From 096a48cfaacefcefee2db5924a5fe97d4fda1125 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Thu, 25 Feb 2016 17:26:29 +0100 Subject: Added a WIP FreeBayes. --- gn/packages/bioinformatics.scm | 158 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 158 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index bf39935..cf79a08 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -48,6 +48,164 @@ #:use-module (gn packages statistics) #:use-module (srfi srfi-1)) +(define-public freebayes + (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")) + (package + (name "freebayes") + (version (string-append "v1.0.2-" (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) + (native-inputs + `(("cmake" ,cmake) + ("htslib" ,htslib) + ;;("openmpi" ,openmpi) + ("zlib" ,zlib) + ("python" ,python-2) + ("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 "https://github.com/vcflib/vcflib/archive/v1.0.0-rc1.tar.gz") + (file-name "vcflib-v1.0.0-rc1.tar.gz") + (sha256 + (base32 "0313cxnf77i74mz4xwkpdablw2a1nn7si9g5ar3kr0ipm02afizx")))) + ;; 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")))) + ("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 "bamtools-src" "bamtools") + (unpack "vcflib-src" "vcflib") + (unpack "intervaltree-src" "intervaltree") + (unpack "fastahack-src" "vcflib/fastahack") + (unpack "filevercmp-src" "vcflib/filevercmp") + (unpack "intervaltree-src" "vcflib/intervaltree") + (unpack "multichoose-src" "vcflib/multichoose") + (unpack "smithwaterman-src" "vcflib/smithwaterman") + (unpack "tabixpp-src" "vcflib/tabixpp"))))) + (replace + 'build + (lambda* (#:key inputs make-flags #:allow-other-keys) + (and + ;; We must compile Bamtools before we can compile the main + ;; project. + (with-directory-excursion "bamtools" + (system* "mkdir" "build") + (with-directory-excursion "build" + (and (zero? (system* "cmake" "../")) + (zero? (system* "make"))))) + ;; We must compile vcflib before we can compile the main + ;; project. + (with-directory-excursion "vcflib" + (with-directory-excursion "tabixpp" + (zero? (system* "make"))) + (zero? (system* "make" "CC=gcc" "-Itabixpp"))) + (zero? (system* "make" "src/version_git.h")) + (zero? (system* "make" "vcflib/Makefile"))))) + (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)))) + ;; (replace + ;; 'check + ;; (lambda* (#:key outputs #:allow-other-keys) + ;; (with-directory-excursion "test" + ;; (zero? (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:non-copyleft)))) + (define-public r-wgcna (package (name "r-wgcna") -- cgit v1.2.3 From 3d81b81500bca24e46bf83eb9750bdec19dd6862 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Mon, 29 Feb 2016 16:03:40 +0100 Subject: Reverted htslib for Sambamba to the repository's version. --- gn/packages/bioinformatics.scm | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index cf79a08..3d27a72 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -495,11 +495,14 @@ and freshness without requiring additional information from the user.") ("htslib-src" ,(origin (method url-fetch) - (uri "https://github.com/samtools/htslib/archive/1.3.tar.gz") - (file-name "htslib-1.3.tar.gz") + (uri (string-append "https://github.com/lomereiter/htslib/archive/" + "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5" ".tar.gz")) + ;;(uri "https://github.com/samtools/htslib/archive/1.3.tar.gz") + (file-name "htslib-2f3c3ea7b.tar.gz") (sha256 - (base32 "1bqkif7yrqmiqak5yb74kgpb2lsdlg7y344qa1xkdg7k1l4m86i9")) - (patches (list (search-patch "htslib-add-cram_to_bam.patch"))))) + (base32 "0bl6w856afnbgdsw8bybsxpqsyf2ba3f12rqh47hhpxvv866g08w")))) + ;;(base32 "1bqkif7yrqmiqak5yb74kgpb2lsdlg7y344qa1xkdg7k1l4m86i9")) + ;;(patches (list (search-patch "htslib-add-cram_to_bam.patch"))))) ("biod-src" ,(origin (method git-fetch) -- cgit v1.2.3 From 8dba0e74b31d02cf42fee9b9d93d1a3070cc0b24 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Tue, 1 Mar 2016 13:27:23 +0100 Subject: Add freebayes. --- gn/packages/bioinformatics.scm | 167 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 167 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index ea4bf91..ffa28ae 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -20,6 +20,7 @@ #:use-module (gnu packages boost) #:use-module (gnu packages compression) #:use-module (gnu packages databases) + #:use-module (gnu packages cmake) #:use-module (gnu packages cpio) #:use-module (gnu packages file) #:use-module (gnu packages gcc) @@ -48,6 +49,172 @@ #:use-module (gn packages statistics) #:use-module (srfi srfi-1)) +(define-public freebayes + (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")) + (package + (name "freebayes") + (version (string-append "v1.0.2-" (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) + (native-inputs + `(("cmake" ,cmake) + ("htslib" ,htslib) + ("zlib" ,zlib) + ("python" ,python-2) + ("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")))) + ;; 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")))) + ("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 "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"))))) + (add-after 'unpack-submodule-sources 'fix-makefile + (lambda* (#:key inputs #:allow-other-keys) + (substitute* '("vcflib/Makefile") + (("^GIT_VERSION.*") "GIT_VERSION = v1.0.0")))) + (replace + 'build + (lambda* (#:key inputs make-flags #:allow-other-keys) + (and + ;; We must compile Bamtools before we can compile the main + ;; project. + (with-directory-excursion "bamtools" + (system* "mkdir" "build") + (with-directory-excursion "build" + (and (zero? (system* "cmake" "../")) + (zero? (system* "make"))))) + ;; We must compile vcflib before we can compile the main + ;; project. + (with-directory-excursion "vcflib" + (with-directory-excursion "tabixpp" + (zero? (system* "make"))) + (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)))) + ;; (replace + ;; 'check + ;; (lambda* (#:key outputs #:allow-other-keys) + ;; (with-directory-excursion "test" + ;; (zero? (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:non-copyleft)))) + (define-public r-biocpreprocesscore (package (name "r-biocpreprocesscore") -- cgit v1.2.3 From 66fc6e38aa7326b49fb79790ba885ab77205b742 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Tue, 1 Mar 2016 13:48:46 +0100 Subject: Changed Sambamba source. --- gn/packages/bioinformatics.scm | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index ffa28ae..12a4bcb 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -470,19 +470,22 @@ association studies (GWAS).") (license license:gpl3)))) (define-public sambamba - (let ((commit "2ca5a2dbac5ab90c3b4c588519edc3edcb71df84")) + (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/pjotrp/sambamba.git") + (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 - "1f14wn9aaxwjkmla6pzq3s28741carbr2v0fd2v2mm1dcpwnrqz5")))) + "0c4c13f021sl7mf5xc2v8dbwsz775n8dlsrrn7qa6qgbx05n54dv")))) + ;;"1f14wn9aaxwjkmla6pzq3s28741carbr2v0fd2v2mm1dcpwnrqz5")))) (build-system gnu-build-system) (native-inputs `(("ldc" ,ldc) @@ -500,6 +503,7 @@ association studies (GWAS).") "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5" ".tar.gz")) ;;(uri "https://github.com/samtools/htslib/archive/1.3.tar.gz") (file-name "htslib-2f3c3ea7b.tar.gz") + ;;(file-name "htslib-1.3.tar.gz") (sha256 (base32 "0bl6w856afnbgdsw8bybsxpqsyf2ba3f12rqh47hhpxvv866g08w")))) ;;(base32 "1bqkif7yrqmiqak5yb74kgpb2lsdlg7y344qa1xkdg7k1l4m86i9")) @@ -535,7 +539,7 @@ association studies (GWAS).") 'build (lambda* (#:key inputs make-flags #:allow-other-keys) (zero? (system* "make" "-f" "Makefile.guix" - (string-append "LDC_LIB_PATH=" + (string-append "LDC_LIB_PATH=" (assoc-ref inputs "ldc") "/lib"))))) (replace -- cgit v1.2.3 From f50227eebb02a8cd1592a2c4d1a2aa9dc7930ee8 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Tue, 1 Mar 2016 14:19:33 +0100 Subject: Use the original Makefile to statically compile lz4. --- gn/packages/bioinformatics.scm | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 12a4bcb..d37a287 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -489,20 +489,24 @@ association studies (GWAS).") (build-system gnu-build-system) (native-inputs `(("ldc" ,ldc) - ("lz4" ,lz4) + ;;("lz4" ,lz4) ("rdmd" ,rdmd) ("zlib" ,zlib) - ("perl" ,perl) ; Needed for htslib tests? - ("ruby" ,ruby) ; Needed for htslib tests? - ("python" ,python) ; Needed for htslib tests? + ("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 (string-append "https://github.com/lomereiter/htslib/archive/" - "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5" ".tar.gz")) + (uri "https://github.com/lomereiter/htslib/archive/2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5.tar.gz") ;;(uri "https://github.com/samtools/htslib/archive/1.3.tar.gz") - (file-name "htslib-2f3c3ea7b.tar.gz") ;;(file-name "htslib-1.3.tar.gz") (sha256 (base32 "0bl6w856afnbgdsw8bybsxpqsyf2ba3f12rqh47hhpxvv866g08w")))) @@ -532,13 +536,16 @@ association studies (GWAS).") (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" "-f" "Makefile.guix" + (zero? (system* "make" "sambamba-ldmd2-64" "CC=gcc" "D_COMPILER=ldc2" (string-append "LDC_LIB_PATH=" (assoc-ref inputs "ldc") "/lib"))))) -- cgit v1.2.3 From 71d988288669830ffa4f3a286853b8fdcde08e9a Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Wed, 2 Mar 2016 12:24:09 +0100 Subject: Add FREEC. --- gn/packages/bioinformatics.scm | 50 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index d37a287..267d988 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -49,6 +49,56 @@ #:use-module (gn packages statistics) #:use-module (srfi srfi-1)) +(define-public freec + (package + (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 freebayes (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")) (package -- cgit v1.2.3 From fc79d528e10995f4e705d2f2863c14f706a2d509 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Wed, 2 Mar 2016 15:11:55 +0100 Subject: Add vcflib. --- gn/packages/bioinformatics.scm | 128 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 128 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 267d988..d826027 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -664,3 +664,131 @@ supported.") (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/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)))) -- cgit v1.2.3 From b79a29c4e756450c6e34a9464a2c321c992b50a6 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Thu, 3 Mar 2016 16:48:57 +0100 Subject: License fix for Freebayes. --- gn/packages/bioinformatics.scm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index d826027..2ef6f2c 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -263,7 +263,7 @@ 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:non-copyleft)))) + (license license:expat)))) (define-public r-biocpreprocesscore (package -- cgit v1.2.3 From fe3e5fe9d0924e5d1f9945f57420f342e1e312a5 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Thu, 3 Mar 2016 21:54:02 +0100 Subject: Fix for home-page, synopsis and description of vcflib. --- gn/packages/bioinformatics.scm | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 2ef6f2c..295a2b3 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -784,11 +784,12 @@ supported.") (install-file file bin)) (find-files "bin" ".*")) (install-file "libvcflib.a" lib))))))) - (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.") + (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)))) + -- cgit v1.2.3 From a4a9f2eec7a770a52bbeda64169ba9e3b1ff2583 Mon Sep 17 00:00:00 2001 From: pjotrp Date: Sat, 5 Mar 2016 16:07:32 +0000 Subject: Guix paths to the tools --- gn/packages/bioinformatics.scm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 295a2b3..c04c928 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -305,8 +305,8 @@ length of a short-read sequencing alignment.") (propagated-inputs `( ;; ("r-annotationdbi" ,r-annotationdbi) ; ("r-biocparallel" ,r-biocparallel) - ("r-dynamictreecut" ,r-dynamictreecut) ("r-doparallel" ,r-doparallel) + ("r-dynamictreecut" ,r-dynamictreecut) ("r-fastcluster" ,r-fastcluster) ("r-foreach" ,r-foreach) ("r-go-db" ,r-go-db) -- cgit v1.2.3 From fa66cadafcdf3787864943910abf3f9348768aa3 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Wed, 9 Mar 2016 13:35:32 +0100 Subject: Added submodules to run tests, and provided an override to run the tests. --- gn/packages/bioinformatics.scm | 75 +++++++++++++++++++++++++++--------------- 1 file changed, 48 insertions(+), 27 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index c04c928..49e54ee 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -100,10 +100,11 @@ mappability data (files created by GEM). ") (license license:gpl2+))) (define-public freebayes - (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")) + (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb") + (revision "1")) (package (name "freebayes") - (version (string-append "v1.0.2-" (string-take commit 7))) + (version (string-append "1.0.2-" revision "." (string-take commit 7))) (source (origin (method git-fetch) (uri (git-reference @@ -113,11 +114,18 @@ mappability data (files created by GEM). ") (sha256 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2")))) (build-system gnu-build-system) + (inputs + `(("zlib" ,zlib))) (native-inputs - `(("cmake" ,cmake) + `(("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) ("htslib" ,htslib) - ("zlib" ,zlib) ("python" ,python-2) + ("r" ,r) ("perl" ,perl) ("bamtools-src" ,(origin @@ -193,20 +201,34 @@ mappability data (files created by GEM). ") (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")))) + ("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 - `(#:tests? #f - #:phases + `(#: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")))))) + (assoc-ref inputs source) + "--strip-components=1")))))) (and (unpack "bamtools-src" "bamtools") (unpack "vcflib-src" "vcflib") @@ -217,47 +239,46 @@ mappability data (files created by GEM). ") (unpack "intervaltree-src" "vcflib/intervaltree") (unpack "multichoose-src" "vcflib/multichoose") (unpack "smithwaterman-src" "vcflib/smithwaterman") - (unpack "tabixpp-src" "vcflib/tabixpp"))))) + (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 + (replace 'build (lambda* (#:key inputs make-flags #:allow-other-keys) (and - ;; We must compile Bamtools before we can compile the main - ;; project. + ;; 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"))))) - ;; We must compile vcflib before we can compile the main - ;; project. + ;; Compile vcflib before we compiling the main project. (with-directory-excursion "vcflib" (with-directory-excursion "tabixpp" (zero? (system* "make"))) (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 + (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)))) - ;; (replace - ;; 'check - ;; (lambda* (#:key outputs #:allow-other-keys) - ;; (with-directory-excursion "test" - ;; (zero? (system* "make" "test"))))) - ))) + ;; 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.") + (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 -- cgit v1.2.3 From d0a8f6e732ab4c0b1a93c3741f246c0ce812ef95 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Wed, 9 Mar 2016 16:11:58 +0100 Subject: Added pindel without test suite. --- gn/packages/bioinformatics.scm | 46 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 49e54ee..5bf7843 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -814,3 +814,49 @@ 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 + `(#:tests? #f + #:phases + (modify-phases %standard-phases + (delete 'configure) ; There is no configure phase. + (replace 'build + (lambda* (#:key inputs #:allow-other-keys) + ;; The first run creates a Makefile.local file. + (system* "make" (string-append "SAMTOOLS=" (assoc-ref inputs "samtools"))) + ;; The second run actually compiles the program. + (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))))))) + (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+))) -- cgit v1.2.3 From f6832be1fe9138418bdd2858dbb2fc305cbcb25e Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 9 Mar 2016 11:34:55 -0500 Subject: Small fixed --- gn/packages/bioinformatics.scm | 1 + 1 file changed, 1 insertion(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 5bf7843..e6aa90f 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -22,6 +22,7 @@ #:use-module (gnu packages databases) #:use-module (gnu packages cmake) #:use-module (gnu packages cpio) + #:use-module (gnu packages cppcheck) #:use-module (gnu packages file) #:use-module (gnu packages gcc) #:use-module (gnu packages graphviz) -- cgit v1.2.3 From 99e4f33740622b50182822b4ef253f017620af44 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Thu, 10 Mar 2016 17:20:53 +0100 Subject: Add multiple packages. - tabixpp - smithwaterman - multichoose - fsom - filevercmp - fastahack - bash-tap - vcflib --- gn/packages/bioinformatics.scm | 460 ++++++++++++++++++++++++++++++++++------- 1 file changed, 382 insertions(+), 78 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 5bf7843..40dde37 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -14,15 +14,22 @@ #: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 curl) + #:use-module (gnu packages doxygen) + #:use-module (gnu packages datastructures) #: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) @@ -30,7 +37,11 @@ #: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) @@ -40,13 +51,13 @@ #: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 @@ -99,6 +110,350 @@ 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")) @@ -115,7 +470,8 @@ 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. @@ -123,35 +479,19 @@ 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) @@ -161,55 +501,15 @@ 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) @@ -232,7 +532,7 @@ 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") @@ -260,7 +560,11 @@ 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"))) -- cgit v1.2.3 From 34ae8b6d400fcce50f9848441ddf4e302b9d1057 Mon Sep 17 00:00:00 2001 From: pjotrp Date: Fri, 11 Mar 2016 09:01:39 +0000 Subject: Small compile fixes for pindel --- gn/packages/bioinformatics.scm | 1 + 1 file changed, 1 insertion(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 276471b..11a624f 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -13,6 +13,7 @@ ;; #: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) -- cgit v1.2.3 From f4e38087ff0c0261196304179f7d537d4806f164 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Fri, 11 Mar 2016 13:02:06 +0100 Subject: Added test suite to pindel package. --- gn/packages/bioinformatics.scm | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index 276471b..2c8feec 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -1140,15 +1140,19 @@ manipulations on VCF files.") ("python" ,python-2) ("perl" ,perl))) (arguments - `(#:tests? #f - #:phases + `(#: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. + ;; 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. + ;; 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) @@ -1156,7 +1160,17 @@ manipulations on VCF files.") (install-file "src/pindel" bin) (install-file "src/pindel2vcf" bin) (install-file "src/pindel2vcf4tcga" bin) - (install-file "src/sam2pindel" 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 -- cgit v1.2.3 From a30321a25267f80df6084104c8d562dc61046c1f Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Wed, 16 Mar 2016 11:14:47 +0100 Subject: Add contra. --- gn/packages/bioinformatics.scm | 51 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index d81a19a..a0a375b 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -62,6 +62,57 @@ #:use-module (gnu packages bootstrap) #:use-module (srfi srfi-1)) +(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-public freec (package (name "control-freec") -- cgit v1.2.3 From e024f97ea8886191fa49d56782dc42954bdc9880 Mon Sep 17 00:00:00 2001 From: Roel Janssen Date: Wed, 16 Mar 2016 13:49:52 +0100 Subject: Add delly. --- gn/packages/bioinformatics.scm | 56 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'gn/packages/bioinformatics.scm') diff --git a/gn/packages/bioinformatics.scm b/gn/packages/bioinformatics.scm index a0a375b..a4d14b0 100644 --- a/gn/packages/bioinformatics.scm +++ b/gn/packages/bioinformatics.scm @@ -113,6 +113,62 @@ standard alignment formats (BAM/SAM) and outputs in variant call format 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 "control-freec") -- cgit v1.2.3