diff options
Diffstat (limited to 'gn')
| -rw-r--r-- | gn/packages/bioinformatics.scm | 462 |
1 files changed, 383 insertions, 79 deletions
diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index e6aa90f..276471b 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -14,16 +14,23 @@ #:use-module (guix build-system r) #:use-module (guix build-system trivial) #: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 cppcheck) + #: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) @@ -31,7 +38,11 @@ #: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) @@ -41,13 +52,13 @@ #: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 (gn packages statistics) #:use-module (srfi srfi-1)) (define-public freec @@ -100,6 +111,350 @@ 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 + `(#: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")) @@ -116,7 +471,8 @@ mappability data (files created by GEM). ") (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2")))) (build-system gnu-build-system) (inputs - `(("zlib" ,zlib))) + `(("zlib" ,zlib) + ("htslib" ,htslib))) (native-inputs `(("bc" ,bc) ; Needed for running tests. ("samtools" ,samtools) ; Needed for running tests. @@ -124,35 +480,19 @@ mappability data (files created by GEM). ") ("procps" ,procps) ; Needed for running tests. ("bamtools" ,bamtools) ("cmake" ,cmake) - ("htslib" ,htslib) ("python" ,python-2) + ("node" ,node) ("r" ,r) ("perl" ,perl) - ("bamtools-src" - ,(origin - (method url-fetch) - (uri (string-append "https://github.com/ekg/bamtools/archive/" - "e77a43f5097ea7eee432ee765049c6b246d49baa" ".tar.gz")) - (file-name "bamtools-src.tar.gz") - (sha256 - (base32 "0rqymka21g6lfjfgxzr40pxz4c4fcl77jpy1np1li70pnc7h2cs1")))) - ("vcflib-src" - ,(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")))) + ("bamtools-src" ,(package-source bamtools)) + ("vcflib-src" ,(package-source vcflib)) ;; These are submodules for the vcflib version used in freebayes - ("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")))) + ("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) @@ -162,55 +502,15 @@ mappability data (files created by GEM). ") (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")))) ;; These submodules are needed to run the tests. - ("bash-tap-src" - ,(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")))) + ("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) @@ -233,7 +533,7 @@ mappability data (files created by GEM). ") (and (unpack "bamtools-src" "bamtools") (unpack "vcflib-src" "vcflib") - (unpack "intervaltree-src" "intervaltree") + ;;(unpack "intervaltree-src" "intervaltree") (unpack "fastahack-src" "vcflib/fastahack") (unpack "filevercmp-src" "vcflib/filevercmp") (unpack "fsom-src" "vcflib/fsom") @@ -261,7 +561,11 @@ mappability data (files created by GEM). ") ;; Compile vcflib before we compiling the main project. (with-directory-excursion "vcflib" (with-directory-excursion "tabixpp" - (zero? (system* "make"))) + (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"))) |