[PATCH] gnu: Add freebayes.

[Roel Janssen <roel@gnu.org>]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: 0001-gnu-Add-freebayes.patch --]
[-- Type: text/x-patch, Size: 8738 bytes --]

From 38302e8cac77275694c8793933be414ec26906ec Mon Sep 17 00:00:00 2001
From: Roel Janssen <roel@gnu.org>
Date: Tue, 8 Mar 2016 16:38:46 +0100
Subject: [PATCH] gnu: Add freebayes.

* gnu/packages/bioinformatics.scm (freebayes): New variable.
---
 gnu/packages/bioinformatics.scm | 160 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 160 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 5d53dc9..601ab9b 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -37,6 +37,7 @@
   #:use-module (gnu packages algebra)
   #:use-module (gnu packages base)
   #:use-module (gnu packages boost)
+  #:use-module (gnu packages cmake)
   #:use-module (gnu packages compression)
   #:use-module (gnu packages cpio)
   #:use-module (gnu packages curl)
@@ -247,6 +248,165 @@ intervals from multiple files in widely-used genomic file formats such as BAM,
 BED, GFF/GTF, VCF.")
     (license license:gpl2)))
 
+(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)
+               ;; 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"
+                   (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)))))))
+      (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))))
+
 (define-public python2-pybedtools
   (package
     (name "python2-pybedtools")
-- 
2.5.0


[-- Attachment #2: Type: text/plain, Size: 431 bytes --]

Dear Guix,

I have a patch to add another bioinformatics tool: FreeBayes. It is a
rather long patch, so suspect it isn't completely 'guix-proof'.

One of the problems with the patch is probably the bulk of dependencies
dragged in (for example, vcflib).  They use specific versions so they
are tied to this package (so that's why I cannot package them separately).

Hope someone is willing to review it.

Kind regards,
Roel Janssen