aboutsummaryrefslogtreecommitdiff
path: root/gn/packages/bioinformatics.scm
diff options
context:
space:
mode:
Diffstat (limited to 'gn/packages/bioinformatics.scm')
-rw-r--r--gn/packages/bioinformatics.scm1125
1 files changed, 1005 insertions, 120 deletions
diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm
index 3629963..0798822 100644
--- a/gn/packages/bioinformatics.scm
+++ b/gn/packages/bioinformatics.scm
@@ -10,25 +10,40 @@
#:use-module (guix build-system cmake)
#:use-module (guix build-system perl)
#:use-module (guix build-system python)
- #:use-module (guix build-system ruby)
+ ;; #:use-module (guix build-system ruby)
#:use-module (guix build-system r)
#:use-module (guix build-system trivial)
+ #:use-module (gn packages statistics)
#:use-module (gnu packages)
+ #:use-module (gnu packages autotools)
#:use-module (gnu packages algebra)
#:use-module (gnu packages base)
#:use-module (gnu packages bioinformatics)
#:use-module (gnu packages boost)
#:use-module (gnu packages compression)
#:use-module (gnu packages databases)
+ #:use-module (gnu packages check)
+ #:use-module (gnu packages cmake)
+ #:use-module (gnu packages compression)
#:use-module (gnu packages cpio)
+ #:use-module (gnu packages curl)
+ #:use-module (gnu packages doxygen)
+ #:use-module (gnu packages datastructures)
+ #:use-module (gnu packages check)
#:use-module (gnu packages file)
+ #:use-module (gnu packages gawk)
#:use-module (gnu packages gcc)
#:use-module (gnu packages graphviz)
#:use-module (gnu packages java)
#:use-module (gnu packages linux)
+ #:use-module (gnu packages ldc)
#:use-module (gnu packages machine-learning)
#:use-module (gnu packages maths)
+ #:use-module (gnu packages mpi)
#:use-module (gnu packages ncurses)
+ #:use-module (gnu packages node)
+ #:use-module (gnu packages parallel)
+ #:use-module (gnu packages pcre)
#:use-module (gnu packages perl)
#:use-module (gnu packages pkg-config)
#:use-module (gnu packages popt)
@@ -38,90 +53,723 @@
#:use-module (gnu packages statistics)
#:use-module (gnu packages tbb)
#:use-module (gnu packages textutils)
+ #:use-module (gnu packages time)
+ #:use-module (gnu packages tls)
#:use-module (gnu packages vim)
#:use-module (gnu packages web)
#:use-module (gnu packages xml)
#:use-module (gnu packages zip)
#:use-module (gnu packages bootstrap)
- #:use-module (gn packages python)
#:use-module (srfi srfi-1))
-(define-public my-deploy
+(define-public contra
+ (package
+ (name "contra")
+ (version "2.0.6")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append
+ "mirror://sourceforge/contra-cnv/CONTRA.v" version ".tar.gz"))
+ (sha256
+ (base32
+ "0agpcm2xh5f0i9n9sx1kvln6mzdksddmh11bvzj6bh76yw5pnw91"))))
+ (build-system gnu-build-system)
+ (propagated-inputs
+ `(("python" ,python-2)
+ ("r" ,r)
+ ("r-dnacopy" ,r-dnacopy)
+ ("bedtools" ,bedtools)
+ ("samtools" ,samtools)))
+ (arguments
+ `(#:tests? #f ; There are no tests.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (delete 'build) ; We can use Guix's BEDtools instead.
+ (replace 'install
+ (lambda _
+ (let* ((out (assoc-ref %outputs "out"))
+ (bin (string-append out "/bin"))
+ (doc (string-append out "/share/doc/contra")))
+ (mkdir-p bin)
+ (mkdir-p doc)
+ (and
+ (zero? (system* "cp" "--recursive" "scripts" bin))
+ (zero? (system* "cp" "contra.py" bin))
+ (zero? (system* "cp" "baseline.py" bin))
+ ;; There's only a pre-built PDF available.
+ (zero? (system* "cp" "CONTRA_User_Guide.2.0.pdf" doc)))))))))
+ (home-page "http://contra-cnv.sourceforge.net/")
+ (synopsis "Tool for copy number variation (CNV) detection for targeted
+resequencing data")
+ (description "CONTRA is a tool for copy number variation (CNV) detection
+for targeted resequencing data such as those from whole-exome capture data.
+CONTRA calls copy number gains and losses for each target region with key
+strategies including the use of base-level log-ratios to remove GC-content
+bias, correction for an imbalanced library size effect on log-ratios, and the
+estimation of log-ratio variations via binning and interpolation. It takes
+standard alignment formats (BAM/SAM) and outputs in variant call format
+(VCF 4.0) for easy integration with other next generation sequencing analysis
+package.")
+ (license license:gpl3+)))
+
+(define boost-delly
+ (package (inherit boost)
+ (name "boost-delly")
+ (version "1.57.0")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append
+ "mirror://sourceforge/boost/boost_"
+ (string-map (lambda (x) (if (eq? x #\.) #\_ x)) version)
+ ".tar.bz2"))
+ (sha256
+ (base32
+ "0rs94vdmg34bwwj23fllva6mhrml2i7mvmlb11zyrk1k5818q34i"))))))
+
+(define-public delly
+ (package
+ (name "delly")
+ (version "0.7.2")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/tobiasrausch/delly/archive/v"
+ version ".tar.gz"))
+ (sha256
+ (base32 "173mmg43dbxqkyq0kiffz63xbmggr2kzd55mwxci9yfh5md1zprn"))
+ (patches (list (search-patch "delly-use-system-libraries.patch")))))
+ (build-system gnu-build-system)
+ (native-inputs
+ `(("python" ,python-2)))
+ (inputs
+ `(("boost" ,boost-delly) ; Use version 1.57.0 instead.
+ ("htslib" ,htslib)
+ ("zlib" ,zlib)
+ ("bzip2" ,bzip2)))
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ (replace 'install
+ (lambda _
+ (let ((bin (string-append (assoc-ref %outputs "out") "/bin")))
+ (install-file "src/cov" bin)
+ (install-file "src/delly" bin)
+ (install-file "src/extract" bin)
+ (install-file "src/iover" bin)
+ (install-file "src/stats" bin)))))))
+ (home-page "https://github.com/tobiasrausch/delly")
+ (synopsis "Integrated structural variant prediction method")
+ (description "Delly is an integrated structural variant prediction method
+that can discover and genotype deletions, tandem duplications, inversions and
+translocations at single-nucleotide resolution in short-read massively parallel
+sequencing data. It uses paired-ends and split-reads to sensitively and
+accurately delineate genomic rearrangements throughout the genome. Structural
+variants can be visualized using Delly-maze and Delly-suave.")
+ (license license:gpl3)))
+
+(define-public freec
(package
- (name "my-deploy")
- (version "0.0.1")
- (source #f)
+ (name "control-freec")
+ (version "8.7")
+ (source (origin
+ (method url-fetch)
+ (uri "http://bioinfo-out.curie.fr/projects/freec/src/FREEC_Linux64.tar.gz")
+ (file-name (string-append name "-" version ".tar.gz"))
+ (sha256
+ (base32 "12sl7gxbklhvv0687qjhml1z4lwpcn159zcyxvawvclsrzqjmv0h"))))
+ (build-system gnu-build-system)
+ ;; The source code's filename indicates only a 64-bit Linux build.
+ ;; We need to investigate whether this is true.
+ (supported-systems '("x86_64-linux"))
+ (arguments
+ `(#:phases
+ (modify-phases %standard-phases
+ ;; There's no configure phase because there are no external
+ ;; dependencies.
+ (delete 'configure)
+ ;; There are no tests.
+ (delete 'check)
+ (replace
+ 'unpack
+ (lambda* (#:key source #:allow-other-keys)
+ (and
+ (zero? (system* "mkdir" "source"))
+ (with-directory-excursion "source"
+ (zero? (system* "tar" "xvf" source))))))
+ (replace
+ 'build
+ (lambda* (#:key inputs #:allow-other-keys)
+ (with-directory-excursion "source"
+ (zero? (system* "make")))))
+ (replace
+ 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "source/freec" bin)))))))
+ (home-page "http://bioinfo-out.curie.fr/projects/freec/")
+ (synopsis "Tool for detection of copy-number changes and allelic imbalances
+(including LOH) using deep-sequencing data")
+ (description "Control-FREEC automatically computes, normalizes, segments
+copy number and beta allele frequency (BAF) profiles, then calls copy number
+alterations and LOH. The control (matched normal) sample is optional for whole
+genome sequencing data but mandatory for whole exome or targeted sequencing
+data. For whole genome sequencing data analysis, the program can also use
+mappability data (files created by GEM). ")
+ (license license:gpl2+)))
+
+(define-public tabixpp
+ (package
+ (name "tabixpp")
+ (version "1.0.0")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/tabixpp/archive/v"
+ version ".tar.gz"))
+ (file-name (string-append name "-" version ".tar.gz"))
+ (sha256
+ (base32 "1s0lgks7qlvlhvcjhi2wm18nnza1bwcnic44ij7z8wfg88h4ivwn"))))
+ (build-system gnu-build-system)
+ (inputs
+ `(("htslib" ,htslib)
+ ("zlib" ,zlib)))
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ ;; The build phase needs overriding the location of htslib.
+ (replace 'build
+ (lambda* (#:key inputs #:allow-other-keys)
+ (let ((htslib-ref (assoc-ref inputs "htslib")))
+ (zero?
+ (system* "make"
+ (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
+ "HTS_HEADERS=" ; No need to check for headers here.
+ (string-append "LIBPATH=-L. -L" htslib-ref "/include"))))))
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "tabix++" bin)))))))
+ (home-page "https://github.com/ekg/tabixpp")
+ (synopsis "C++ wrapper around tabix project")
+ (description "This is a C++ wrapper around the Tabix project which abstracts
+some of the details of opening and jumping in tabix-indexed files.")
+ (license license:expat)))
+
+;; This version works with FreeBayes while the released version doesn't. The
+;; released creates a variable with the name "vcf" somewhere, which is also the
+;; name of a namespace in vcflib.
+(define-public tabixpp-freebayes
+ (let ((commit "bbc63a49acc52212199f92e9e3b8fba0a593e3f7"))
+ (package (inherit tabixpp)
+ (name "tabixpp-freebayes")
+ (version (string-append "0-1." (string-take commit 7)))
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/tabixpp/archive/"
+ commit ".tar.gz"))
+ (file-name (string-append name "-" version "-checkout.tar.gz"))
+ (sha256
+ (base32 "1s06wmpgj4my4pik5kp2lc42hzzazbp5ism2y4i2ajp2y1c68g77")))))))
+
+(define-public smithwaterman
+ ;; TODO: Upgrading smithwaterman breaks FreeBayes.
+ (let ((commit "203218b47d45ac56ef234716f1bd4c741b289be1"))
+ (package
+ (name "smithwaterman")
+ (version (string-append "0-1." (string-take commit 7)))
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/smithwaterman/archive/"
+ commit ".tar.gz"))
+ (file-name (string-append name "-" version "-checkout.tar.gz"))
+ (sha256
+ (base32 "1lkxy4xkjn96l70jdbsrlm687jhisgw4il0xr2dm33qwcclzzm3b"))))
+ (build-system gnu-build-system)
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "smithwaterman" bin)))))))
+ (home-page "https://github.com/ekg/smithwaterman")
+ (synopsis "Implementation of the Smith-Waterman algorithm")
+ (description "Implementation of the Smith-Waterman algorithm.")
+ ;; The project contains a license file for the GPLv2. The source files
+ ;; do not contain a license notice, so GPLv2-only is assumed here.
+ (license license:gpl2))))
+
+(define-public multichoose
+ (package
+ (name "multichoose")
+ (version "1.0.3")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/multichoose/archive/v"
+ version ".tar.gz"))
+ (file-name (string-append name "-" version ".tar.gz"))
+ (sha256
+ (base32 "0xy86vvr3qrs4l81qis7ia1q2hnqv0xcb4a1n60smxbhqqis5w3l"))))
+ (build-system gnu-build-system)
+ (native-inputs
+ `(("python" ,python-2)
+ ("node" ,node)))
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ ;; TODO: There are Python modules for these programs too.
+ (install-file "multichoose" bin)
+ (install-file "multipermute" bin)))))))
+ (home-page "https://github.com/ekg/multichoose")
+ (synopsis "Library for efficient loopless multiset combination generation
+algorithm")
+ (description "A library implements an efficient loopless multiset
+combination generation algorithm which is (approximately) described in
+\"Loopless algorithms for generating permutations, combinations, and other
+combinatorial configurations.\" G Ehrlich - Journal of the ACM (JACM),
+1973. (Algorithm 7.)")
+ (license license:expat)))
+
+(define-public fsom
+ (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
+ (package
+ (name "fsom")
+ (version (string-append "0-1." (string-take commit 7)))
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/fsom/archive/"
+ "a6ef318fbd347c53189384aef7f670c0e6ce89a3" ".tar.gz"))
+ (file-name (string-append name "-" version "-checkout.tar.gz"))
+ (sha256
+ (base32 "0q6b57ppxfvsm5cqmmbfmjpn5qvx2zi5pamvp3yh8gpmmz8cfbl3"))))
+ (build-system gnu-build-system)
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "fsom" bin)))))))
+ (home-page "https://github.com/ekg/fsom")
+ (synopsis "Program for managing SOM (Self-Organizing Maps) neural networks")
+ (description "Program for managing SOM (Self-Organizing Maps) neural networks.")
+ (license license:gpl3))))
+
+(define-public filevercmp
+ (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
+ (package
+ (name "filevercmp")
+ (version (string-append "0-1." (string-take commit 7)))
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/filevercmp/archive/"
+ commit ".tar.gz"))
+ (file-name "filevercmp-src.tar.gz")
+ (sha256
+ (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
+ (build-system gnu-build-system)
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "filevercmp" bin)))))))
+ (home-page "https://github.com/ekg/filevercmp")
+ (synopsis "Program to compare version strings")
+ (description "A program to compare version strings. It intends to be a
+replacement for strverscmp.")
+ (license license:gpl3+))))
+
+(define-public fastahack
+ (let ((commit "c68cebb4f2e5d5d2b70cf08fbdf1944e9ab2c2dd"))
+ (package
+ (name "fastahack")
+ (version (string-append "0-1." (string-take commit 7)))
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/fastahack/archive/"
+ commit ".tar.gz"))
+ (file-name (string-append name "-" version "-checkout.tar.gz"))
+ (sha256
+ (base32 "0j25lcl3jk1kls66zzxjfyq5ir6sfcvqrdwfcva61y3ajc9ssay2"))))
+ (build-system gnu-build-system)
+ (arguments
+ `(#:tests? #f ; There are no tests to run.
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "fastahack" bin)))))))
+ (home-page "https://github.com/ekg/fastahack")
+ (synopsis "Program for indexing and sequence extraction from FASTA files")
+ (description "Fastahack is a small application for indexing and extracting
+sequences and subsequences from FASTA files. The included Fasta.cpp library
+provides a FASTA reader and indexer that can be embeddedinto applications which
+would benefit from directly reading subsequences from FASTA files. The library
+automatically handles index file generation and use.")
+ ;; There is no specific license for fastahack.
+ ;; A part of the program is licensed GPLv2.
+ (license (list license:non-copyleft license:gpl2)))))
+
+(define-public vcflib
+ (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb"))
+ (package
+ (name "vcflib")
+ (version (string-append "1.0.2-1." (string-take commit 7)))
+ (source
+ (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/vcflib/vcflib/archive/"
+ "5ac091365fdc716cc47cc5410bb97ee5dc2a2c92" ".tar.gz"))
+ (file-name "vcflib-5ac0913.tar.gz")
+ (sha256
+ (base32 "0ywshwpif059z5h0g7zzrdfzzdj2gr8xvwlwcsdxrms3p9iy35h8"))))
+ (build-system gnu-build-system)
+ (native-inputs
+ `(("htslib" ,htslib)
+ ("zlib" ,zlib)
+ ("python" ,python-2)
+ ("perl" ,perl)
+ ("r" ,r)
+ ("node" ,node)
+ ("tabixpp-src" ,(package-source tabixpp-freebayes))
+ ("smithwaterman-src" ,(package-source smithwaterman))
+ ("multichoose-src" ,(package-source multichoose))
+ ("fsom-src" ,(package-source fsom))
+ ("filevercmp-src" ,(package-source filevercmp))
+ ("fastahack-src" ,(package-source fastahack))
+ ("intervaltree-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append
+ "https://github.com/ekg/intervaltree/archive/"
+ "dbb4c513d1ad3baac516fc1484c995daf9b42838" ".tar.gz"))
+ (file-name "intervaltree-src.tar.gz")
+ (sha256
+ (base32 "19prwpn2wxsrijp5svfqvfcxl5nj7zdhm3jycd5kqhl9nifpmcks"))))))
+ (arguments
+ `(#:tests? #f
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (delete 'check)
+ (add-after 'unpack 'unpack-submodule-sources
+ (lambda* (#:key inputs #:allow-other-keys)
+ (let ((unpack (lambda (source target)
+ (with-directory-excursion target
+ (zero? (system* "tar" "xvf"
+ (assoc-ref inputs source)
+ "--strip-components=1"))))))
+ (and
+ (unpack "intervaltree-src" "intervaltree")
+ (unpack "fastahack-src" "fastahack")
+ (unpack "filevercmp-src" "filevercmp")
+ (unpack "fsom-src" "fsom")
+ (unpack "multichoose-src" "multichoose")
+ (unpack "smithwaterman-src" "smithwaterman")
+ (unpack "tabixpp-src" "tabixpp")))))
+ (add-after 'unpack-submodule-sources 'fix-makefile
+ (lambda* (#:key inputs #:allow-other-keys)
+ (substitute* '("Makefile")
+ (("^GIT_VERSION.*") "GIT_VERSION = v1.0.0"))))
+ (replace
+ 'build
+ (lambda* (#:key inputs make-flags #:allow-other-keys)
+ (with-directory-excursion "tabixpp"
+ (zero? (system* "make")))
+ (zero? (system* "make" "CC=gcc"
+ (string-append "CFLAGS=\"" "-Itabixpp "
+ "-I" (assoc-ref inputs "htslib") "/include " "\"") "all"))))
+ (replace
+ 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
+ ;;(include (string-append (assoc-ref outputs "out") "/include"))
+ (lib (string-append (assoc-ref outputs "out") "/lib")))
+ (for-each (lambda (file)
+ (install-file file bin))
+ (find-files "bin" ".*"))
+ ;; The header files do not correspond to libvcflib.a, therefore
+ ;; I left them out.
+ ;;(for-each (lambda (file)
+ ;; (install-file file include))
+ ;; (find-files "src" "\\.h$"))
+ (install-file "libvcflib.a" lib)))))))
+ (home-page "https://github.com/vcflib/vcflib/")
+ (synopsis "Library for parsing and manipulating VCF files")
+ (description "Vcflib provides methods to manipulate and interpret
+sequence variation as it can be described by VCF. It is both an API for parsing
+and operating on records of genomic variation as it can be described by the VCF
+format, and a collection of command-line utilities for executing complex
+manipulations on VCF files.")
+ (license license:expat))))
+
+(define-public bash-tap
+ (package
+ (name "bash-tap")
+ (version "1.0.2")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/illusori/bash-tap/archive/"
+ version ".tar.gz"))
+ (file-name (string-append name "-" version ".tar.gz"))
+ (sha256
+ (base32 "0qs1qi38bl3ns4mpagcawv618dsk2q1lgrbddgvs0wl3ia12cyz5"))))
(build-system trivial-build-system)
+ (native-inputs `(("source" ,source)
+ ("tar" ,tar)
+ ("gzip" ,gzip)))
(arguments
- `(#:guile ,%bootstrap-guile
- #:modules ((guix build utils))
- #:builder
- (let* ((out (assoc-ref %outputs "out"))
- (bash (assoc-ref %build-inputs "bash"))
- (foo (string-append out "/foo")))
- (begin
- (use-modules (guix build utils))
- (mkdir out)
- (call-with-output-file foo
- (lambda (p)
- (format p
- "#!~a~%echo \"${GUIX_FOO} ${GUIX_BAR}\"~%"
- bash)))
- (chmod foo #o777)
- ;; wrap-program uses `which' to find bash for the wrapper
- ;; shebang, but it can't know about the bootstrap bash in
- ;; the store, since it's not named "bash". Help it out a
- ;; bit by providing a symlink it this package's output.
- (symlink bash (string-append out "/bash"))
- (setenv "PATH" out)
- (wrap-program foo `("GUIX_FOO" prefix ("hello")))
- (wrap-program foo `("GUIX_BAR" prefix ("world")))
- #t))))
- (inputs `(("bash" ,(search-bootstrap-binary "bash"
- (%current-system)))))
+ `(#:modules ((guix build utils))
+ #:builder (begin
+ (use-modules (guix build utils))
+ (let ((tar (string-append (assoc-ref %build-inputs "tar") "/bin/tar"))
+ (path (string-append (assoc-ref %build-inputs "gzip") "/bin"))
+ (bin (string-append %output "/bin"))
+ (source (string-append (assoc-ref %build-inputs "source"))))
+ (setenv "PATH" path)
+ (mkdir-p bin)
+ (with-directory-excursion bin
+ (zero? (system* tar "xvf" source
+ "--strip-components=1"
+ "--no-anchored"
+ "bash-tap"
+ "bash-tap-bootstrap"
+ "bash-tap-mock")))))))
+ (home-page "http://www.illusori.co.uk/projects/bash-tap/")
+ (synopsis "Bash port of a Test::More/Test::Builder-style TAP-compliant
+test library")
+ (description "Bash TAP is a TAP-compliant Test::More-style testing library
+for Bash shell scripts and functions. Along with the Test::More-style testing
+helpers it provides helper functions for mocking commands and functions and
+in-process output capturing.")
+ ;; The author didn't specify a license.
+ (license license:public-domain)))
+
+(define-public freebayes
+ (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
+ (revision "1"))
+ (package
+ (name "freebayes")
+ (version (string-append "1.0.2-" revision "." (string-take commit 7)))
+ (source (origin
+ (method git-fetch)
+ (uri (git-reference
+ (url "https://github.com/ekg/freebayes.git")
+ (commit commit)))
+ (file-name (string-append name "-" version "-checkout"))
+ (sha256
+ (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
+ (build-system gnu-build-system)
+ (inputs
+ `(("zlib" ,zlib)
+ ("htslib" ,htslib)))
+ (native-inputs
+ `(("bc" ,bc) ; Needed for running tests.
+ ("samtools" ,samtools) ; Needed for running tests.
+ ("parallel" ,parallel) ; Needed for running tests.
+ ("procps" ,procps) ; Needed for running tests.
+ ("bamtools" ,bamtools)
+ ("cmake" ,cmake)
+ ("python" ,python-2)
+ ("node" ,node)
+ ("r" ,r)
+ ("perl" ,perl)
+ ("bamtools-src" ,(package-source bamtools))
+ ("vcflib-src" ,(package-source vcflib))
+ ;; These are submodules for the vcflib version used in freebayes
+ ("tabixpp-src" ,(package-source tabixpp-freebayes))
+ ("smithwaterman-src" ,(package-source smithwaterman))
+ ("multichoose-src" ,(package-source multichoose))
+ ("fsom-src" ,(package-source fsom))
+ ("filevercmp-src" ,(package-source filevercmp))
+ ("fastahack-src" ,(package-source fastahack))
+ ("intervaltree-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append
+ "https://github.com/ekg/intervaltree/archive/"
+ "dbb4c513d1ad3baac516fc1484c995daf9b42838" ".tar.gz"))
+ (file-name "intervaltree-src.tar.gz")
+ (sha256
+ (base32 "19prwpn2wxsrijp5svfqvfcxl5nj7zdhm3jycd5kqhl9nifpmcks"))))
+ ;; These submodules are needed to run the tests.
+ ("bash-tap-src" ,(package-source bash-tap))
+ ;; ,(origin
+ ;; (method url-fetch)
+ ;; (uri (string-append "https://github.com/illusori/bash-tap/archive/"
+ ;; "c38fbfa401600cc81ccda66bfc0da3ea56288d03" ".tar.gz"))
+ ;; (file-name "bash-tap-src.tar.gz")
+ ;; (sha256
+ ;; (base32 "07ijb1p0aa65ajpg9nkghc183iha6lwiydkckay8pghapa01j6nz"))))
+ ("test-simple-bash-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ingydotnet/test-simple-bash/archive/"
+ "124673ff204b01c8e96b7fc9f9b32ee35d898acc" ".tar.gz"))
+ (file-name "test-simple-bash-src.tar.gz")
+ (sha256
+ (base32 "016xf3wbgqbav9dncvfdx5k0f10z5xwq8jdszajzmcvnhz5wis14"))))))
+ (arguments
+ `(#:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (add-after 'unpack 'unpack-submodule-sources
+ (lambda* (#:key inputs #:allow-other-keys)
+ (let ((unpack (lambda (source target)
+ (with-directory-excursion target
+ (zero? (system* "tar" "xvf"
+ (assoc-ref inputs source)
+ "--strip-components=1"))))))
+ (and
+ (unpack "bamtools-src" "bamtools")
+ (unpack "vcflib-src" "vcflib")
+ ;;(unpack "intervaltree-src" "intervaltree")
+ (unpack "fastahack-src" "vcflib/fastahack")
+ (unpack "filevercmp-src" "vcflib/filevercmp")
+ (unpack "fsom-src" "vcflib/fsom")
+ (unpack "intervaltree-src" "vcflib/intervaltree")
+ (unpack "multichoose-src" "vcflib/multichoose")
+ (unpack "smithwaterman-src" "vcflib/smithwaterman")
+ (unpack "tabixpp-src" "vcflib/tabixpp")
+ (unpack "test-simple-bash-src" "test/test-simple-bash")
+ (unpack "bash-tap-src" "test/bash-tap")))))
+ (add-after 'unpack-submodule-sources 'fix-makefile
+ (lambda* (#:key inputs #:allow-other-keys)
+ ;; We don't have the .git folder to get the version tag from.
+ ;; For this checkout of the code, it's v1.0.0.
+ (substitute* '("vcflib/Makefile")
+ (("^GIT_VERSION.*") "GIT_VERSION = v1.0.0"))))
+ (replace 'build
+ (lambda* (#:key inputs make-flags #:allow-other-keys)
+ (and
+ ;; Compile Bamtools before compiling the main project.
+ (with-directory-excursion "bamtools"
+ (system* "mkdir" "build")
+ (with-directory-excursion "build"
+ (and (zero? (system* "cmake" "../"))
+ (zero? (system* "make")))))
+ ;; Compile vcflib before we compiling the main project.
+ (with-directory-excursion "vcflib"
+ (with-directory-excursion "tabixpp"
+ (let ((htslib-ref (assoc-ref inputs "htslib")))
+ (zero?
+ (system* "make" "HTS_HEADERS="
+ (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
+ (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
+ (zero? (system* "make" "CC=gcc"
+ (string-append "CFLAGS=\"" "-Itabixpp "
+ "-I" (assoc-ref inputs "htslib") "/include " "\"") "all")))
+ (with-directory-excursion "src"
+ (zero? (system* "make"))))))
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "bin/freebayes" bin)
+ (install-file "bin/bamleftalign" bin))))
+ ;; There are three tests that fail. All because of the -P
+ ;; (--perl-regexp) option in grep, which is not compiled into the
+ ;; version of grep in Guix.
+ (replace 'check
+ (lambda* (#:key inputs #:allow-other-keys)
+ (system* "make" "test"))))))
+ (home-page "https://github.com/ekg/freebayes")
+ (synopsis "Haplotype-based variant detector")
+ (description "FreeBayes is a Bayesian genetic variant detector designed to
+find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
+indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
+complex events (composite insertion and substitution events) smaller than the
+length of a short-read sequencing alignment.")
+ (license license:expat))))
- (home-page #f)
- (synopsis #f)
- (description #f)
- (license #f)))
+(define-public r-biocpreprocesscore
+ (package
+ (name "r-biocpreprocesscore")
+ (version "1.32.0")
+ (source (origin
+ (method url-fetch)
+ (uri (bioconductor-uri "preprocessCore" version))
+ (sha256
+ (base32
+ "07isghjkqm91rg37l1fzpjrbq36b7w4pbsi95wwh6a8qq7r69z1n"))))
+ (properties
+ `((upstream-name . "BiocpreprocessCore")
+ (r-repository . bioconductor)))
+ (build-system r-build-system)
+ (home-page "http://bioconductor.org/packages/preprocessCore")
+ (synopsis "Preprocess functions for Bioconductor")
+ (description
+ "A library of core preprocessing routines.")
+ (license license:lgpl2.0+)))
(define-public r-wgcna
+ (let ((commit "425bc170cc0873ddbd414675ac40f6d4d724c7cb"))
(package
(name "r-wgcna")
- (version "1.48")
- (source
- (origin
- (method url-fetch)
- (uri (cran-uri "WGCNA" version))
- (sha256
- (base32
- "18yl2v3s279saq318vd5hlwnqfm89rxmjjji778d2d26vviaf6bn"))))
+ (version (string-append "1.49-" commit))
+ (source (origin
+ (method git-fetch)
+ (uri (git-reference
+ ;; (url "https://github.com/genenetwork/WGCNA.git")
+ (url "https://github.com/pjotrp/WGCNA.git")
+ (commit commit)))
+ (file-name (string-append name "-" commit))
+ (sha256
+ (base32
+ "1zqnsb8s3065rq1y2y3l79zi8wmdwjkcjls96ypycrb7pmdil58j"))))
(properties `((upstream-name . "WGCNA")))
(build-system r-build-system)
- ;; (propagated-inputs
- ;; `( ;; ("r-annotationdbi" ,r-annotationdbi)
- ;; ("r-doparallel" ,r-doparallel)
- ;; ("r-dynamictreecut" ,r-dynamictreecut)
- ;; ("r-fastcluster" ,r-fastcluster)
- ;; ("r-foreach" ,r-foreach)
- ;; ("r-go.db" ,r-go.db)
- ;; ("r-grdevices" ,r-grdevices)
- ;; ("r-hmisc" ,r-hmisc)
- ;; ("r-impute" ,r-impute)
- ;; ("r-matrixstats" ,r-matrixstats)
- ;; ("r-parallel" ,r-parallel)
- ;; ("r-preprocesscore" ,r-preprocesscore)
- ;; ("r-splines" ,r-splines)
- ;; ("r-stats" ,r-stats)
- ;; ("r-survival" ,r-survival)
- ;; ("r-utils" ,r-utils)))
+ (propagated-inputs
+ `( ;; ("r-annotationdbi" ,r-annotationdbi)
+ ; ("r-biocparallel" ,r-biocparallel)
+ ("r-doparallel" ,r-doparallel)
+ ("r-dynamictreecut" ,r-dynamictreecut)
+ ("r-fastcluster" ,r-fastcluster)
+ ("r-foreach" ,r-foreach)
+ ("r-go-db" ,r-go-db)
+ ; ("r-grdevices" ,r-grdevices)
+ ("r-hmisc" ,r-hmisc)
+ ("r-impute" ,r-impute)
+ ("r-matrixstats" ,r-matrixstats)
+ ; ("r-parallel" ,r-parallel)
+ ("r-biocpreprocesscore" ,r-biocpreprocesscore)
+ ; ("r-splines" ,r-splines)
+ ; ("r-stats" ,r-stats)
+ ; ("r-survival" ,r-survival)
+ ; ("r-utils" ,r-utils)
+ ))
+ (arguments
+ `(
+ #:tests? #f)) ; no 'setup.py test'
(home-page
"http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
(synopsis
- "Weighted Correlation Network Analysis")
+ "Weighted gene correlation network analysis (wgcna)")
(description
- "Functions necessary to perform Weighted Correlation Network Analysis on high-dimensional data. Includes functions for rudimentary data cleaning, construction of correlation networks, module identification, summarization, and relating of variables and modules to sample traits. Also includes a number of utility functions for data manipulation and visualization.")
- (license license:gpl2+)))
+ "Functions necessary to perform Weighted Correlation Network
+Analysis on high-dimensional data. Includes functions for rudimentary
+data cleaning, construction of correlation networks, module
+identification, summarization, and relating of variables and modules
+to sample traits. Also includes a number of utility functions for
+data manipulation and visualization.")
+ (license license:gpl2+))))
(define-public qtlreaper
(package
@@ -156,7 +804,7 @@ test. For the permutation test, it performs only as many permutations
as are necessary to define the empirical P-value to a reasonable
precision. It also performs bootstrap resampling to estimate the
confidence region for the location of a putative QTL.")
- (license license:gpl2)))
+ (license license:gpl2+)))
(define-public plink2
(package
@@ -305,58 +953,100 @@ mixed model and some of its close relatives for genome-wide
association studies (GWAS).")
(license license:gpl3))))
-
-(define-public genenetwork1
- (let ((commit "d622c803b"))
- (package
- (name "genenetwork1")
- (version (string-append "1.0-" commit ))
- (source (origin
+(define-public sambamba
+ (let ((commit "c810c7ef14957f16288c205fd7b9d25c4ae7005d"))
+ ;;(let ((commit "2ca5a2dbac5ab90c3b4c588519edc3edcb71df84"))
+ (package
+ (name "sambamba")
+ (version (string-append "0.5.9-1." (string-take commit 7)))
+ (source (origin
+ (method git-fetch)
+ (uri (git-reference
+ (url "https://github.com/roelj/sambamba.git")
+ ;;(url "https://github.com/pjotrp/sambamba.git")
+ (commit commit)))
+ (file-name (string-append name "-" version "-checkout"))
+ (sha256
+ (base32
+ "0c4c13f021sl7mf5xc2v8dbwsz775n8dlsrrn7qa6qgbx05n54dv"))))
+ ;;"1f14wn9aaxwjkmla6pzq3s28741carbr2v0fd2v2mm1dcpwnrqz5"))))
+ (build-system gnu-build-system)
+ (native-inputs
+ `(("ldc" ,ldc)
+ ;;("lz4" ,lz4)
+ ("rdmd" ,rdmd)
+ ("zlib" ,zlib)
+ ("perl" ,perl) ; Needed for htslib
+ ("ruby" ,ruby) ; Needed for htslib
+ ("python" ,python) ; Needed for htslib
+ ("gcc" ,gcc)
+ ("lz4-src"
+ ,(origin
+ (method url-fetch)
+ (uri "https://github.com/Cyan4973/lz4/archive/160661c7a4cbf805f4af74d2e3932a17a66e6ce7.tar.gz")
+ (sha256
+ (base32 "131nnbsd5dh7c8sdqzc9kawh3mi0qi4qxznv7zhzfszlx4g2fd20"))))
+ ("htslib-src"
+ ,(origin
+ (method url-fetch)
+ (uri "https://github.com/lomereiter/htslib/archive/2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5.tar.gz")
+ ;;(uri "https://github.com/samtools/htslib/archive/1.3.tar.gz")
+ ;;(file-name "htslib-1.3.tar.gz")
+ (sha256
+ (base32 "0bl6w856afnbgdsw8bybsxpqsyf2ba3f12rqh47hhpxvv866g08w"))))
+ ;;(base32 "1bqkif7yrqmiqak5yb74kgpb2lsdlg7y344qa1xkdg7k1l4m86i9"))
+ ;;(patches (list (search-patch "htslib-add-cram_to_bam.patch")))))
+ ("biod-src"
+ ,(origin
(method git-fetch)
(uri (git-reference
- (url "https://github.com/genenetwork/genenetwork.git")
- ;; (url "https://github.com/pjotrp/genenetwork.git")
- (commit commit)))
- (file-name (string-append name "-" commit))
+ (url "https://github.com/biod/BioD.git")
+ (commit "7efdb8a2f7fdcd71c9ad9596be48d1262bb1bd5b")))
+ (file-name "biod-src")
(sha256
- (base32
- "14fzfcm4vl20mlhxjslfa01i1nmxpk8lbxmfvpq6dyfc22ir62py"))))
- (propagated-inputs `(
- ("python" ,python-2) ;; probably superfluous
- ("r" ,r)
- ))
- (inputs `(
- ;; http://spring211.uthsc.edu/gn/thirdparty.tbz
- ;; graphviz-2.22.2 htmlgen json numarray-1.5.2 piddle PIL pp-1.5.7 pyx pyXLWriter svg
- ("mysql" ,mysql)
- ("nginx" ,nginx)
- ("graphviz" ,graphviz)
- ; ("python2-jinja2" ,python2-jinja2)
- ; ("python2-sqlalchemy" ,python2-sqlalchemy)
- ; ("python2-setuptools" ,python2-setuptools)
- ; ("python2-scipy" ,python2-scipy)
- ;; looks like python-numarray is not needed
- ; ("python2-numpy" ,python2-numpy)
- ; ("python2-pandas" ,python2-pandas)
- ; ("python2-passlib" ,python2-passlib)
- ; ("python2-redis" ,python2-redis)
- ; ("python2-requests" ,python2-requests)
- ; ("python2-simplejson" ,python2-simplejson)
- ; ("python2-pyyaml" ,python2-pyyaml)
- ;; python-yolk is not needed
- ("python2-pil" ,python2-pil)
- ("python2-numarray" ,python2-numarray)
- ("plink" ,plink) ;; gn1
- ; ("r-qtl" ,r-qtl)
- ))
- (build-system python-build-system)
- (arguments
- `(#:python ,python-2
- #:tests? #f)) ; no 'setup.py test'
- (home-page "http://genenetwork.org/")
- (synopsis "Full genenetwork services")
- (description "Genenetwork installation sumo.")
- (license license:agpl3+))))
+ (base32 "09icc2bjsg9y4hxjim4ql275izadf0kh1nnmapg8manyz6bc8svf"))))))
+ (arguments
+ `(#:tests? #f
+ #:make-flags (list "-f" "Makefile.guix")
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (delete 'check)
+ (add-after 'unpack 'unpack-htslib-sources
+ (lambda* (#:key inputs #:allow-other-keys)
+ ;; The current build compiles htslib statically into the
+ ;; executable. On top of that, we need to patch the latest
+ ;; version of htslib to have it working with Sambamba.
+ (and (with-directory-excursion "htslib"
+ (zero? (system* "tar" "xvf" (assoc-ref inputs "htslib-src")
+ "--strip-components=1")))
+ (with-directory-excursion "lz4"
+ (zero? (system* "tar" "xvf" (assoc-ref inputs "lz4-src")
+ "--strip-components=1")))
+ (zero? (system* "rm" "-r" "BioD"))
+ (zero? (system* "ln" "--symbolic" "--no-target-directory"
+ (assoc-ref inputs "biod-src") "BioD")))))
+ (replace
+ 'build
+ (lambda* (#:key inputs make-flags #:allow-other-keys)
+ (zero? (system* "make" "sambamba-ldmd2-64" "CC=gcc" "D_COMPILER=ldc2"
+ (string-append "LDC_LIB_PATH="
+ (assoc-ref inputs "ldc")
+ "/lib")))))
+ (replace
+ 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "build/sambamba" bin)))))))
+ (home-page "https://github.com/lomereiter/sambamba")
+ (synopsis "A tool for working with SAM and BAM files written in D.")
+ (description
+ "Sambamba is a high performance modern robust and fast tool (and
+library), written in the D programming language, for working with SAM
+and BAM files. Current parallelised functionality is an important
+subset of samtools functionality, including view, index, sort,
+markdup, and depth.")
+ (license license:gpl2+))))
(define-public genenetwork2
(let ((commit "234aa9820eeaa3e4611239de31de1ba526d8bf09"))
@@ -412,9 +1102,204 @@ association studies (GWAS).")
))
(build-system python-build-system)
(arguments
- `(#:python ,python-2
- #:tests? #f)) ; no 'setup.py test'
- (home-page "http://genenetwork.org/")
- (synopsis "Full genenetwork services")
- (description "Genenetwork installation sumo.")
- (license license:agpl3+))))
+ `(("perl" ,perl) ; Needed to run the java command.
+ ("jdk" ,icedtea "jdk")))
+ (native-inputs
+ `(("ant" ,ant) ; TODO: Most Java packages need Ant, but in this case, IDK..
+ ("jdk" ,icedtea "jdk")
+ ;;("htsjdk" ,htsjdk) ; It is based on htsjdk, but it ships its own copy.
+ ("unzip" ,unzip)))
+ (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
+ (synopsis "A quality control tool for high throughput sequence data")
+ (description
+ "FastQC aims to provide a QC report which can spot problems which originate either in the sequencer or in the starting library material. It can either run as a stand alone interactive application for the immediate analysis of small numbers of FastQ files, or it can be run in a non-interactive mode where it would be suitable for integrating into a larger analysis pipeline for the systematic processing of large numbers of files.")
+ (license license:gpl3+)))
+
+(define-public vcflib
+ (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb"))
+ (package
+ (name "vcflib")
+ (version (string-append "v1.0.2-" (string-take commit 7)))
+ (source
+ (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/vcflib/vcflib/archive/"
+ "5ac091365fdc716cc47cc5410bb97ee5dc2a2c92" ".tar.gz"))
+ (file-name "vcflib-5ac0913.tar.gz")
+ (sha256
+ (base32 "0ywshwpif059z5h0g7zzrdfzzdj2gr8xvwlwcsdxrms3p9iy35h8"))))
+ (build-system gnu-build-system)
+ (native-inputs
+ `(("htslib" ,htslib)
+ ("zlib" ,zlib)
+ ("python" ,python-2)
+ ("perl" ,perl)
+ ("tabixpp-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/tabixpp/archive/"
+ "bbc63a49acc52212199f92e9e3b8fba0a593e3f7" ".tar.gz"))
+ (file-name "tabixpp-src.tar.gz")
+ (sha256
+ (base32 "1s06wmpgj4my4pik5kp2lc42hzzazbp5ism2y4i2ajp2y1c68g77"))))
+ ("intervaltree-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append
+ "https://github.com/ekg/intervaltree/archive/"
+ "dbb4c513d1ad3baac516fc1484c995daf9b42838" ".tar.gz"))
+ (file-name "intervaltree-src.tar.gz")
+ (sha256
+ (base32 "19prwpn2wxsrijp5svfqvfcxl5nj7zdhm3jycd5kqhl9nifpmcks"))))
+ ("smithwaterman-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/smithwaterman/archive/"
+ "203218b47d45ac56ef234716f1bd4c741b289be1" ".tar.gz"))
+ (file-name "smithwaterman-src.tar.gz")
+ (sha256
+ (base32 "1lkxy4xkjn96l70jdbsrlm687jhisgw4il0xr2dm33qwcclzzm3b"))))
+ ("multichoose-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/multichoose/archive/"
+ "73d35daa18bf35729b9ba758041a9247a72484a5" ".tar.gz"))
+ (file-name "multichoose-src.tar.gz")
+ (sha256
+ (base32 "07aizwdabmlnjaq4p3v0vsasgz1xzxid8xcxcw3paq8kh9c1099i"))))
+ ("fsom-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/fsom/archive/"
+ "a6ef318fbd347c53189384aef7f670c0e6ce89a3" ".tar.gz"))
+ (file-name "fsom-src.tar.gz")
+ (sha256
+ (base32 "0q6b57ppxfvsm5cqmmbfmjpn5qvx2zi5pamvp3yh8gpmmz8cfbl3"))))
+ ("filevercmp-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/filevercmp/archive/"
+ "1a9b779b93d0b244040274794d402106907b71b7" ".tar.gz"))
+ (file-name "filevercmp-src.tar.gz")
+ (sha256
+ (base32 "0yp5jswf5j2pqc6517x277s4s6h1ss99v57kxw9gy0jkfl3yh450"))))
+ ("fastahack-src"
+ ,(origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/ekg/fastahack/archive/"
+ "c68cebb4f2e5d5d2b70cf08fbdf1944e9ab2c2dd" ".tar.gz"))
+ (file-name "fastahack-src.tar.gz")
+ (sha256
+ (base32 "0j25lcl3jk1kls66zzxjfyq5ir6sfcvqrdwfcva61y3ajc9ssay2"))))))
+ (arguments
+ `(#:tests? #f
+ #:phases
+ (modify-phases %standard-phases
+ (delete 'configure)
+ (delete 'check)
+ (add-after 'unpack 'unpack-submodule-sources
+ (lambda* (#:key inputs #:allow-other-keys)
+ (let ((unpack (lambda (source target)
+ (with-directory-excursion target
+ (zero? (system* "tar" "xvf"
+ (assoc-ref inputs source)
+ "--strip-components=1"))))))
+ (and
+ (unpack "intervaltree-src" "intervaltree")
+ (unpack "fastahack-src" "fastahack")
+ (unpack "filevercmp-src" "filevercmp")
+ (unpack "fsom-src" "fsom")
+ (unpack "intervaltree-src" "intervaltree")
+ (unpack "multichoose-src" "multichoose")
+ (unpack "smithwaterman-src" "smithwaterman")
+ (unpack "tabixpp-src" "tabixpp")))))
+ (add-after 'unpack-submodule-sources 'fix-makefile
+ (lambda* (#:key inputs #:allow-other-keys)
+ (substitute* '("Makefile")
+ (("^GIT_VERSION.*") "GIT_VERSION = v1.0.0"))))
+ (replace
+ 'build
+ (lambda* (#:key inputs make-flags #:allow-other-keys)
+ (with-directory-excursion "tabixpp"
+ (zero? (system* "make")))
+ (zero? (system* "make" "CC=gcc"
+ (string-append "CFLAGS=\"" "-Itabixpp "
+ "-I" (assoc-ref inputs "htslib") "/include " "\"") "all"))))
+ (replace
+ 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
+ (lib (string-append (assoc-ref outputs "out") "/lib")))
+ (for-each (lambda (file)
+ (install-file file bin))
+ (find-files "bin" ".*"))
+ (install-file "libvcflib.a" lib)))))))
+ (home-page "https://github.com/vcflib/vcflib/")
+ (synopsis "Library for parsing and manipulating VCF files")
+ (description "Vcflib provides methods to manipulate and interpret
+sequence variation as it can be described by VCF. It is both an API for parsing
+and operating on records of genomic variation as it can be described by the VCF
+format, and a collection of command-line utilities for executing complex
+manipulations on VCF files.")
+ (license license:expat))))
+
+(define-public pindel
+ (package
+ (name "pindel")
+ (version "0.2.5b8")
+ (source (origin
+ (method url-fetch)
+ (uri (string-append "https://github.com/genome/pindel/archive/v"
+ version ".tar.gz"))
+ (file-name (string-append name "-" version ".tar.gz"))
+ (sha256
+ (base32 "06bsf0psxwf7h5p3j97xkh9k5qrwhxh6xn942y1j1m2inyhgs8bz"))))
+ (build-system gnu-build-system)
+ (inputs
+ `(("samtools" ,samtools)
+ ("htslib" ,htslib)
+ ("zlib" ,zlib)))
+ (native-inputs
+ `(("cppcheck" ,cppcheck)
+ ("python" ,python-2)
+ ("perl" ,perl)))
+ (arguments
+ `(#:phases
+ (modify-phases %standard-phases
+ (delete 'configure) ; There is no configure phase.
+ ;; The build phase needs to run 'make' twice for the reasons described
+ ;; below.
+ (replace 'build
+ (lambda* (#:key inputs #:allow-other-keys)
+ ;; The first run creates a Makefile.local file. Make will report
+ ;; the failure to find Makefile.local, but we can ignore this error.
+ (system* "make" (string-append "SAMTOOLS=" (assoc-ref inputs "samtools")))
+ ;; The second run actually compiles the program. Now Makefile.local
+ ;; is available, and we should treat an exiting make with an error as
+ ;; a true error.
+ (zero? (system* "make"))))
+ (replace 'install
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+ (install-file "src/pindel" bin)
+ (install-file "src/pindel2vcf" bin)
+ (install-file "src/pindel2vcf4tcga" bin)
+ (install-file "src/sam2pindel" bin))))
+ ;; There are multiple test targets, so in order to run all
+ ;; tests, we must run the separate make targets.
+ (replace 'check
+ (lambda* (#:key inputs #:allow-other-keys)
+ (and
+ (zero? (system* "make" "acceptance-tests"))
+ (zero? (system* "make" "coverage-tests"))
+ (zero? (system* "make" "cppcheck"))
+ (zero? (system* "make" "functional-tests"))
+ (zero? (system* "make" "regression-tests"))))))))
+ (home-page "https://github.com/genome/pindel")
+ (synopsis "Structural variants detector for next-gen sequencing data")
+ (description "Pindel can detect breakpoints of large deletions, medium sized
+insertions, inversions, tandem duplications and other structural variants at
+single-based resolution from next-gen sequence data. It uses a pattern growth
+approach to identify the breakpoints of these variants from paired-end short
+reads.")
+ (license license:gpl3+)))
generated by cgit v1.2.3 (git 2.44.0) at 2024-11-05 09:17:03 +0000