[PATCH] gnu: Add mash.

[Marius Bakke]

>From 20974083333c8e94d10423d4a156caa5298d6dcb Mon Sep 17 00:00:00 2001
From: Marius Bakke <address@hidden>
Date: Tue, 30 Aug 2016 18:49:21 +0100
Subject: [PATCH 1/1] gnu: Add mash.

* gnu/packages/bioinformatics.scm (mash): New variable.
---
 gnu/packages/bioinformatics.scm | 53 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index ed20b56..9b96d37 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -76,6 +76,7 @@
   #:use-module (gnu packages python)
   #:use-module (gnu packages readline)
   #:use-module (gnu packages ruby)
+  #:use-module (gnu packages serialization)
   #:use-module (gnu packages statistics)
   #:use-module (gnu packages tbb)
   #:use-module (gnu packages tex)
@@ -3046,6 +3047,58 @@ sequences).")
               "http://mafft.cbrc.jp/alignment/software/license.txt";
               "BSD-3 with different formatting"))))
 
+(define-public mash
+  (package
+    (name "mash")
+    (version "1.1.1")
+    (source (origin
+              (method url-fetch)
+              (uri (string-append
+                    "https://github.com/marbl/mash/archive/v";
+                    version ".tar.gz"))
+              (file-name (string-append name "-" version ".tar.gz"))
+              (sha256
+               (base32
+                "08znbvqq5xknfhmpp3wcj574zvi4p7i8zifi67c9qw9a6ikp42fj"))
+              (modules '((guix build utils)))
+              (snippet
+               ;; Delete bundled kseq.
+               ;; TODO: Also delete bundled murmurhash and open bloom filter.
+               '(delete-file "src/mash/kseq.h"))))
+    (build-system gnu-build-system)
+    (arguments
+     `(#:tests? #f ; No tests.
+       #:configure-flags
+       (list
+        (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
+        (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
+       #:make-flags (list "CC=gcc")
+       #:phases
+       (modify-phases %standard-phases
+         (add-after 'unpack 'fix-includes
+           (lambda _
+             (substitute* '("src/mash/Sketch.cpp" "src/mash/CommandFind.cpp")
+               (("^#include \"kseq\\.h\"")
+                "#include \"htslib/kseq.h\""))
+             #t))
+         (add-before 'configure 'autoconf
+           (lambda _ (zero? (system* "autoconf")))))))
+    (native-inputs
+     `(("autoconf" ,autoconf)
+       ("capnproto" ,capnproto)
+       ("htslib" ,htslib)))
+    (inputs
+     `(("gsl" ,gsl)
+       ("zlib" ,zlib)))
+    (home-page "https://mash.readthedocs.io";)
+    (synopsis "Fast genome and metagenome distance estimation using MinHash")
+    (description "Mash is a fast sequence distance estimator that uses the
+MinHash algorithm and is designed to work with genomes and metagenomes in the
+form of assemblies or reads.")
+    ;; Mash is distributed under 3-clause BSD, but includes software covered
+    ;; by other licenses.
+    (license (list license:bsd-3 license:public-domain license:cpl1.0))))
+
 (define-public metabat
   (package
     (name "metabat")
-- 
2.9.3