11931 (description "Salmon is a program to produce highly-accurate,
11932 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11933 its accuracy and speed via a number of different innovations, including the
11934 use of lightweight alignments (accurate but fast-to-compute proxies for
11935 traditional read alignments) and massively-parallel stochastic collapsed
11936 variational inference.")
11937 (license license:gpl3+)))
11939 (define-public python-loompy
11941 (name "python-loompy")
11943 ;; The tarball on Pypi does not include the tests.
11946 (uri (git-reference
11947 (url "https://github.com/linnarsson-lab/loompy.git")
11949 (file-name (git-file-name name version))
11952 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
11953 (build-system python-build-system)
11956 (modify-phases %standard-phases
11959 (setenv "PYTHONPATH"
11960 (string-append (getcwd) ":"
11961 (getenv "PYTHONPATH")))
11962 (invoke "pytest" "tests")
11965 `(("python-h5py" ,python-h5py)
11966 ("python-numpy" ,python-numpy)
11967 ("python-pandas" ,python-pandas)
11968 ("python-scipy" ,python-scipy)))
11970 `(("python-pytest" ,python-pytest)))
11971 (home-page "https://github.com/linnarsson-lab/loompy")
11972 (synopsis "Work with .loom files for single-cell RNA-seq data")
11973 (description "The loom file format is an efficient format for very large
11974 omics datasets, consisting of a main matrix, optional additional layers, a
11975 variable number of row and column annotations. Loom also supports sparse
11976 graphs. This library makes it easy to work with @file{.loom} files for
11977 single-cell RNA-seq data.")
11978 (license license:bsd-3)))
11980 ;; pigx-scrnaseq does not work with the latest version of loompy.
11981 (define-public python-loompy-for-pigx-scrnaseq
11982 (package (inherit python-loompy)
11983 (name "python-loompy")
11987 (uri (git-reference
11988 (url "https://github.com/linnarsson-lab/loompy.git")
11989 (commit (string-append "v" version))))
11990 (file-name (git-file-name name version))
11993 "0pjyl532pl8sbv71yci6h0agchn0naw2qjcwj50n6afrsahbsag3"))))
11995 (arguments '(#:tests? #f))))
11997 ;; We cannot use the latest commit because it requires Java 9.
11998 (define-public java-forester
11999 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12002 (name "java-forester")
12003 (version (string-append "0-" revision "." (string-take commit 7)))
12006 (uri (git-reference
12007 (url "https://github.com/cmzmasek/forester.git")
12009 (file-name (string-append name "-" version "-checkout"))
12012 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12013 (modules '((guix build utils)))
12016 ;; Delete bundled jars and pre-built classes
12017 (delete-file-recursively "forester/java/resources")
12018 (delete-file-recursively "forester/java/classes")
12019 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12020 ;; Delete bundled applications
12021 (delete-file-recursively "forester_applications")
12023 (build-system ant-build-system)
12025 `(#:tests? #f ; there are none
12027 #:modules ((guix build ant-build-system)
12029 (guix build java-utils)
12033 (modify-phases %standard-phases
12034 (add-after 'unpack 'chdir
12035 (lambda _ (chdir "forester/java") #t))
12036 (add-after 'chdir 'fix-dependencies
12038 (chmod "build.xml" #o664)
12039 (call-with-output-file "build.xml.new"
12043 (with-input-from-file "build.xml"
12044 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12045 `(;; Remove all unjar tags to avoid repacking classes.
12046 (unjar . ,(lambda _ '()))
12047 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12048 (*text* . ,(lambda (_ txt) txt))))
12050 (rename-file "build.xml.new" "build.xml")
12052 ;; FIXME: itext is difficult to package as it depends on a few
12053 ;; unpackaged libraries.
12054 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12056 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12057 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12058 (("pdf_written_to = PdfExporter.*")
12059 "throw new IOException(\"PDF export is not available.\");"))
12061 ;; There is no install target
12062 (replace 'install (install-jars ".")))))
12064 `(("java-commons-codec" ,java-commons-codec)
12065 ("java-openchart2" ,java-openchart2)))
12066 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12067 (synopsis "Phylogenomics libraries for Java")
12068 (description "Forester is a collection of Java libraries for
12069 phylogenomics and evolutionary biology research. It includes support for
12070 reading, writing, and exporting phylogenetic trees.")
12071 (license license:lgpl2.1+))))
12073 (define-public java-forester-1.005
12075 (name "java-forester")
12079 (uri (string-append "http://search.maven.org/remotecontent?"
12080 "filepath=org/biojava/thirdparty/forester/"
12081 version "/forester-" version "-sources.jar"))
12082 (file-name (string-append name "-" version ".jar"))
12085 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12086 (build-system ant-build-system)
12088 `(#:tests? #f ; there are none
12090 #:modules ((guix build ant-build-system)
12092 (guix build java-utils)
12096 (modify-phases %standard-phases
12097 (add-after 'unpack 'fix-dependencies
12098 (lambda* (#:key inputs #:allow-other-keys)
12099 (call-with-output-file "build.xml"
12103 (with-input-from-file "src/build.xml"
12104 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12105 `(;; Remove all unjar tags to avoid repacking classes.
12106 (unjar . ,(lambda _ '()))
12107 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12108 (*text* . ,(lambda (_ txt) txt))))
12110 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12111 "synth_look_and_feel_1.xml")
12112 (copy-file (assoc-ref inputs "phyloxml.xsd")
12114 (substitute* "build.xml"
12115 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12116 "synth_look_and_feel_1.xml")
12117 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12120 ;; FIXME: itext is difficult to package as it depends on a few
12121 ;; unpackaged libraries.
12122 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12124 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12125 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12126 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12127 (("pdf_written_to = PdfExporter.*")
12128 "throw new IOException(\"PDF export is not available.\"); /*")
12129 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12130 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12132 (add-after 'unpack 'delete-pre-built-classes
12133 (lambda _ (delete-file-recursively "src/classes") #t))
12134 ;; There is no install target
12135 (replace 'install (install-jars ".")))))
12137 `(("java-commons-codec" ,java-commons-codec)
12138 ("java-openchart2" ,java-openchart2)))
12139 ;; The source archive does not contain the resources.
12144 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12145 "b61cc2dcede0bede317db362472333115756b8c6/"
12146 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12147 (file-name (string-append name "-phyloxml-" version ".xsd"))
12150 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12151 ("synth_look_and_feel_1.xml"
12154 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12155 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12156 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12157 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12160 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12161 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12162 (synopsis "Phylogenomics libraries for Java")
12163 (description "Forester is a collection of Java libraries for
12164 phylogenomics and evolutionary biology research. It includes support for
12165 reading, writing, and exporting phylogenetic trees.")
12166 (license license:lgpl2.1+)))
12168 (define-public java-biojava-core
12170 (name "java-biojava-core")
12174 (uri (git-reference
12175 (url "https://github.com/biojava/biojava")
12176 (commit (string-append "biojava-" version))))
12177 (file-name (string-append name "-" version "-checkout"))
12180 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12181 (build-system ant-build-system)
12184 #:jar-name "biojava-core.jar"
12185 #:source-dir "biojava-core/src/main/java/"
12186 #:test-dir "biojava-core/src/test"
12187 ;; These tests seem to require internet access.
12188 #:test-exclude (list "**/SearchIOTest.java"
12189 "**/BlastXMLParserTest.java"
12190 "**/GenbankCookbookTest.java"
12191 "**/GenbankProxySequenceReaderTest.java")
12193 (modify-phases %standard-phases
12194 (add-before 'build 'copy-resources
12196 (copy-recursively "biojava-core/src/main/resources"
12199 (add-before 'check 'copy-test-resources
12201 (copy-recursively "biojava-core/src/test/resources"
12202 "build/test-classes")
12205 `(("java-log4j-api" ,java-log4j-api)
12206 ("java-log4j-core" ,java-log4j-core)
12207 ("java-slf4j-api" ,java-slf4j-api)
12208 ("java-slf4j-simple" ,java-slf4j-simple)))
12210 `(("java-junit" ,java-junit)
12211 ("java-hamcrest-core" ,java-hamcrest-core)))
12212 (home-page "http://biojava.org")
12213 (synopsis "Core libraries of Java framework for processing biological data")
12214 (description "BioJava is a project dedicated to providing a Java framework
12215 for processing biological data. It provides analytical and statistical
12216 routines, parsers for common file formats, reference implementations of
12217 popular algorithms, and allows the manipulation of sequences and 3D
12218 structures. The goal of the biojava project is to facilitate rapid
12219 application development for bioinformatics.
12221 This package provides the core libraries.")
12222 (license license:lgpl2.1+)))
12224 (define-public java-biojava-phylo
12225 (package (inherit java-biojava-core)
12226 (name "java-biojava-phylo")
12227 (build-system ant-build-system)
12230 #:jar-name "biojava-phylo.jar"
12231 #:source-dir "biojava-phylo/src/main/java/"
12232 #:test-dir "biojava-phylo/src/test"
12234 (modify-phases %standard-phases
12235 (add-before 'build 'copy-resources
12237 (copy-recursively "biojava-phylo/src/main/resources"
12240 (add-before 'check 'copy-test-resources
12242 (copy-recursively "biojava-phylo/src/test/resources"
12243 "build/test-classes")
12246 `(("java-log4j-api" ,java-log4j-api)
12247 ("java-log4j-core" ,java-log4j-core)
12248 ("java-slf4j-api" ,java-slf4j-api)
12249 ("java-slf4j-simple" ,java-slf4j-simple)
12250 ("java-biojava-core" ,java-biojava-core)
12251 ("java-forester" ,java-forester)))
12253 `(("java-junit" ,java-junit)
12254 ("java-hamcrest-core" ,java-hamcrest-core)))
12255 (home-page "http://biojava.org")
12256 (synopsis "Biojava interface to the forester phylogenomics library")
12257 (description "The phylo module provides a biojava interface layer to the
12258 forester phylogenomics library for constructing phylogenetic trees.")))
12260 (define-public java-biojava-alignment
12261 (package (inherit java-biojava-core)
12262 (name "java-biojava-alignment")
12263 (build-system ant-build-system)
12266 #:jar-name "biojava-alignment.jar"
12267 #:source-dir "biojava-alignment/src/main/java/"
12268 #:test-dir "biojava-alignment/src/test"
12270 (modify-phases %standard-phases
12271 (add-before 'build 'copy-resources
12273 (copy-recursively "biojava-alignment/src/main/resources"
12276 (add-before 'check 'copy-test-resources
12278 (copy-recursively "biojava-alignment/src/test/resources"
12279 "build/test-classes")
12282 `(("java-log4j-api" ,java-log4j-api)
12283 ("java-log4j-core" ,java-log4j-core)
12284 ("java-slf4j-api" ,java-slf4j-api)
12285 ("java-slf4j-simple" ,java-slf4j-simple)
12286 ("java-biojava-core" ,java-biojava-core)
12287 ("java-biojava-phylo" ,java-biojava-phylo)
12288 ("java-forester" ,java-forester)))
12290 `(("java-junit" ,java-junit)
12291 ("java-hamcrest-core" ,java-hamcrest-core)))
12292 (home-page "http://biojava.org")
12293 (synopsis "Biojava API for genetic sequence alignment")
12294 (description "The alignment module of BioJava provides an API that
12298 @item implementations of dynamic programming algorithms for sequence
12300 @item reading and writing of popular alignment file formats;
12301 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12304 (define-public java-biojava-core-4.0
12305 (package (inherit java-biojava-core)
12306 (name "java-biojava-core")
12310 (uri (git-reference
12311 (url "https://github.com/biojava/biojava")
12312 (commit (string-append "biojava-" version))))
12313 (file-name (string-append name "-" version "-checkout"))
12316 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12318 (define-public java-biojava-phylo-4.0
12319 (package (inherit java-biojava-core-4.0)
12320 (name "java-biojava-phylo")
12321 (build-system ant-build-system)
12324 #:jar-name "biojava-phylo.jar"
12325 #:source-dir "biojava-phylo/src/main/java/"
12326 #:test-dir "biojava-phylo/src/test"
12328 (modify-phases %standard-phases
12329 (add-before 'build 'copy-resources
12331 (copy-recursively "biojava-phylo/src/main/resources"
12334 (add-before 'check 'copy-test-resources
12336 (copy-recursively "biojava-phylo/src/test/resources"
12337 "build/test-classes")
12340 `(("java-log4j-api" ,java-log4j-api)
12341 ("java-log4j-core" ,java-log4j-core)
12342 ("java-slf4j-api" ,java-slf4j-api)
12343 ("java-slf4j-simple" ,java-slf4j-simple)
12344 ("java-biojava-core" ,java-biojava-core-4.0)
12345 ("java-forester" ,java-forester-1.005)))
12347 `(("java-junit" ,java-junit)
12348 ("java-hamcrest-core" ,java-hamcrest-core)))
12349 (home-page "http://biojava.org")
12350 (synopsis "Biojava interface to the forester phylogenomics library")
12351 (description "The phylo module provides a biojava interface layer to the
12352 forester phylogenomics library for constructing phylogenetic trees.")))
12354 (define-public java-biojava-alignment-4.0
12355 (package (inherit java-biojava-core-4.0)
12356 (name "java-biojava-alignment")
12357 (build-system ant-build-system)
12360 #:jar-name "biojava-alignment.jar"
12361 #:source-dir "biojava-alignment/src/main/java/"
12362 #:test-dir "biojava-alignment/src/test"
12364 (modify-phases %standard-phases
12365 (add-before 'build 'copy-resources
12367 (copy-recursively "biojava-alignment/src/main/resources"
12370 (add-before 'check 'copy-test-resources
12372 (copy-recursively "biojava-alignment/src/test/resources"
12373 "build/test-classes")
12376 `(("java-log4j-api" ,java-log4j-api)
12377 ("java-log4j-core" ,java-log4j-core)
12378 ("java-slf4j-api" ,java-slf4j-api)
12379 ("java-slf4j-simple" ,java-slf4j-simple)
12380 ("java-biojava-core" ,java-biojava-core-4.0)
12381 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12382 ("java-forester" ,java-forester-1.005)))
12384 `(("java-junit" ,java-junit)
12385 ("java-hamcrest-core" ,java-hamcrest-core)))
12386 (home-page "http://biojava.org")
12387 (synopsis "Biojava API for genetic sequence alignment")
12388 (description "The alignment module of BioJava provides an API that
12392 @item implementations of dynamic programming algorithms for sequence
12394 @item reading and writing of popular alignment file formats;
12395 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12398 (define-public dropseq-tools
12400 (name "dropseq-tools")
12405 (uri "http://mccarrolllab.com/download/1276/")
12406 (file-name (string-append "dropseq-tools-" version ".zip"))
12409 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12410 ;; Delete bundled libraries
12411 (modules '((guix build utils)))
12414 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12415 (delete-file-recursively "3rdParty")
12417 (build-system ant-build-system)
12419 `(#:tests? #f ; test data are not included
12420 #:test-target "test"
12421 #:build-target "all"
12422 #:source-dir "public/src/"
12425 (list (string-append "-Dpicard.executable.dir="
12426 (assoc-ref %build-inputs "java-picard")
12428 #:modules ((ice-9 match)
12431 (guix build java-utils)
12432 (guix build ant-build-system))
12434 (modify-phases %standard-phases
12435 ;; FIXME: fails with "java.io.FileNotFoundException:
12436 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12437 (delete 'generate-jar-indices)
12438 ;; All dependencies must be linked to "lib", because that's where
12439 ;; they will be searched for when the Class-Path property of the
12440 ;; manifest is computed.
12441 (add-after 'unpack 'record-references
12442 (lambda* (#:key inputs #:allow-other-keys)
12443 (mkdir-p "jar/lib")
12444 (let ((dirs (filter-map (match-lambda
12446 (if (and (string-prefix? "java-" name)
12447 (not (string=? name "java-testng")))
12450 (for-each (lambda (jar)
12451 (symlink jar (string-append "jar/lib/" (basename jar))))
12452 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12455 ;; There is no installation target
12457 (lambda* (#:key inputs outputs #:allow-other-keys)
12458 (let* ((out (assoc-ref outputs "out"))
12459 (bin (string-append out "/bin"))
12460 (share (string-append out "/share/java/"))
12461 (lib (string-append share "/lib/"))
12462 (scripts (list "BAMTagHistogram"
12463 "BAMTagofTagCounts"
12464 "BaseDistributionAtReadPosition"
12465 "CollapseBarcodesInPlace"
12466 "CollapseTagWithContext"
12468 "CreateIntervalsFiles"
12469 "DetectBeadSynthesisErrors"
12470 "DigitalExpression"
12471 "Drop-seq_alignment.sh"
12474 "GatherGeneGCLength"
12475 "GatherMolecularBarcodeDistributionByGene"
12476 "GatherReadQualityMetrics"
12479 "SelectCellsByNumTranscripts"
12480 "SingleCellRnaSeqMetricsCollector"
12481 "TagBamWithReadSequenceExtended"
12482 "TagReadWithGeneExon"
12483 "TagReadWithInterval"
12484 "TrimStartingSequence"
12485 "ValidateReference")))
12486 (for-each mkdir-p (list bin share lib))
12487 (install-file "dist/dropseq.jar" share)
12488 (for-each (lambda (script)
12489 (chmod script #o555)
12490 (install-file script bin))
12492 (substitute* (map (lambda (script)
12493 (string-append bin "/" script))
12495 (("^java") (which "java"))
12496 (("jar_deploy_dir=.*")
12497 (string-append "jar_deploy_dir=" share "\n"))))
12499 ;; FIXME: We do this after stripping jars because we don't want it to
12500 ;; copy all these jars and strip them. We only want to install
12501 ;; links. Arguably, this is a problem with the ant-build-system.
12502 (add-after 'strip-jar-timestamps 'install-links
12503 (lambda* (#:key outputs #:allow-other-keys)
12504 (let* ((out (assoc-ref outputs "out"))
12505 (share (string-append out "/share/java/"))
12506 (lib (string-append share "/lib/")))
12507 (for-each (lambda (jar)
12508 (symlink (readlink jar)
12509 (string-append lib (basename jar))))
12510 (find-files "jar/lib" "\\.jar$")))
12513 `(("jdk" ,icedtea-8)
12514 ("java-picard" ,java-picard-2.10.3)
12515 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12516 ("java-commons-math3" ,java-commons-math3)
12517 ("java-commons-jexl2" ,java-commons-jexl-2)
12518 ("java-commons-collections4" ,java-commons-collections4)
12519 ("java-commons-lang2" ,java-commons-lang)
12520 ("java-commons-io" ,java-commons-io)
12521 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12522 ("java-guava" ,java-guava)
12523 ("java-la4j" ,java-la4j)
12524 ("java-biojava-core" ,java-biojava-core-4.0)
12525 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12526 ("java-jdistlib" ,java-jdistlib)
12527 ("java-simple-xml" ,java-simple-xml)
12528 ("java-snakeyaml" ,java-snakeyaml)))
12531 ("java-testng" ,java-testng)))
12532 (home-page "http://mccarrolllab.com/dropseq/")
12533 (synopsis "Tools for Drop-seq analyses")
12534 (description "Drop-seq is a technology to enable biologists to
12535 analyze RNA expression genome-wide in thousands of individual cells at
12536 once. This package provides tools to perform Drop-seq analyses.")
12537 (license license:expat)))
12539 (define-public pigx-rnaseq
12541 (name "pigx-rnaseq")
12545 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12546 "releases/download/v" version
12547 "/pigx_rnaseq-" version ".tar.gz"))
12550 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12551 (build-system gnu-build-system)
12553 `(#:parallel-tests? #f ; not supported
12555 (modify-phases %standard-phases
12556 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12557 (add-after 'unpack 'disable-resource-intensive-test
12559 (substitute* "Makefile.in"
12560 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12561 (("^ tests/test_multiqc/test.sh") "")
12562 (("^ test.sh") ""))
12565 `(("coreutils" ,coreutils)
12568 ("snakemake" ,snakemake)
12570 ("multiqc" ,multiqc)
12572 ("trim-galore" ,trim-galore)
12574 ("samtools" ,samtools)
12575 ("r-minimal" ,r-minimal)
12576 ("r-rmarkdown" ,r-rmarkdown)
12577 ("r-ggplot2" ,r-ggplot2)
12578 ("r-ggrepel" ,r-ggrepel)
12579 ("r-gprofiler" ,r-gprofiler)
12580 ("r-deseq2" ,r-deseq2)
12582 ("r-knitr" ,r-knitr)
12583 ("r-pheatmap" ,r-pheatmap)
12584 ("r-corrplot" ,r-corrplot)
12585 ("r-reshape2" ,r-reshape2)
12586 ("r-plotly" ,r-plotly)
12587 ("r-scales" ,r-scales)
12588 ("r-summarizedexperiment" ,r-summarizedexperiment)
12589 ("r-crosstalk" ,r-crosstalk)
12590 ("r-tximport" ,r-tximport)
12591 ("r-rtracklayer" ,r-rtracklayer)
12592 ("r-rjson" ,r-rjson)
12594 ("ghc-pandoc" ,ghc-pandoc)
12595 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12596 ("python-wrapper" ,python-wrapper)
12597 ("python-pyyaml" ,python-pyyaml)))
12598 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12599 (synopsis "Analysis pipeline for RNA sequencing experiments")
12600 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12601 reporting for RNA sequencing experiments. It is easy to use and produces high
12602 quality reports. The inputs are reads files from the sequencing experiment,
12603 and a configuration file which describes the experiment. In addition to
12604 quality control of the experiment, the pipeline produces a differential
12605 expression report comparing samples in an easily configurable manner.")
12606 (license license:gpl3+)))
12608 (define-public pigx-chipseq
12610 (name "pigx-chipseq")
12614 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12615 "releases/download/v" version
12616 "/pigx_chipseq-" version ".tar.gz"))
12619 "0akbxdmsjsq5fzbwaap04hqjpsfgv1l6yrc2pwgbya1xgqvcq6vy"))))
12620 (build-system gnu-build-system)
12621 ;; parts of the tests rely on access to the network
12622 (arguments '(#:tests? #f))
12625 ("coreutils" ,coreutils)
12626 ("r-minimal" ,r-minimal)
12627 ("r-argparser" ,r-argparser)
12628 ("r-biocparallel" ,r-biocparallel)
12629 ("r-biostrings" ,r-biostrings)
12630 ("r-chipseq" ,r-chipseq)
12631 ("r-data-table" ,r-data-table)
12632 ("r-dplyr" ,r-dplyr)
12633 ("r-genomation" ,r-genomation)
12634 ("r-genomicalignments" ,r-genomicalignments)
12635 ("r-genomicranges" ,r-genomicranges)
12636 ("r-rsamtools" ,r-rsamtools)
12637 ("r-rtracklayer" ,r-rtracklayer)
12638 ("r-s4vectors" ,r-s4vectors)
12639 ("r-stringr" ,r-stringr)
12640 ("r-tibble" ,r-tibble)
12641 ("r-tidyr" ,r-tidyr)
12642 ("r-jsonlite" ,r-jsonlite)
12643 ("r-heatmaply" ,r-heatmaply)
12644 ("r-htmlwidgets" ,r-htmlwidgets)
12645 ("r-ggplot2" ,r-ggplot2)
12646 ("r-plotly" ,r-plotly)
12647 ("r-rmarkdown" ,r-rmarkdown)
12648 ("python-wrapper" ,python-wrapper)
12649 ("python-pyyaml" ,python-pyyaml)
12650 ("python-magic" ,python-magic)
12651 ("python-xlrd" ,python-xlrd)
12652 ("trim-galore" ,trim-galore)
12654 ("multiqc" ,multiqc)
12656 ("ghc-pandoc" ,ghc-pandoc)
12657 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12661 ("snakemake" ,snakemake)
12662 ("samtools" ,samtools)
12663 ("bedtools" ,bedtools)
12664 ("kentutils" ,kentutils)))
12666 `(("python-pytest" ,python-pytest)))
12667 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12668 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12669 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12670 calling and reporting for ChIP sequencing experiments. It is easy to use and
12671 produces high quality reports. The inputs are reads files from the sequencing
12672 experiment, and a configuration file which describes the experiment. In
12673 addition to quality control of the experiment, the pipeline enables to set up
12674 multiple peak calling analysis and allows the generation of a UCSC track hub
12675 in an easily configurable manner.")
12676 (license license:gpl3+)))
12678 (define-public pigx-bsseq
12680 (name "pigx-bsseq")
12684 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12685 "releases/download/v" version
12686 "/pigx_bsseq-" version ".tar.gz"))
12689 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12690 (build-system gnu-build-system)
12693 (modify-phases %standard-phases
12694 (add-before 'check 'set-timezone
12695 ;; The readr package is picky about timezones.
12696 (lambda* (#:key inputs #:allow-other-keys)
12697 (setenv "TZ" "UTC+1")
12699 (string-append (assoc-ref inputs "tzdata")
12700 "/share/zoneinfo"))
12703 `(("tzdata" ,tzdata)))
12705 `(("coreutils" ,coreutils)
12708 ("r-minimal" ,r-minimal)
12709 ("r-annotationhub" ,r-annotationhub)
12711 ("r-genomation" ,r-genomation)
12712 ("r-methylkit" ,r-methylkit)
12713 ("r-rtracklayer" ,r-rtracklayer)
12714 ("r-rmarkdown" ,r-rmarkdown)
12715 ("r-bookdown" ,r-bookdown)
12716 ("r-ggplot2" ,r-ggplot2)
12717 ("r-ggbio" ,r-ggbio)
12718 ("ghc-pandoc" ,ghc-pandoc)
12719 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12720 ("python-wrapper" ,python-wrapper)
12721 ("python-pyyaml" ,python-pyyaml)
12722 ("snakemake" ,snakemake)
12723 ("bismark" ,bismark)
12726 ("trim-galore" ,trim-galore)
12727 ("cutadapt" ,cutadapt)
12728 ("samtools" ,samtools)))
12729 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12730 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12731 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12732 data of bisulfite experiments; it produces reports on aggregate methylation
12733 and coverage and can be used to produce information on differential
12734 methylation and segmentation.")
12735 (license license:gpl3+)))
12737 (define-public pigx-scrnaseq
12739 (name "pigx-scrnaseq")
12743 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12744 "releases/download/v" version
12745 "/pigx_scrnaseq-" version ".tar.gz"))
12748 "0zv0sc5amivxhb95vx2gfx6l9bh7n80fh7h47dalnwxxnfvnzai4"))))
12749 (build-system gnu-build-system)
12751 `(#:configure-flags
12752 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12753 "/share/java/picard.jar")
12754 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12755 "/share/java/dropseq.jar"))))
12757 `(("coreutils" ,coreutils)
12759 ("dropseq-tools" ,dropseq-tools)
12761 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12762 ("java" ,icedtea-8)
12763 ("python-wrapper" ,python-wrapper)
12764 ("python-pyyaml" ,python-pyyaml)
12765 ("python-pandas" ,python-pandas)
12766 ("python-magic" ,python-magic)
12767 ("python-numpy" ,python-numpy)
12768 ("python-loompy" ,python-loompy-for-pigx-scrnaseq)
12769 ("ghc-pandoc" ,ghc-pandoc)
12770 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12771 ("samtools" ,samtools)
12772 ("snakemake" ,snakemake)
12774 ("r-minimal" ,r-minimal)
12775 ("r-argparser" ,r-argparser)
12776 ("r-cowplot" ,r-cowplot)
12777 ("r-data-table" ,r-data-table)
12778 ("r-delayedarray" ,r-delayedarray)
12779 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12780 ("r-dplyr" ,r-dplyr)
12781 ("r-dropbead" ,r-dropbead)
12783 ("r-genomicalignments" ,r-genomicalignments)
12784 ("r-genomicfiles" ,r-genomicfiles)
12785 ("r-genomicranges" ,r-genomicranges)
12786 ("r-ggplot2" ,r-ggplot2)
12787 ("r-hdf5array" ,r-hdf5array)
12788 ("r-pheatmap" ,r-pheatmap)
12789 ("r-rmarkdown" ,r-rmarkdown)
12790 ("r-rsamtools" ,r-rsamtools)
12791 ("r-rtracklayer" ,r-rtracklayer)
12792 ("r-rtsne" ,r-rtsne)
12793 ("r-scater" ,r-scater)
12794 ("r-scran" ,r-scran)
12795 ("r-singlecellexperiment" ,r-singlecellexperiment)
12796 ("r-stringr" ,r-stringr)
12797 ("r-yaml" ,r-yaml)))
12798 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12799 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12800 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12801 quality control for single cell RNA sequencing experiments. The inputs are
12802 read files from the sequencing experiment, and a configuration file which
12803 describes the experiment. It produces processed files for downstream analysis
12804 and interactive quality reports. The pipeline is designed to work with UMI
12806 (license license:gpl3+)))
12808 (define-public pigx
12814 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12815 "releases/download/v" version
12816 "/pigx-" version ".tar.gz"))
12819 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12820 (build-system gnu-build-system)
12822 `(("python" ,python)
12823 ("pigx-bsseq" ,pigx-bsseq)
12824 ("pigx-chipseq" ,pigx-chipseq)
12825 ("pigx-rnaseq" ,pigx-rnaseq)
12826 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12827 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12828 (synopsis "Analysis pipelines for genomics")
12829 (description "PiGx is a collection of genomics pipelines. It includes the
12830 following pipelines:
12833 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12834 @item PiGx RNAseq for RNAseq samples
12835 @item PiGx scRNAseq for single cell dropseq analysis
12836 @item PiGx ChIPseq for reads from ChIPseq experiments
12839 All pipelines are easily configured with a simple sample sheet and a
12840 descriptive settings file. The result is a set of comprehensive, interactive
12841 HTML reports with interesting findings about your samples.")
12842 (license license:gpl3+)))
12844 (define-public genrich
12850 (uri (git-reference
12851 (url "https://github.com/jsh58/Genrich.git")
12852 (commit (string-append "v" version))))
12855 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12856 (build-system gnu-build-system)
12858 `(#:tests? #f ; there are none
12860 (modify-phases %standard-phases
12861 (delete 'configure)
12863 (lambda* (#:key outputs #:allow-other-keys)
12864 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12868 (home-page "https://github.com/jsh58/Genrich")
12869 (synopsis "Detecting sites of genomic enrichment")
12870 (description "Genrich is a peak-caller for genomic enrichment
12871 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12872 following the assay and produces a file detailing peaks of significant
12874 (license license:expat)))
12876 (define-public mantis
12877 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12881 (version (git-version "0" revision commit))
12884 (uri (git-reference
12885 (url "https://github.com/splatlab/mantis.git")
12887 (file-name (git-file-name name version))
12890 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12891 (build-system cmake-build-system)
12892 (arguments '(#:tests? #f)) ; there are none
12894 `(("sdsl-lite" ,sdsl-lite)
12895 ("openssl" ,openssl)
12897 (home-page "https://github.com/splatlab/mantis")
12898 (synopsis "Large-scale sequence-search index data structure")
12899 (description "Mantis is a space-efficient data structure that can be
12900 used to index thousands of raw-read genomics experiments and facilitate
12901 large-scale sequence searches on those experiments. Mantis uses counting
12902 quotient filters instead of Bloom filters, enabling rapid index builds and
12903 queries, small indexes, and exact results, i.e., no false positives or
12904 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12905 representation, so it supports fast graph traversal and other topological
12906 analyses in addition to large-scale sequence-level searches.")
12907 ;; uses __uint128_t and inline assembly
12908 (supported-systems '("x86_64-linux"))
12909 (license license:bsd-3))))
12911 (define-public r-diversitree
12913 (name "r-diversitree")
12918 (uri (cran-uri "diversitree" version))
12921 "1jqfjmmaigq581l4zxysmkhld0xv6izlbr1hihf9zplkix36majc"))))
12922 (build-system r-build-system)
12924 `(("gfortran" ,gfortran)))
12925 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12928 ("r-desolve" ,r-desolve)
12930 ("r-subplex" ,r-subplex)))
12931 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
12932 (synopsis "Comparative 'phylogenetic' analyses of diversification")
12933 (description "This package contains a number of comparative \"phylogenetic\"
12934 methods, mostly focusing on analysing diversification and character evolution.
12935 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
12936 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
12937 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
12938 include Markov models of discrete and continuous trait evolution and constant
12939 rate speciation and extinction.")
12940 (license license:gpl2+)))
12942 (define-public sjcount
12943 ;; There is no tag for version 3.2, nor is there a release archive.
12944 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12948 (version (git-version "3.2" revision commit))
12951 (uri (git-reference
12952 (url "https://github.com/pervouchine/sjcount-full.git")
12954 (file-name (string-append name "-" version "-checkout"))
12957 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12958 (build-system gnu-build-system)
12960 `(#:tests? #f ; requires a 1.4G test file
12962 (list (string-append "SAMTOOLS_DIR="
12963 (assoc-ref %build-inputs "samtools")
12966 (modify-phases %standard-phases
12967 (replace 'configure
12968 (lambda* (#:key inputs #:allow-other-keys)
12969 (substitute* "makefile"
12970 (("-I \\$\\{SAMTOOLS_DIR\\}")
12971 (string-append "-I" (assoc-ref inputs "samtools")
12972 "/include/samtools"))
12973 (("-lz ") "-lz -lpthread "))
12976 (lambda* (#:key outputs #:allow-other-keys)
12977 (for-each (lambda (tool)
12979 (string-append (assoc-ref outputs "out")
12981 '("j_count" "b_count" "sjcount"))
12984 `(("samtools" ,samtools-0.1)
12986 (home-page "https://github.com/pervouchine/sjcount-full/")
12987 (synopsis "Annotation-agnostic splice junction counting pipeline")
12988 (description "Sjcount is a utility for fast quantification of splice
12989 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
12990 version does count multisplits.")
12991 (license license:gpl3+))))
12993 (define-public minimap2
13000 (uri (string-append "https://github.com/lh3/minimap2/"
13001 "releases/download/v" version "/"
13002 "minimap2-" version ".tar.bz2"))
13005 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13006 (build-system gnu-build-system)
13008 `(#:tests? #f ; there are none
13011 (let ((system ,(or (%current-target-system)
13012 (%current-system))))
13014 ((string-prefix? "x86_64" system)
13016 ((or (string-prefix? "armhf" system)
13017 (string-prefix? "aarch64" system))
13019 (_ "sse2only=1"))))
13021 (modify-phases %standard-phases
13022 (delete 'configure)
13024 (lambda* (#:key outputs #:allow-other-keys)
13025 (let* ((out (assoc-ref outputs "out"))
13026 (bin (string-append out "/bin"))
13027 (man (string-append out "/share/man/man1")))
13028 (install-file "minimap2" bin)
13030 (install-file "minimap2.1" man))
13034 (home-page "https://lh3.github.io/minimap2/")
13035 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13036 (description "Minimap2 is a versatile sequence alignment program that
13037 aligns DNA or mRNA sequences against a large reference database. Typical use
13041 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13042 @item finding overlaps between long reads with error rate up to ~15%;
13043 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13044 reads against a reference genome;
13045 @item aligning Illumina single- or paired-end reads;
13046 @item assembly-to-assembly alignment;
13047 @item full-genome alignment between two closely related species with
13048 divergence below ~15%.
13050 (license license:expat)))
13052 (define-public r-circus
13059 (uri (git-reference
13060 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13061 (commit (string-append "v" version))))
13062 (file-name (git-file-name name version))
13065 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13066 (build-system r-build-system)
13068 `(("r-annotationdbi" ,r-annotationdbi)
13069 ("r-annotationhub" ,r-annotationhub)
13070 ("r-biomart" ,r-biomart)
13071 ("r-data-table" ,r-data-table)
13073 ("r-genomicfeatures" ,r-genomicfeatures)
13074 ("r-genomicranges" ,r-genomicranges)
13075 ("r-ggplot2" ,r-ggplot2)
13077 ("r-iranges" ,r-iranges)
13078 ("r-rcolorbrewer" ,r-rcolorbrewer)
13079 ("r-rmysql" ,r-rmysql)
13080 ("r-s4vectors" ,r-s4vectors)
13081 ("r-stringr" ,r-stringr)
13082 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13084 `(("r-knitr" ,r-knitr)))
13085 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13086 (synopsis "Annotation, analysis and visualization of circRNA data")
13087 (description "Circus is an R package for annotation, analysis and
13088 visualization of circRNA data. Users can annotate their circRNA candidates
13089 with host genes, gene featrues they are spliced from, and discriminate between
13090 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13091 can be calculated, and a number of descriptive plots easily generated.")
13092 (license license:artistic2.0)))
13094 (define-public gffread
13095 ;; We cannot use the tagged release because it is not in sync with gclib.
13096 ;; See https://github.com/gpertea/gffread/issues/26
13097 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13101 (version (git-version "0.9.12" revision commit))
13105 (uri (git-reference
13106 (url "https://github.com/gpertea/gffread.git")
13108 (file-name (git-file-name name version))
13111 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13112 (build-system gnu-build-system)
13114 `(#:tests? #f ; no check target
13116 (list "GCLDIR=gclib")
13118 (modify-phases %standard-phases
13119 (delete 'configure)
13120 (add-after 'unpack 'copy-gclib-source
13121 (lambda* (#:key inputs #:allow-other-keys)
13123 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13125 ;; There is no install target
13127 (lambda* (#:key outputs #:allow-other-keys)
13128 (let* ((out (assoc-ref outputs "out"))
13129 (bin (string-append out "/bin")))
13130 (install-file "gffread" bin))
13134 ,(let ((version "0.10.3")
13135 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13139 (uri (git-reference
13140 (url "https://github.com/gpertea/gclib.git")
13142 (file-name (git-file-name "gclib" version))
13145 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13146 (home-page "https://github.com/gpertea/gffread/")
13147 (synopsis "Parse and convert GFF/GTF files")
13149 "This package provides a GFF/GTF file parsing utility providing format
13150 conversions, region filtering, FASTA sequence extraction and more.")
13151 ;; gffread is under Expat, but gclib is under Artistic 2.0
13152 (license (list license:expat
13153 license:artistic2.0)))))
13155 (define-public find-circ
13156 ;; The last release was in 2015. The license was clarified in 2017, so we
13157 ;; take the latest commit.
13158 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13162 (version (git-version "1.2" revision commit))
13166 (uri (git-reference
13167 (url "https://github.com/marvin-jens/find_circ.git")
13169 (file-name (git-file-name name version))
13172 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13173 (build-system gnu-build-system)
13175 `(#:tests? #f ; there are none
13177 ;; There is no actual build system.
13178 (modify-phases %standard-phases
13179 (delete 'configure)
13182 (lambda* (#:key outputs #:allow-other-keys)
13183 (let* ((out (assoc-ref outputs "out"))
13184 (bin (string-append out "/bin"))
13185 (path (getenv "PYTHONPATH")))
13186 (for-each (lambda (script)
13187 (install-file script bin)
13188 (wrap-program (string-append bin "/" script)
13189 `("PYTHONPATH" ":" prefix (,path))))
13194 "unmapped2anchors.py")))
13197 `(("python2" ,python-2)
13198 ("python2-pysam" ,python2-pysam)
13199 ("python2-numpy" ,python2-numpy)))
13200 (home-page "https://github.com/marvin-jens/find_circ")
13201 (synopsis "circRNA detection from RNA-seq reads")
13202 (description "This package provides tools to detect head-to-tail
13203 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13205 (license license:gpl3))))
13207 (define-public python-scanpy
13209 (name "python-scanpy")
13211 ;; Fetch from git because the pypi tarball does not include tests.
13215 (uri (git-reference
13216 (url "https://github.com/theislab/scanpy.git")
13218 (file-name (git-file-name name version))
13221 "0zn6x6c0cnm1a20i6isigwb51g3pr9zpjk8r1minjqnxi5yc9pm4"))))
13222 (build-system python-build-system)
13225 (modify-phases %standard-phases
13227 (lambda* (#:key inputs #:allow-other-keys)
13228 ;; These tests require Internet access.
13229 (delete-file-recursively "scanpy/tests/notebooks")
13230 (delete-file "scanpy/tests/test_clustering.py")
13232 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13233 (delete-file "scanpy/tests/test_plotting.py")
13234 (delete-file "scanpy/tests/test_preprocessing.py")
13235 (delete-file "scanpy/tests/test_read_10x.py")
13237 (setenv "PYTHONPATH"
13238 (string-append (getcwd) ":"
13239 (getenv "PYTHONPATH")))
13243 `(("python-anndata" ,python-anndata)
13244 ("python-h5py" ,python-h5py)
13245 ("python-igraph" ,python-igraph)
13246 ("python-joblib" ,python-joblib)
13247 ("python-louvain" ,python-louvain)
13248 ("python-matplotlib" ,python-matplotlib)
13249 ("python-natsort" ,python-natsort)
13250 ("python-networkx" ,python-networkx)
13251 ("python-numba" ,python-numba)
13252 ("python-pandas" ,python-pandas)
13253 ("python-scikit-learn" ,python-scikit-learn)
13254 ("python-scipy" ,python-scipy)
13255 ("python-seaborn" ,python-seaborn)
13256 ("python-statsmodels" ,python-statsmodels)
13257 ("python-tables" ,python-tables)))
13259 `(("python-pytest" ,python-pytest)))
13260 (home-page "https://github.com/theislab/scanpy")
13261 (synopsis "Single-Cell Analysis in Python.")
13262 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13263 expression data. It includes preprocessing, visualization, clustering,
13264 pseudotime and trajectory inference and differential expression testing. The
13265 Python-based implementation efficiently deals with datasets of more than one
13267 (license license:bsd-3)))
13269 (define-public python-bbknn
13271 (name "python-bbknn")
13276 (uri (pypi-uri "bbknn" version))
13279 "1qgdganvj3lyxj84v7alm23b9vqhwpn8z0115qndpnpy90qxynwz"))))
13280 (build-system python-build-system)
13282 `(("python-annoy" ,python-annoy)
13283 ("python-cython" ,python-cython)
13284 ("python-faiss" ,python-faiss)
13285 ("python-numpy" ,python-numpy)
13286 ("python-scanpy" ,python-scanpy)))
13287 (home-page "https://github.com/Teichlab/bbknn")
13288 (synopsis "Batch balanced KNN")
13289 (description "BBKNN is a batch effect removal tool that can be directly
13290 used in the Scanpy workflow. It serves as an alternative to
13291 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13292 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13293 technical artifacts are present in the data, they will make it challenging to
13294 link corresponding cell types across different batches. BBKNN actively
13295 combats this effect by splitting your data into batches and finding a smaller
13296 number of neighbours for each cell within each of the groups. This helps
13297 create connections between analogous cells in different batches without
13298 altering the counts or PCA space.")
13299 (license license:expat)))
13301 (define-public gffcompare
13302 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13305 (name "gffcompare")
13306 (version (git-version "0.10.15" revision commit))
13310 (uri (git-reference
13311 (url "https://github.com/gpertea/gffcompare/")
13313 (file-name (git-file-name name version))
13315 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13316 (build-system gnu-build-system)
13318 `(#:tests? #f ; no check target
13320 (modify-phases %standard-phases
13321 (delete 'configure)
13322 (add-before 'build 'copy-gclib-source
13323 (lambda* (#:key inputs #:allow-other-keys)
13326 (assoc-ref inputs "gclib-source") "../gclib")
13329 (lambda* (#:key outputs #:allow-other-keys)
13330 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13331 (install-file "gffcompare" bin)
13334 `(("gclib-source" ; see 'README.md' of gffcompare
13335 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13338 (version (git-version "0.10.3" revision commit)))
13341 (uri (git-reference
13342 (url "https://github.com/gpertea/gclib/")
13344 (file-name (git-file-name name version))
13346 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13347 (home-page "https://github.com/gpertea/gffcompare/")
13348 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13350 "@code{gffcompare} is a tool that can:
13352 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13353 (Cufflinks, Stringtie);
13354 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13355 resulted from assembly of different samples);
13356 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13357 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13361 license:expat ;license for gffcompare
13362 license:artistic2.0))))) ;license for gclib
13364 (define-public python-intervaltree
13366 (name "python-intervaltree")
13371 (uri (pypi-uri "intervaltree" version))
13374 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13375 (build-system python-build-system)
13376 ;; FIXME: error when collecting tests
13377 (arguments '(#:tests? #f))
13379 `(("python-sortedcontainers" ,python-sortedcontainers)))
13381 `(("python-pytest" ,python-pytest)))
13382 (home-page "https://github.com/chaimleib/intervaltree")
13383 (synopsis "Editable interval tree data structure")
13385 "This package provides a mutable, self-balancing interval tree
13386 implementation for Python. Queries may be by point, by range overlap, or by
13387 range envelopment. This library was designed to allow tagging text and time
13388 intervals, where the intervals include the lower bound but not the upper
13390 (license license:asl2.0)))
13392 (define-public python-pypairix
13394 (name "python-pypairix")
13399 (uri (pypi-uri "pypairix" version))
13402 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13403 (build-system python-build-system)
13404 ;; FIXME: the tests fail because test.support cannot be loaded:
13405 ;; ImportError: cannot import name 'support'
13406 (arguments '(#:tests? #f))
13409 (home-page "https://github.com/4dn-dcic/pairix")
13410 (synopsis "Support for querying pairix-indexed bgzipped text files")
13412 "Pypairix is a Python module for fast querying on a pairix-indexed
13413 bgzipped text file that contains a pair of genomic coordinates per line.")
13414 (license license:expat)))
13416 (define-public python-pyfaidx
13418 (name "python-pyfaidx")
13419 (version "0.5.4.2")
13423 (uri (pypi-uri "pyfaidx" version))
13426 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13427 (build-system python-build-system)
13429 `(("python-six" ,python-six)))
13430 (home-page "http://mattshirley.com")
13431 (synopsis "Random access to fasta subsequences")
13433 "This package provides procedures for efficient pythonic random access to
13434 fasta subsequences.")
13435 (license license:bsd-3)))
13437 (define-public python-cooler
13439 (name "python-cooler")
13444 (uri (pypi-uri "cooler" version))
13447 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13448 (build-system python-build-system)
13450 `(("python-biopython" ,python-biopython)
13451 ("python-click" ,python-click)
13452 ("python-cytoolz" ,python-cytoolz)
13453 ("python-dask" ,python-dask)
13454 ("python-h5py" ,python-h5py)
13455 ("python-multiprocess" ,python-multiprocess)
13456 ("python-pandas" ,python-pandas)
13457 ("python-pyfaidx" ,python-pyfaidx)
13458 ("python-pypairix" ,python-pypairix)
13459 ("python-pysam" ,python-pysam)
13460 ("python-scipy" ,python-scipy)))
13462 `(("python-mock" ,python-mock)
13463 ("python-nose" ,python-nose)
13464 ("python-numpydoc" ,python-numpydoc)
13465 ("python-sphinx" ,python-sphinx)))
13466 (home-page "https://github.com/mirnylab/cooler")
13467 (synopsis "Sparse binary format for genomic interaction matrices")
13469 "Cooler is a support library for a sparse, compressed, binary persistent
13470 storage format, called @code{cool}, used to store genomic interaction data,
13471 such as Hi-C contact matrices.")
13472 (license license:bsd-3)))
13474 (define-public python-hicexplorer
13476 (name "python-hicexplorer")
13480 ;; The latest version is not available on Pypi.
13482 (uri (git-reference
13483 (url "https://github.com/deeptools/HiCExplorer.git")
13485 (file-name (git-file-name name version))
13488 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13489 (build-system python-build-system)
13492 (modify-phases %standard-phases
13493 (add-after 'unpack 'loosen-up-requirements
13495 (substitute* "setup.py"
13499 `(("python-biopython" ,python-biopython)
13500 ("python-configparser" ,python-configparser)
13501 ("python-cooler" ,python-cooler)
13502 ("python-future" ,python-future)
13503 ("python-intervaltree" ,python-intervaltree)
13504 ("python-jinja2" ,python-jinja2)
13505 ("python-matplotlib" ,python-matplotlib)
13506 ("python-numpy" ,python-numpy)
13507 ("python-pandas" ,python-pandas)
13508 ("python-pybigwig" ,python-pybigwig)
13509 ("python-pysam" ,python-pysam)
13510 ("python-scipy" ,python-scipy)
13511 ("python-six" ,python-six)
13512 ("python-tables" ,python-tables)
13513 ("python-unidecode" ,python-unidecode)))
13514 (home-page "http://hicexplorer.readthedocs.io")
13515 (synopsis "Process, analyze and visualize Hi-C data")
13517 "HiCExplorer is a powerful and easy to use set of tools to process,
13518 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13519 contact matrices, correction of contacts, TAD detection, A/B compartments,
13520 merging, reordering or chromosomes, conversion from different formats
13521 including cooler and detection of long-range contacts. Moreover, it allows
13522 the visualization of multiple contact matrices along with other types of data
13523 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13524 genomic scores), long range contacts and the visualization of viewpoints.")
13525 (license license:gpl3)))
13527 (define-public python-pygenometracks
13529 (name "python-pygenometracks")
13534 (uri (pypi-uri "pyGenomeTracks" version))
13537 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13538 (build-system python-build-system)
13540 `(("python-configparser" ,python-configparser)
13541 ("python-future" ,python-future)
13542 ("python-hicexplorer" ,python-hicexplorer)
13543 ("python-intervaltree" ,python-intervaltree)
13544 ("python-matplotlib" ,python-matplotlib)
13545 ("python-numpy" ,python-numpy)
13546 ("python-pybigwig" ,python-pybigwig)))
13548 `(("python-pytest" ,python-pytest)))
13549 (home-page "https://pygenometracks.readthedocs.io")
13550 (synopsis "Program and library to plot beautiful genome browser tracks")
13552 "This package aims to produce high-quality genome browser tracks that
13553 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13554 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13555 pyGenomeTracks can make plots with or without Hi-C data.")
13556 (license license:gpl3+)))
13558 (define-public python-hic2cool
13560 (name "python-hic2cool")
13565 (uri (pypi-uri "hic2cool" version))
13568 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13569 (build-system python-build-system)
13570 (arguments '(#:tests? #f)) ; no tests included
13572 `(("python-cooler" ,python-cooler)))
13573 (home-page "https://github.com/4dn-dcic/hic2cool")
13574 (synopsis "Converter for .hic and .cool files")
13576 "This package provides a converter between @code{.hic} files (from
13577 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13578 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13580 (license license:expat)))
13582 (define-public r-pore
13590 (string-append "mirror://sourceforge/rpore/" version
13591 "/poRe_" version ".tar.gz"))
13593 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13594 (properties `((upstream-name . "poRe")))
13595 (build-system r-build-system)
13597 `(("r-bit64" ,r-bit64)
13598 ("r-data-table" ,r-data-table)
13599 ("r-rhdf5" ,r-rhdf5)
13600 ("r-shiny" ,r-shiny)
13601 ("r-svdialogs" ,r-svdialogs)))
13602 (home-page "https://sourceforge.net/projects/rpore/")
13603 (synopsis "Visualize Nanopore sequencing data")
13605 "This package provides graphical user interfaces to organize and visualize Nanopore
13607 ;; This is free software but the license variant is unclear:
13608 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13609 (license license:bsd-3)))
13611 (define-public r-xbioc
13612 (let ((revision "1")
13613 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13616 (version (git-version "0.1.16" revision commit))
13619 (uri (git-reference
13620 (url "https://github.com/renozao/xbioc.git")
13622 (file-name (git-file-name name version))
13625 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13626 (build-system r-build-system)
13628 `(("r-annotationdbi" ,r-annotationdbi)
13629 ("r-assertthat" ,r-assertthat)
13630 ("r-biobase" ,r-biobase)
13631 ("r-biocmanager" ,r-biocmanager)
13632 ("r-digest" ,r-digest)
13633 ("r-pkgmaker" ,r-pkgmaker)
13635 ("r-reshape2" ,r-reshape2)
13636 ("r-stringr" ,r-stringr)))
13637 (home-page "https://github.com/renozao/xbioc/")
13638 (synopsis "Extra base functions for Bioconductor")
13639 (description "This package provides extra utility functions to perform
13640 common tasks in the analysis of omics data, leveraging and enhancing features
13641 provided by Bioconductor packages.")
13642 (license license:gpl3+))))
13644 (define-public r-cssam
13645 (let ((revision "1")
13646 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13649 (version (git-version "1.4" revision commit))
13652 (uri (git-reference
13653 (url "https://github.com/shenorrLab/csSAM.git")
13655 (file-name (git-file-name name version))
13658 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13659 (build-system r-build-system)
13661 `(("r-formula" ,r-formula)
13662 ("r-ggplot2" ,r-ggplot2)
13663 ("r-pkgmaker" ,r-pkgmaker)
13665 ("r-rngtools" ,r-rngtools)
13666 ("r-scales" ,r-scales)))
13667 (home-page "https://github.com/shenorrLab/csSAM/")
13668 (synopsis "Cell type-specific statistical analysis of microarray")
13669 (description "This package implements the method csSAM that computes
13670 cell-specific differential expression from measured cell proportions using
13673 (license license:lgpl2.1+))))
13675 (define-public r-bseqsc
13676 (let ((revision "1")
13677 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13680 (version (git-version "1.0" revision commit))
13683 (uri (git-reference
13684 (url "https://github.com/shenorrLab/bseqsc.git")
13686 (file-name (git-file-name name version))
13689 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13690 (build-system r-build-system)
13692 `(("r-abind" ,r-abind)
13693 ("r-annotationdbi" ,r-annotationdbi)
13694 ("r-biobase" ,r-biobase)
13695 ("r-cssam" ,r-cssam)
13696 ("r-dplyr" ,r-dplyr)
13697 ("r-e1071" ,r-e1071)
13698 ("r-edger" ,r-edger)
13699 ("r-ggplot2" ,r-ggplot2)
13701 ("r-openxlsx" ,r-openxlsx)
13702 ("r-pkgmaker" ,r-pkgmaker)
13704 ("r-preprocesscore" ,r-preprocesscore)
13705 ("r-rngtools" ,r-rngtools)
13706 ("r-scales" ,r-scales)
13707 ("r-stringr" ,r-stringr)
13708 ("r-xbioc" ,r-xbioc)))
13709 (home-page "https://github.com/shenorrLab/bseqsc")
13710 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13711 (description "BSeq-sc is a bioinformatics analysis pipeline that
13712 leverages single-cell sequencing data to estimate cell type proportion and
13713 cell type-specific gene expression differences from RNA-seq data from bulk
13714 tissue samples. This is a companion package to the publication \"A
13715 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13716 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13717 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13718 (license license:gpl2+))))
13720 (define-public porechop
13721 ;; The recommended way to install is to clone the git repository
13722 ;; https://github.com/rrwick/Porechop#installation
13723 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13727 (version (git-version "0.2.3" revision commit))
13731 (uri (git-reference
13732 (url "https://github.com/rrwick/Porechop.git")
13734 (file-name (git-file-name name version))
13736 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13737 (build-system python-build-system)
13738 (home-page "https://github.com/rrwick/porechop")
13739 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13741 "The porechop package is a tool for finding and removing adapters from Oxford
13742 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13743 has an adapter in its middle, it is treated as chimeric and chopped into
13744 separate reads. Porechop performs thorough alignments to effectively find
13745 adapters, even at low sequence identity. Porechop also supports demultiplexing
13746 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13747 Barcoding Kit or Rapid Barcoding Kit.")
13748 (license license:gpl3+))))
13750 (define-public poretools
13751 ;; The latest release was in 2016 and the latest commit is from 2017
13752 ;; the recommended way to install is to clone the git repository
13753 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13754 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13758 (version (git-version "0.6.0" revision commit))
13762 (uri (git-reference
13763 (url "https://github.com/arq5x/poretools.git")
13765 (file-name (git-file-name name version))
13767 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13768 (build-system python-build-system)
13769 ;; requires python >=2.7, <3.0, and the same for python dependencies
13770 (arguments `(#:python ,python-2))
13774 `(("python-dateutil" ,python2-dateutil)
13775 ("python-h5py" ,python2-h5py)
13776 ("python-matplotlib" ,python2-matplotlib)
13777 ("python-pandas" ,python2-pandas)
13778 ("python-seaborn" ,python2-seaborn)))
13779 (home-page "https://poretools.readthedocs.io")
13780 (synopsis "Toolkit for working with nanopore sequencing data")
13782 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13783 This @code{poretools} package is a flexible toolkit for exploring datasets
13784 generated by nanopore sequencing devices for the purposes of quality control and
13785 downstream analysis. Poretools operates directly on the native FAST5, a variant
13786 of the Hierarchical Data Format (HDF5) standard.")
13787 (license license:expat))))
13789 (define-public r-absfiltergsea
13791 (name "r-absfiltergsea")
13796 (uri (cran-uri "AbsFilterGSEA" version))
13798 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13799 (properties `((upstream-name . "AbsFilterGSEA")))
13800 (build-system r-build-system)
13802 `(("r-biobase" ,r-biobase)
13803 ("r-deseq" ,r-deseq)
13804 ("r-limma" ,r-limma)
13806 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13807 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13808 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13810 "This package provides a function that performs gene-permuting of a gene-set
13811 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13812 Without filtering, users can perform (original) two-tailed or one-tailed
13814 (license license:gpl2)))
13816 (define-public jamm
13819 (version "1.0.7.5")
13823 (uri (git-reference
13824 (url "https://github.com/mahmoudibrahim/JAMM.git")
13825 (commit (string-append "JAMMv" version))))
13826 (file-name (git-file-name name version))
13829 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13830 (build-system gnu-build-system)
13832 `(#:tests? #f ; there are none
13834 (modify-phases %standard-phases
13835 (delete 'configure)
13838 (lambda* (#:key inputs outputs #:allow-other-keys)
13839 (let* ((out (assoc-ref outputs "out"))
13840 (libexec (string-append out "/libexec/jamm"))
13841 (bin (string-append out "/bin")))
13842 (substitute* '("JAMM.sh"
13843 "SignalGenerator.sh")
13845 (string-append "sPath=\"" libexec "\"\n")))
13846 (for-each (lambda (file)
13847 (install-file file libexec))
13848 (list "bincalculator.r"
13860 (chmod script #o555)
13861 (install-file script bin)
13862 (wrap-program (string-append bin "/" script)
13863 `("PATH" ":" prefix
13864 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13865 ,(string-append (assoc-ref inputs "gawk") "/bin")
13866 ,(string-append (assoc-ref inputs "perl") "/bin")
13867 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13868 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13869 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13870 (list "JAMM.sh" "SignalGenerator.sh")))
13874 ("coreutils" ,coreutils)
13877 ("r-minimal" ,r-minimal)
13878 ;;("r-parallel" ,r-parallel)
13879 ("r-signal" ,r-signal)
13880 ("r-mclust" ,r-mclust)))
13881 (home-page "https://github.com/mahmoudibrahim/JAMM")
13882 (synopsis "Peak finder for NGS datasets")
13884 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13885 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13886 boundaries accurately. JAMM is applicable to both broad and narrow
13888 (license license:gpl3+)))
13890 (define-public ngless
13897 (uri (git-reference
13898 (url "https://gitlab.com/ngless/ngless.git")
13899 (commit (string-append "v" version))))
13900 (file-name (git-file-name name version))
13903 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
13904 (build-system haskell-build-system)
13906 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13907 ; error: parse error on input import
13908 ; import Options.Applicative
13910 (modify-phases %standard-phases
13911 (add-after 'unpack 'create-cabal-file
13912 (lambda _ (invoke "hpack") #t))
13913 ;; These tools are expected to be installed alongside ngless.
13914 (add-after 'install 'link-tools
13915 (lambda* (#:key inputs outputs #:allow-other-keys)
13916 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13917 (symlink (string-append (assoc-ref inputs "prodigal")
13919 (string-append bin "ngless-" ,version "-prodigal"))
13920 (symlink (string-append (assoc-ref inputs "minimap2")
13922 (string-append bin "ngless-" ,version "-minimap2"))
13923 (symlink (string-append (assoc-ref inputs "samtools")
13925 (string-append bin "ngless-" ,version "-samtools"))
13926 (symlink (string-append (assoc-ref inputs "bwa")
13928 (string-append bin "ngless-" ,version "-bwa"))
13931 `(("prodigal" ,prodigal)
13933 ("samtools" ,samtools)
13934 ("minimap2" ,minimap2)
13935 ("ghc-aeson" ,ghc-aeson)
13936 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13937 ("ghc-async" ,ghc-async)
13938 ("ghc-atomic-write" ,ghc-atomic-write)
13939 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13940 ("ghc-chart" ,ghc-chart)
13941 ("ghc-chart-cairo" ,ghc-chart-cairo)
13942 ("ghc-conduit" ,ghc-conduit)
13943 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13944 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
13945 ("ghc-conduit-extra" ,ghc-conduit-extra)
13946 ("ghc-configurator" ,ghc-configurator)
13947 ("ghc-convertible" ,ghc-convertible)
13948 ("ghc-data-default" ,ghc-data-default)
13949 ("ghc-double-conversion" ,ghc-double-conversion)
13950 ("ghc-edit-distance" ,ghc-edit-distance)
13951 ("ghc-either" ,ghc-either)
13952 ("ghc-errors" ,ghc-errors)
13953 ("ghc-extra" ,ghc-extra)
13954 ("ghc-filemanip" ,ghc-filemanip)
13955 ("ghc-file-embed" ,ghc-file-embed)
13956 ("ghc-gitrev" ,ghc-gitrev)
13957 ("ghc-hashtables" ,ghc-hashtables)
13958 ("ghc-http-conduit" ,ghc-http-conduit)
13959 ("ghc-inline-c" ,ghc-inline-c)
13960 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13961 ("ghc-intervalmap" ,ghc-intervalmap)
13962 ("ghc-missingh" ,ghc-missingh)
13963 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13964 ("ghc-regex" ,ghc-regex)
13965 ("ghc-safe" ,ghc-safe)
13966 ("ghc-safeio" ,ghc-safeio)
13967 ("ghc-strict" ,ghc-strict)
13968 ("ghc-tar" ,ghc-tar)
13969 ("ghc-unliftio" ,ghc-unliftio)
13970 ("ghc-unliftio-core" ,ghc-unliftio-core)
13971 ("ghc-vector" ,ghc-vector)
13972 ("ghc-yaml" ,ghc-yaml)
13973 ("ghc-zlib" ,ghc-zlib)))
13976 ("r-hdf5r" ,r-hdf5r)
13977 ("r-iterators" ,r-iterators)
13978 ("r-itertools" ,r-itertools)
13979 ("r-matrix" ,r-matrix)))
13981 `(("ghc-hpack" ,ghc-hpack)
13982 ("ghc-quickcheck" ,ghc-quickcheck)
13983 ("ghc-test-framework" ,ghc-test-framework)
13984 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
13985 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
13986 ("ghc-test-framework-th" ,ghc-test-framework-th)))
13987 (home-page "https://gitlab.com/ngless/ngless")
13988 (synopsis "DSL for processing next-generation sequencing data")
13989 (description "Ngless is a domain-specific language for
13990 @dfn{next-generation sequencing} (NGS) data processing.")
13991 (license license:expat)))
13993 (define-public filtlong
13994 ;; The recommended way to install is to clone the git repository
13995 ;; https://github.com/rrwick/Filtlong#installation
13996 ;; and the lastest release is more than nine months old
13997 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14001 (version (git-version "0.2.0" revision commit))
14005 (uri (git-reference
14006 (url "https://github.com/rrwick/Filtlong.git")
14008 (file-name (git-file-name name version))
14010 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14011 (build-system gnu-build-system)
14013 `(#:tests? #f ; no check target
14015 (modify-phases %standard-phases
14016 (delete 'configure)
14018 (lambda* (#:key outputs #:allow-other-keys)
14019 (let* ((out (assoc-ref outputs "out"))
14020 (bin (string-append out "/bin"))
14021 (scripts (string-append out "/share/filtlong/scripts")))
14022 (install-file "bin/filtlong" bin)
14023 (install-file "scripts/histogram.py" scripts)
14024 (install-file "scripts/read_info_histograms.sh" scripts))
14026 (add-after 'install 'wrap-program
14027 (lambda* (#:key inputs outputs #:allow-other-keys)
14028 (let* ((out (assoc-ref outputs "out"))
14029 (path (getenv "PYTHONPATH")))
14030 (wrap-program (string-append out
14031 "/share/filtlong/scripts/histogram.py")
14032 `("PYTHONPATH" ":" prefix (,path))))
14034 (add-before 'check 'patch-tests
14036 (substitute* "scripts/read_info_histograms.sh"
14037 (("awk") (which "gawk")))
14040 `(("gawk" ,gawk) ;for read_info_histograms.sh
14041 ("python" ,python-2) ;required for histogram.py
14043 (home-page "https://github.com/rrwick/Filtlong/")
14044 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14046 "The Filtlong package is a tool for filtering long reads by quality.
14047 It can take a set of long reads and produce a smaller, better subset. It uses
14048 both read length (longer is better) and read identity (higher is better) when
14049 choosing which reads pass the filter.")
14050 (license (list license:gpl3 ;filtlong
14051 license:asl2.0))))) ;histogram.py
14053 (define-public nanopolish
14054 ;; The recommended way to install is to clone the git repository
14055 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14056 ;; Also, the differences between release and current version seem to be
14058 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14061 (name "nanopolish")
14062 (version (git-version "0.11.1" revision commit))
14066 (uri (git-reference
14067 (url "https://github.com/jts/nanopolish.git")
14070 (file-name (git-file-name name version))
14072 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14073 (modules '((guix build utils)))
14076 (delete-file-recursively "htslib")
14078 (build-system gnu-build-system)
14081 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14082 #:tests? #f ; no check target
14084 (modify-phases %standard-phases
14085 (add-after 'unpack 'find-eigen
14086 (lambda* (#:key inputs #:allow-other-keys)
14088 (string-append (assoc-ref inputs "eigen")
14090 (or (getenv "CPATH") "")))
14092 (delete 'configure)
14094 (lambda* (#:key outputs #:allow-other-keys)
14095 (let* ((out (assoc-ref outputs "out"))
14096 (bin (string-append out "/bin"))
14097 (scripts (string-append out "/share/nanopolish/scripts")))
14099 (install-file "nanopolish" bin)
14100 (for-each (lambda (file) (install-file file scripts))
14101 (find-files "scripts" ".*"))
14103 (add-after 'install 'wrap-programs
14104 (lambda* (#:key outputs #:allow-other-keys)
14105 (for-each (lambda (file)
14106 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14107 (find-files "/share/nanopolish/scripts" "\\.py"))
14108 (for-each (lambda (file)
14109 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14110 (find-files "/share/nanopolish/scripts" "\\.pl"))
14117 ("python" ,python-wrapper)
14118 ("python-biopython" ,python-biopython)
14119 ("python-numpy" ,python-numpy)
14120 ("python-pysam" ,python-pysam)
14121 ("python-scikit-learn" , python-scikit-learn)
14122 ("python-scipy" ,python-scipy)
14124 (home-page "https://github.com/jts/nanopolish")
14125 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14127 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14128 Nanopolish can calculate an improved consensus sequence for a draft genome
14129 assembly, detect base modifications, call SNPs (Single nucleotide
14130 polymorphisms) and indels with respect to a reference genome and more.")
14131 (license license:expat))))
14133 (define-public cnvkit
14140 (uri (git-reference
14141 (url "https://github.com/etal/cnvkit.git")
14142 (commit (string-append "v" version))))
14143 (file-name (git-file-name name version))
14145 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14146 (build-system python-build-system)
14148 `(("python-biopython" ,python-biopython)
14149 ("python-future" ,python-future)
14150 ("python-matplotlib" ,python-matplotlib)
14151 ("python-numpy" ,python-numpy)
14152 ("python-reportlab" ,python-reportlab)
14153 ("python-pandas" ,python-pandas)
14154 ("python-pysam" ,python-pysam)
14155 ("python-pyfaidx" ,python-pyfaidx)
14156 ("python-scipy" ,python-scipy)
14158 ("r-dnacopy" ,r-dnacopy)))
14159 (home-page "https://cnvkit.readthedocs.org/")
14160 (synopsis "Copy number variant detection from targeted DNA sequencing")
14162 "CNVkit is a Python library and command-line software toolkit to infer
14163 and visualize copy number from high-throughput DNA sequencing data. It is
14164 designed for use with hybrid capture, including both whole-exome and custom
14165 target panels, and short-read sequencing platforms such as Illumina and Ion
14167 (license license:asl2.0)))
14169 (define-public python-pyfit-sne
14171 (name "python-pyfit-sne")
14176 (uri (git-reference
14177 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14179 (file-name (git-file-name name version))
14181 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14182 (build-system python-build-system)
14184 `(("python-numpy" ,python-numpy)))
14188 `(("python-cython" ,python-cython)))
14189 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14190 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14192 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14193 method for dimensionality reduction and visualization of high dimensional
14194 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14195 approximate the gradient at each iteration of gradient descent. This package
14196 is a Cython wrapper for FIt-SNE.")
14197 (license license:bsd-4)))
14199 (define-public bbmap
14205 (uri (string-append
14206 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14209 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14210 (build-system ant-build-system)
14212 `(#:build-target "dist"
14213 #:tests? #f ; there are none
14215 (list (string-append "-Dmpijar="
14216 (assoc-ref %build-inputs "java-openmpi")
14218 #:modules ((guix build ant-build-system)
14220 (guix build java-utils))
14222 (modify-phases %standard-phases
14223 (add-after 'build 'build-jni-library
14225 (with-directory-excursion "jni"
14226 (invoke "make" "-f" "makefile.linux"))))
14227 ;; There is no install target
14228 (replace 'install (install-jars "dist"))
14229 (add-after 'install 'install-scripts-and-documentation
14230 (lambda* (#:key outputs #:allow-other-keys)
14231 (substitute* "calcmem.sh"
14232 (("\\| awk ") (string-append "| " (which "awk") " ")))
14233 (let* ((scripts (find-files "." "\\.sh$"))
14234 (out (assoc-ref outputs "out"))
14235 (bin (string-append out "/bin"))
14236 (doc (string-append out "/share/doc/bbmap"))
14237 (jni (string-append out "/lib/jni")))
14238 (substitute* scripts
14239 (("\\$DIR\"\"docs") doc)
14241 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14242 (("^NATIVELIBDIR.*")
14243 (string-append "NATIVELIBDIR=" jni "\n"))
14245 (string-append "CMD=\"" (which "java"))))
14246 (for-each (lambda (script) (install-file script bin)) scripts)
14248 ;; Install JNI library
14249 (install-file "jni/libbbtoolsjni.so" jni)
14251 ;; Install documentation
14252 (install-file "docs/readme.txt" doc)
14253 (copy-recursively "docs/guides" doc))
14258 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14259 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14260 ("java-openmpi" ,java-openmpi)))
14261 (home-page "http://sourceforge.net/projects/bbmap/")
14262 (synopsis "Aligner and other tools for short sequencing reads")
14264 "This package provides bioinformatic tools to align, deduplicate,
14265 reformat, filter and normalize DNA and RNA-seq data. It includes the
14266 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14267 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14268 simplify assemblies by removing duplicate or contained subsequences that share
14269 a target percent identity; Reformat, to convert reads between
14270 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14271 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14272 to an artifact/contaminant file.")
14273 (license license:bsd-3)))
14275 (define-public velvet
14281 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14282 "velvet_" version ".tgz"))
14285 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14286 ;; Delete bundled libraries
14287 (modules '((guix build utils)))
14290 (delete-file "Manual.pdf")
14291 (delete-file-recursively "third-party")
14293 (build-system gnu-build-system)
14295 `(#:make-flags '("OPENMP=t")
14296 #:test-target "test"
14298 (modify-phases %standard-phases
14299 (delete 'configure)
14300 (add-after 'unpack 'fix-zlib-include
14302 (substitute* "src/binarySequences.c"
14303 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14306 (lambda* (#:key outputs #:allow-other-keys)
14307 (let* ((out (assoc-ref outputs "out"))
14308 (bin (string-append out "/bin"))
14309 (doc (string-append out "/share/doc/velvet")))
14312 (install-file "velveth" bin)
14313 (install-file "velvetg" bin)
14314 (install-file "Manual.pdf" doc)
14315 (install-file "Columbus_manual.pdf" doc)
14318 `(("openmpi" ,openmpi)
14321 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14322 texlive-latex-hyperref)))))
14323 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14324 (synopsis "Nucleic acid sequence assembler for very short reads")
14326 "Velvet is a de novo genomic assembler specially designed for short read
14327 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14328 short read sequences, removes errors then produces high quality unique
14329 contigs. It then uses paired read information, if available, to retrieve the
14330 repeated areas between contigs.")
14331 (license license:gpl2+)))
14333 (define-public python-velocyto
14335 (name "python-velocyto")
14336 (version "0.17.17")
14340 (uri (pypi-uri "velocyto" version))
14343 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14344 (build-system python-build-system)
14346 `(("python-click" ,python-click)
14347 ("python-cython" ,python-cython)
14348 ("python-h5py" ,python-h5py)
14349 ("python-loompy" ,python-loompy)
14350 ("python-matplotlib" ,python-matplotlib)
14351 ("python-numba" ,python-numba)
14352 ("python-numpy" ,python-numpy)
14353 ("python-pandas" ,python-pandas)
14354 ("python-pysam" ,python-pysam)
14355 ("python-scikit-learn" ,python-scikit-learn)
14356 ("python-scipy" ,python-scipy)))
14357 (home-page "https://github.com/velocyto-team/velocyto.py")
14358 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14360 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14361 includes a command line tool and an analysis pipeline.")
14362 (license license:bsd-2)))
14364 (define-public arriba
14371 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14372 "download/v" version "/arriba_v" version ".tar.gz"))
14375 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14376 (build-system gnu-build-system)
14378 `(#:tests? #f ; there are none
14380 (modify-phases %standard-phases
14381 (replace 'configure
14382 (lambda* (#:key inputs #:allow-other-keys)
14383 (let ((htslib (assoc-ref inputs "htslib")))
14384 (substitute* "Makefile"
14385 (("-I\\$\\(HTSLIB\\)/htslib")
14386 (string-append "-I" htslib "/include/htslib"))
14387 ((" \\$\\(HTSLIB\\)/libhts.a")
14388 (string-append " " htslib "/lib/libhts.so"))))
14389 (substitute* "run_arriba.sh"
14390 (("^STAR ") (string-append (which "STAR") " "))
14391 (("samtools --version-only")
14392 (string-append (which "samtools") " --version-only"))
14393 (("samtools index")
14394 (string-append (which "samtools") " index"))
14396 (string-append (which "samtools") " sort")))
14399 (lambda* (#:key outputs #:allow-other-keys)
14400 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14401 (install-file "arriba" bin)
14402 (install-file "run_arriba.sh" bin)
14403 (install-file "draw_fusions.R" bin)
14404 (wrap-program (string-append bin "/draw_fusions.R")
14405 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14408 `(("htslib" ,htslib)
14409 ("r-minimal" ,r-minimal)
14410 ("r-circlize" ,r-circlize)
14411 ("r-genomicalignments" ,r-genomicalignments)
14412 ("r-genomicranges" ,r-genomicranges)
14413 ("samtools" ,samtools)
14416 (home-page "https://github.com/suhrig/arriba")
14417 (synopsis "Gene fusion detection from RNA-Seq data ")
14419 "Arriba is a command-line tool for the detection of gene fusions from
14420 RNA-Seq data. It was developed for the use in a clinical research setting.
14421 Therefore, short runtimes and high sensitivity were important design criteria.
14422 It is based on the fast STAR aligner and the post-alignment runtime is
14423 typically just around two minutes. In contrast to many other fusion detection
14424 tools which build on STAR, Arriba does not require to reduce the
14425 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14426 ;; All code is under the Expat license with the exception of
14427 ;; "draw_fusions.R", which is under GPLv3.
14428 (license (list license:expat license:gpl3))))
14430 (define-public adapterremoval
14432 (name "adapterremoval")
14437 (uri (git-reference
14438 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14439 (commit (string-append "v" version))))
14440 (file-name (git-file-name name version))
14443 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14444 (build-system gnu-build-system)
14446 `(#:make-flags (list "COLOR_BUILD=no"
14447 (string-append "PREFIX="
14448 (assoc-ref %outputs "out")))
14449 #:test-target "test"
14451 (modify-phases %standard-phases
14452 (delete 'configure))))
14455 (home-page "https://adapterremoval.readthedocs.io/")
14456 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14458 "This program searches for and removes remnant adapter sequences from
14459 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14460 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14461 analyze both single end and paired end data, and can be used to merge
14462 overlapping paired-ended reads into (longer) consensus sequences.
14463 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14464 sequence for paired-ended data, for which this information is not available.")
14465 (license license:gpl3+)))
14467 (define-public pplacer
14468 (let ((commit "807f6f3"))
14471 ;; The commit should be updated with each version change.
14472 (version "1.1.alpha19")
14476 (uri (git-reference
14477 (url "https://github.com/matsen/pplacer.git")
14478 (commit (string-append "v" version))))
14479 (file-name (git-file-name name version))
14481 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14482 (build-system ocaml-build-system)
14484 `(#:modules ((guix build ocaml-build-system)
14488 (modify-phases %standard-phases
14489 (delete 'configure)
14490 (add-after 'unpack 'fix-build-with-latest-ocaml
14492 (substitute* "myocamlbuild.ml"
14493 (("dep \\[\"c_pam\"\\]" m)
14494 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14496 (("let run_and_read" m)
14501 let pos = String.index s ch in
14502 x := (String.before s pos)::!x;
14503 go (String.after s (pos + 1))
14506 with Not_found -> !x
14507 let split_nl s = split s '\\n'
14508 let before_space s =
14509 try String.before s (String.index s ' ')
14510 with Not_found -> s
14513 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14514 (string-append "List.map before_space (split_nl & " m ")"))
14515 ((" blank_sep_strings &") "")
14516 ((" Lexing.from_string &") ""))
14518 (add-after 'unpack 'replace-bundled-cddlib
14519 (lambda* (#:key inputs #:allow-other-keys)
14520 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14521 (local-dir "cddlib_guix"))
14523 (with-directory-excursion local-dir
14524 (invoke "tar" "xvf" cddlib-src))
14525 (let ((cddlib-src-folder
14526 (string-append local-dir "/"
14527 (list-ref (scandir local-dir) 2)
14529 (for-each make-file-writable (find-files "cdd_src" ".*"))
14533 (string-append "cdd_src/" (basename file))))
14534 (find-files cddlib-src-folder ".*[ch]$")))
14536 (add-after 'unpack 'fix-makefile
14538 ;; Remove system calls to 'git'.
14539 (substitute* "Makefile"
14540 (("^DESCRIPT:=pplacer-.*")
14542 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14543 (substitute* "myocamlbuild.ml"
14544 (("git describe --tags --long .*\\\" with")
14546 "echo -n v" ,version "-" ,commit "\" with")))
14549 (lambda* (#:key outputs #:allow-other-keys)
14550 (let* ((out (assoc-ref outputs "out"))
14551 (bin (string-append out "/bin")))
14552 (copy-recursively "bin" bin))
14555 `(("zlib" ,zlib "static")
14557 ("ocaml-ounit" ,ocaml-ounit)
14558 ("ocaml-batteries" ,ocaml-batteries)
14559 ("ocaml-camlzip" ,camlzip)
14560 ("ocaml-csv" ,ocaml-csv)
14561 ("ocaml-sqlite3" ,ocaml-sqlite3)
14562 ("ocaml-xmlm" ,ocaml-xmlm)
14563 ("ocaml-mcl" ,ocaml-mcl)
14564 ("ocaml-gsl" ,ocaml-gsl-1)))
14566 `(("cddlib-src" ,(package-source cddlib))
14567 ("ocamlbuild" ,ocamlbuild)
14568 ("pkg-config" ,pkg-config)))
14570 `(("pplacer-scripts" ,pplacer-scripts)))
14571 (synopsis "Phylogenetic placement of biological sequences")
14573 "Pplacer places query sequences on a fixed reference phylogenetic tree
14574 to maximize phylogenetic likelihood or posterior probability according to a
14575 reference alignment. Pplacer is designed to be fast, to give useful
14576 information about uncertainty, and to offer advanced visualization and
14577 downstream analysis.")
14578 (home-page "http://matsen.fhcrc.org/pplacer")
14579 (license license:gpl3))))
14581 ;; This package is installed alongside 'pplacer'. It is a separate package so
14582 ;; that it can use the python-build-system for the scripts that are
14583 ;; distributed alongside the main OCaml binaries.
14584 (define pplacer-scripts
14587 (name "pplacer-scripts")
14588 (build-system python-build-system)
14590 `(#:python ,python-2
14592 (modify-phases %standard-phases
14593 (add-after 'unpack 'enter-scripts-dir
14594 (lambda _ (chdir "scripts") #t))
14596 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14597 (add-after 'install 'wrap-executables
14598 (lambda* (#:key inputs outputs #:allow-other-keys)
14599 (let* ((out (assoc-ref outputs "out"))
14600 (bin (string-append out "/bin")))
14601 (let ((path (string-append
14602 (assoc-ref inputs "hmmer") "/bin:"
14603 (assoc-ref inputs "infernal") "/bin")))
14605 (wrap-program (string-append bin "/refpkg_align.py")
14606 `("PATH" ":" prefix (,path))))
14607 (let ((path (string-append
14608 (assoc-ref inputs "hmmer") "/bin")))
14609 (wrap-program (string-append bin "/hrefpkg_query.py")
14610 `("PATH" ":" prefix (,path)))))
14613 `(("infernal" ,infernal)
14616 `(("python-biopython" ,python2-biopython)
14617 ("taxtastic" ,taxtastic)))
14618 (synopsis "Pplacer Python scripts")))
14620 (define-public python2-checkm-genome
14622 (name "python2-checkm-genome")
14627 (uri (pypi-uri "checkm-genome" version))
14630 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14631 (build-system python-build-system)
14633 `(#:python ,python-2
14634 #:tests? #f)) ; some tests are interactive
14636 `(("python-dendropy" ,python2-dendropy)
14637 ("python-matplotlib" ,python2-matplotlib)
14638 ("python-numpy" ,python2-numpy)
14639 ("python-pysam" ,python2-pysam)
14640 ("python-scipy" ,python2-scipy)))
14641 (home-page "http://pypi.python.org/pypi/checkm/")
14642 (synopsis "Assess the quality of putative genome bins")
14644 "CheckM provides a set of tools for assessing the quality of genomes
14645 recovered from isolates, single cells, or metagenomes. It provides robust
14646 estimates of genome completeness and contamination by using collocated sets of
14647 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14648 Assessment of genome quality can also be examined using plots depicting key
14649 genomic characteristics (e.g., GC, coding density) which highlight sequences
14650 outside the expected distributions of a typical genome. CheckM also provides
14651 tools for identifying genome bins that are likely candidates for merging based
14652 on marker set compatibility, similarity in genomic characteristics, and
14653 proximity within a reference genome.")
14654 (license license:gpl3+)))
14656 (define-public umi-tools
14663 (uri (pypi-uri "umi_tools" version))
14666 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14667 (build-system python-build-system)
14669 `(("python-pandas" ,python-pandas)
14670 ("python-future" ,python-future)
14671 ("python-scipy" ,python-scipy)
14672 ("python-matplotlib" ,python-matplotlib)
14673 ("python-regex" ,python-regex)
14674 ("python-pysam" ,python-pysam)))
14676 `(("python-cython" ,python-cython)))
14677 (home-page "https://github.com/CGATOxford/UMI-tools")
14678 (synopsis "Tools for analyzing unique modular identifiers")
14679 (description "This package provides tools for dealing with @dfn{Unique
14680 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14681 genetic sequences. There are six tools: the @code{extract} and
14682 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14683 cell barcodes for alignment. The remaining commands, @code{group},
14684 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14685 duplicates using the UMIs and perform different levels of analysis depending
14686 on the needs of the user.")
14687 (license license:expat)))
14689 (define-public ataqv
14696 (uri (git-reference
14697 (url "https://github.com/ParkerLab/ataqv.git")
14699 (file-name (git-file-name name version))
14702 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14703 (build-system gnu-build-system)
14706 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14707 (string-append "BOOST_ROOT="
14708 (assoc-ref %build-inputs "boost"))
14709 (string-append "HTSLIB_ROOT="
14710 (assoc-ref %build-inputs "htslib")))
14711 #:test-target "test"
14713 (modify-phases %standard-phases
14714 (delete 'configure))))
14718 ("ncurses" ,ncurses)
14722 (home-page "https://github.com/ParkerLab/ataqv")
14723 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14724 (description "This package provides a toolkit for measuring and comparing
14725 ATAC-seq results. It was written to make it easier to spot differences that
14726 might be caused by ATAC-seq library prep or sequencing. The main program,
14727 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14728 (license license:gpl3+)))
14730 (define-public r-psiplot
14737 (uri (git-reference
14738 (url "https://github.com/kcha/psiplot.git")
14739 (commit (string-append "v" version))))
14740 (file-name (git-file-name name version))
14742 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14743 (build-system r-build-system)
14745 `(("r-mass" ,r-mass)
14746 ("r-dplyr" ,r-dplyr)
14747 ("r-tidyr" ,r-tidyr)
14748 ("r-purrr" ,r-purrr)
14749 ("r-readr" ,r-readr)
14750 ("r-magrittr" ,r-magrittr)
14751 ("r-ggplot2" ,r-ggplot2)))
14752 (home-page "https://github.com/kcha/psiplot")
14753 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14755 "PSIplot is an R package for generating plots of @dfn{percent
14756 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
14757 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
14758 are generated using @code{ggplot2}.")
14759 (license license:expat)))
14761 (define-public python-ont-fast5-api
14763 (name "python-ont-fast5-api")
14768 (uri (git-reference
14769 (url "https://github.com/nanoporetech/ont_fast5_api.git")
14770 (commit (string-append "release_" version))))
14771 (file-name (git-file-name name version))
14774 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
14775 (build-system python-build-system)
14777 `(("python-numpy" ,python-numpy)
14778 ("python-six" ,python-six)
14779 ("python-h5py" ,python-h5py)
14780 ("python-progressbar33" ,python-progressbar33)))
14781 (home-page "https://github.com/nanoporetech/ont_fast5_api")
14782 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
14784 "This package provides a concrete implementation of the fast5 file schema
14785 using the generic @code{h5py} library, plain-named methods to interact with
14786 and reflect the fast5 file schema, and tools to convert between
14787 @code{multi_read} and @code{single_read} formats.")
14788 (license license:mpl2.0)))
14790 (define-public tbsp
14791 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
14795 (version (git-version "1.0.0" revision commit))
14799 (uri (git-reference
14800 (url "https://github.com/phoenixding/tbsp.git")
14804 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
14805 (build-system python-build-system)
14806 (arguments '(#:tests? #f)) ; no tests included
14808 `(("python-matplotlib" ,python-matplotlib)
14809 ("python-networkx" ,python-networkx)
14810 ("python-numpy" ,python-numpy)
14811 ("python-pybigwig" ,python-pybigwig)
14812 ("python-biopython" ,python-biopython)
14813 ("python-scikit-learn" ,python-scikit-learn)
14814 ("python-scipy" ,python-scipy)))
14815 (home-page "https://github.com/phoenixding/tbsp/")
14816 (synopsis "SNP-based trajectory inference")
14818 "Several studies focus on the inference of developmental and response
14819 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
14820 computational methods, often referred to as pseudo-time ordering, have been
14821 developed for this task. CRISPR has also been used to reconstruct lineage
14822 trees by inserting random mutations. The tbsp package implements an
14823 alternative method to detect significant, cell type specific sequence
14824 mutations from scRNA-Seq data.")
14825 (license license:expat))))
14827 (define-public tabixpp
14833 (uri (git-reference
14834 (url "https://github.com/ekg/tabixpp")
14835 (commit (string-append "v" version))))
14836 (file-name (git-file-name name version))
14838 (base32 "08vx6nsipk971cyr8z53rnzwkvlld63kcn1fw0pwddynz91xfny8"))))
14839 (build-system gnu-build-system)
14841 `(("htslib" ,htslib)
14844 `(#:tests? #f ; There are no tests to run.
14846 (modify-phases %standard-phases
14847 (delete 'configure) ; There is no configure phase.
14848 ;; The build phase needs overriding the location of htslib.
14850 (lambda* (#:key inputs #:allow-other-keys)
14851 (let ((htslib-ref (assoc-ref inputs "htslib")))
14853 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
14854 "HTS_HEADERS=" ; No need to check for headers here.
14855 (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
14857 (lambda* (#:key outputs #:allow-other-keys)
14858 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14859 (install-file "tabix++" bin))
14861 (home-page "https://github.com/ekg/tabixpp")
14862 (synopsis "C++ wrapper around tabix project")
14863 (description "This is a C++ wrapper around the Tabix project which abstracts
14864 some of the details of opening and jumping in tabix-indexed files.")
14865 (license license:expat)))
14867 (define tabixpp-freebayes
14868 ;; This version works with FreeBayes while the released
14869 ;; version doesn't. The released creates a variable with the name \"vcf\"
14870 ;; somewhere, which is also the name of a namespace in vcflib.
14871 (let ((commit "bbc63a49acc52212199f92e9e3b8fba0a593e3f7"))
14874 (name "tabixpp-freebayes")
14875 (version (git-version "0.0.0" "1" commit))
14878 (uri (git-reference
14879 (url "https://github.com/ekg/tabixpp/")
14881 (file-name (git-file-name name version))
14883 (base32 "017qsmsc2kyiyzqr9nl8cc6pfldxf16dbn8flx5i59mbqr9ydi7g")))))))
14885 (define-public smithwaterman
14886 ;; TODO: Upgrading smithwaterman breaks FreeBayes.
14887 (let ((commit "203218b47d45ac56ef234716f1bd4c741b289be1"))
14889 (name "smithwaterman")
14890 (version (string-append "0-1." (string-take commit 7)))
14893 (uri (git-reference
14894 (url "https://github.com/ekg/smithwaterman/")
14896 (file-name (git-file-name name version))
14898 (base32 "0z9xsmsv452kgdfbbwydyc6nymg3fwyv8zswls8qjin3r4ia4415"))))
14899 (build-system gnu-build-system)
14901 `(#:tests? #f ; There are no tests to run.
14903 (modify-phases %standard-phases
14904 (delete 'configure) ; There is no configure phase.
14906 (lambda* (#:key outputs #:allow-other-keys)
14907 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14908 (install-file "smithwaterman" bin))
14910 (home-page "https://github.com/ekg/smithwaterman")
14911 (synopsis "Implementation of the Smith-Waterman algorithm")
14912 (description "Implementation of the Smith-Waterman algorithm.")
14913 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
14914 (license (list license:gpl2 license:expat)))))
14916 (define-public multichoose
14918 (name "multichoose")
14922 (uri (git-reference
14923 (url "https://github.com/ekg/multichoose/")
14924 (commit (string-append "v" version))))
14925 (file-name (git-file-name name version))
14927 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
14928 (build-system gnu-build-system)
14930 `(#:tests? #f ; Tests require node.
14932 (modify-phases %standard-phases
14933 (delete 'configure) ; There is no configure phase.
14935 (lambda* (#:key outputs #:allow-other-keys)
14936 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14937 ;; TODO: There are Python modules for these programs too.
14938 (install-file "multichoose" bin)
14939 (install-file "multipermute" bin))
14941 (home-page "https://github.com/ekg/multichoose")
14942 (synopsis "Efficient loopless multiset combination generation algorithm")
14943 (description "This library implements an efficient loopless multiset
14944 combination generation algorithm which is (approximately) described in
14945 \"Loopless algorithms for generating permutations, combinations, and other
14946 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
14947 1973. (Algorithm 7.)")
14948 (license license:expat)))
14950 (define-public fsom
14951 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
14954 (version (git-version "0.0.0" "1" commit))
14957 (uri (git-reference
14958 (url "https://github.com/ekg/fsom/")
14960 (file-name (git-file-name name version))
14962 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
14963 (build-system gnu-build-system)
14965 `(#:tests? #f ; There are no tests to run.
14967 (modify-phases %standard-phases
14968 (delete 'configure) ; There is no configure phase.
14970 (lambda* (#:key outputs #:allow-other-keys)
14971 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14972 (install-file "fsom" bin))
14974 (home-page "https://github.com/ekg/fsom")
14975 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
14976 (description "A tiny C library for managing SOM (Self-Organizing Maps)
14978 (license license:gpl3))))
14980 (define-public fastahack
14981 (let ((commit "c68cebb4f2e5d5d2b70cf08fbdf1944e9ab2c2dd"))
14984 (version (git-version "0.0.0" "1" commit))
14987 (uri (git-reference
14988 (url "https://github.com/ekg/fastahack/")
14990 (file-name (git-file-name name version))
14992 (base32 "0hfdv67l9g611i2ck4l92pd6ygmsp9g1ph4zx1ni7qkpsikf0l19"))))
14993 (build-system gnu-build-system)
14995 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
14997 (modify-phases %standard-phases
14998 (delete 'configure) ; There is no configure phase.
15000 (lambda* (#:key outputs #:allow-other-keys)
15001 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15002 (install-file "fastahack" bin))
15004 (home-page "https://github.com/ekg/fastahack")
15005 (synopsis "Indexing and sequence extraction from FASTA files")
15006 (description "Fastahack is a small application for indexing and
15007 extracting sequences and subsequences from FASTA files. The included library
15008 provides a FASTA reader and indexer that can be embedded into applications
15009 which would benefit from directly reading subsequences from FASTA files. The
15010 library automatically handles index file generation and use.")
15011 (license (list license:expat license:gpl2)))))
15013 (define-public vcflib
15014 (let ((commit "5ac091365fdc716cc47cc5410bb97ee5dc2a2c92")
15018 (version (git-version "0.0.0" revision commit))
15022 (uri (git-reference
15023 (url "https://github.com/vcflib/vcflib/")
15025 (file-name (git-file-name name version))
15027 (base32 "1gijvcz1lcdn5kvgzb671l6iby0379qk00nqmcrszgk67hfwx6kq"))))
15028 (build-system gnu-build-system)
15033 ("python" ,python-2)
15035 ;; This package builds against the .o files so we need to extract the source.
15036 ("tabixpp-src" ,(package-source tabixpp-freebayes))
15037 ("smithwaterman-src" ,(package-source smithwaterman))
15038 ("multichoose-src" ,(package-source multichoose))
15039 ("fsom-src" ,(package-source fsom))
15040 ("filevercmp-src" ,(package-source filevercmp))
15041 ("fastahack-src" ,(package-source fastahack))
15042 ("intervaltree-src"
15045 (uri (git-reference
15046 (url "https://github.com/ekg/intervaltree/")
15047 (commit "dbb4c513d1ad3baac516fc1484c995daf9b42838")))
15048 (file-name "intervaltree-src-checkout")
15050 (base32 "1fy5qbj4bg8d2bjysvaa9wfnqn2rj2sk5yra2h4l5pzvy53f23fj"))))))
15052 `(#:tests? #f ; no tests
15054 (modify-phases %standard-phases
15055 (delete 'configure)
15057 (add-after 'unpack 'unpack-submodule-sources
15058 (lambda* (#:key inputs #:allow-other-keys)
15059 (let ((unpack (lambda (source target)
15060 (with-directory-excursion target
15061 (if (file-is-directory? (assoc-ref inputs source))
15062 (copy-recursively (assoc-ref inputs source) ".")
15063 (invoke "tar" "xvf"
15064 (assoc-ref inputs source)
15065 "--strip-components=1"))))))
15067 (unpack "intervaltree-src" "intervaltree")
15068 (unpack "fastahack-src" "fastahack")
15069 (unpack "filevercmp-src" "filevercmp")
15070 (unpack "fsom-src" "fsom")
15071 (unpack "multichoose-src" "multichoose")
15072 (unpack "smithwaterman-src" "smithwaterman")
15073 (unpack "tabixpp-src" "tabixpp")))))
15075 (lambda* (#:key inputs make-flags #:allow-other-keys)
15076 (with-directory-excursion "tabixpp"
15078 (invoke "make" "CC=gcc"
15079 (string-append "CFLAGS=\"" "-Itabixpp " "\"")
15082 (lambda* (#:key outputs #:allow-other-keys)
15083 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
15084 (lib (string-append (assoc-ref outputs "out") "/lib")))
15085 (for-each (lambda (file)
15086 (install-file file bin))
15087 (find-files "bin" ".*"))
15088 ;; The header files in src/ do not interface libvcflib,
15089 ;; therefore they are left out.
15090 (install-file "libvcflib.a" lib))
15092 (home-page "https://github.com/vcflib/vcflib/")
15093 (synopsis "Library for parsing and manipulating VCF files")
15094 (description "Vcflib provides methods to manipulate and interpret
15095 sequence variation as it can be described by VCF. It is both an API for parsing
15096 and operating on records of genomic variation as it can be described by the VCF
15097 format, and a collection of command-line utilities for executing complex
15098 manipulations on VCF files.")
15099 (license license:expat))))
15101 (define-public freebayes
15102 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15107 (version (git-version version revision commit))
15110 (uri (git-reference
15111 (url "https://github.com/ekg/freebayes.git")
15113 (file-name (git-file-name name version))
15115 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15116 (build-system gnu-build-system)
15118 `(("bamtools" ,bamtools)
15122 `(("bc" ,bc) ; Needed for running tests.
15123 ("samtools" ,samtools) ; Needed for running tests.
15124 ("parallel" ,parallel) ; Needed for running tests.
15125 ("perl" ,perl) ; Needed for running tests.
15126 ("procps" ,procps) ; Needed for running tests.
15127 ("python" ,python-2) ; Needed for running tests.
15128 ("vcflib-src" ,(package-source vcflib))
15129 ;; These are submodules for the vcflib version used in freebayes.
15130 ;; This package builds against the .o files so we need to extract the source.
15131 ("tabixpp-src" ,(package-source tabixpp-freebayes))
15132 ("smithwaterman-src" ,(package-source smithwaterman))
15133 ("multichoose-src" ,(package-source multichoose))
15134 ("fsom-src" ,(package-source fsom))
15135 ("filevercmp-src" ,(package-source filevercmp))
15136 ("fastahack-src" ,(package-source fastahack))
15137 ("intervaltree-src"
15140 (uri (git-reference
15141 (url "https://github.com/ekg/intervaltree/")
15142 (commit "dbb4c513d1ad3baac516fc1484c995daf9b42838")))
15143 (file-name "intervaltree-src-checkout")
15145 (base32 "1fy5qbj4bg8d2bjysvaa9wfnqn2rj2sk5yra2h4l5pzvy53f23fj"))))
15146 ;; These submodules are needed to run the tests.
15147 ("bash-tap-src" ,(package-source bash-tap))
15148 ("test-simple-bash-src"
15151 (uri (git-reference
15152 (url "https://github.com/ingydotnet/test-simple-bash/")
15153 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15154 (file-name "test-simple-bash-src-checkout")
15156 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15160 (string-append "BAMTOOLS_ROOT="
15161 (assoc-ref %build-inputs "bamtools")))
15162 #:test-target "test"
15164 (modify-phases %standard-phases
15165 (delete 'configure)
15166 (add-after 'unpack 'fix-tests
15168 (substitute* "test/t/01_call_variants.t"
15169 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15170 "grep -E ' (500|11000|1000)$'"))
15172 (add-after 'unpack 'unpack-submodule-sources
15173 (lambda* (#:key inputs #:allow-other-keys)
15174 (let ((unpack (lambda (source target)
15175 (with-directory-excursion target
15176 (if (file-is-directory? (assoc-ref inputs source))
15177 (copy-recursively (assoc-ref inputs source) ".")
15178 (invoke "tar" "xvf"
15179 (assoc-ref inputs source)
15180 "--strip-components=1"))))))
15182 (unpack "vcflib-src" "vcflib")
15183 (unpack "fastahack-src" "vcflib/fastahack")
15184 (unpack "filevercmp-src" "vcflib/filevercmp")
15185 (unpack "fsom-src" "vcflib/fsom")
15186 (unpack "intervaltree-src" "vcflib/intervaltree")
15187 (unpack "multichoose-src" "vcflib/multichoose")
15188 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15189 (unpack "tabixpp-src" "vcflib/tabixpp")
15190 (unpack "test-simple-bash-src" "test/test-simple-bash")
15191 (unpack "bash-tap-src" "test/bash-tap")))))
15192 (add-after 'unpack-submodule-sources 'fix-makefiles
15194 ;; We don't have the .git folder to get the version tag from.
15195 (substitute* "vcflib/Makefile"
15196 (("^GIT_VERSION.*")
15197 (string-append "GIT_VERSION = v" ,version)))
15198 (substitute* "src/Makefile"
15199 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15200 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15202 (add-before 'build 'build-tabixpp-and-vcflib
15203 (lambda* (#:key inputs make-flags #:allow-other-keys)
15204 (with-directory-excursion "vcflib"
15205 (with-directory-excursion "tabixpp"
15206 (apply invoke "make"
15207 (string-append "HTS_LIB="
15208 (assoc-ref inputs "htslib")
15211 (apply invoke "make"
15212 (string-append "CFLAGS=-Itabixpp")
15216 (lambda* (#:key outputs #:allow-other-keys)
15217 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15218 (install-file "bin/freebayes" bin)
15219 (install-file "bin/bamleftalign" bin))
15221 (home-page "https://github.com/ekg/freebayes")
15222 (synopsis "Haplotype-based variant detector")
15223 (description "FreeBayes is a Bayesian genetic variant detector designed to
15224 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15225 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15226 complex events (composite insertion and substitution events) smaller than the
15227 length of a short-read sequencing alignment.")
15228 (license license:expat))))
15230 (define-public samblaster
15232 (name "samblaster")
15236 (uri (git-reference
15237 (url "https://github.com/GregoryFaust/samblaster.git")
15238 (commit (string-append "v." version))))
15239 (file-name (git-file-name name version))
15242 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15243 (build-system gnu-build-system)
15245 `(#:tests? #f ; there are none
15247 (modify-phases %standard-phases
15248 (delete 'configure) ; There is no configure phase.
15250 (lambda* (#:key outputs #:allow-other-keys)
15251 (install-file "samblaster"
15252 (string-append (assoc-ref outputs "out") "/bin"))
15254 (home-page "https://github.com/GregoryFaust/samblaster")
15255 (synopsis "Mark duplicates in paired-end SAM files")
15256 (description "Samblaster is a fast and flexible program for marking
15257 duplicates in read-id grouped paired-end SAM files. It can also optionally
15258 output discordant read pairs and/or split read mappings to separate SAM files,
15259 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15260 duplicates, samblaster will require approximately 20MB of memory per 1M read
15262 (license license:expat)))
15264 (define-public r-velocyto
15265 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15268 (name "r-velocyto")
15269 (version (git-version "0.6" revision commit))
15273 (uri (git-reference
15274 (url "https://github.com/velocyto-team/velocyto.R.git")
15276 (file-name (git-file-name name version))
15279 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15280 (build-system r-build-system)
15282 `(("boost" ,boost)))
15284 `(("r-hdf5r" ,r-hdf5r)
15287 ("r-pcamethods" ,r-pcamethods)
15289 ("r-rcpparmadillo" ,r-rcpparmadillo)
15290 ;; Suggested packages
15291 ("r-rtsne" ,r-rtsne)
15292 ("r-cluster" ,r-cluster)
15293 ("r-abind" ,r-abind)
15295 ("r-biocgenerics" ,r-biocgenerics)
15296 ("r-genomicalignments" ,r-genomicalignments)
15297 ("r-rsamtools" ,r-rsamtools)
15298 ("r-edger" ,r-edger)
15299 ("r-igraph" ,r-igraph)))
15300 (home-page "http://velocyto.org")
15301 (synopsis "RNA velocity estimation in R")
15303 "This package provides basic routines for estimation of gene-specific
15304 transcriptional derivatives and visualization of the resulting velocity
15306 (license license:gpl3))))
15308 (define-public methyldackel
15310 (name "methyldackel")
15314 (uri (git-reference
15315 (url "https://github.com/dpryan79/MethylDackel.git")
15317 (file-name (git-file-name name version))
15320 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15321 (build-system gnu-build-system)
15323 `(#:test-target "test"
15326 (string-append "prefix="
15327 (assoc-ref %outputs "out") "/bin/"))
15329 (modify-phases %standard-phases
15330 (replace 'configure
15331 (lambda* (#:key outputs #:allow-other-keys)
15332 (substitute* "Makefile"
15333 (("install MethylDackel \\$\\(prefix\\)" match)
15334 (string-append "install -d $(prefix); " match)))
15337 `(("htslib" ,htslib)
15339 ;; Needed for tests
15341 `(("python" ,python-wrapper)))
15342 (home-page "https://github.com/dpryan79/MethylDackel")
15343 (synopsis "Universal methylation extractor for BS-seq experiments")
15345 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15346 file containing some form of BS-seq alignments and extract per-base
15347 methylation metrics from them. MethylDackel requires an indexed fasta file
15348 containing the reference genome as well.")
15349 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15350 (license license:expat)))