aboutsummaryrefslogtreecommitdiff
path: root/gnu/packages/bioinformatics.scm
diff options
context:
space:
mode:
authorMarius Bakke <mbakke@fastmail.com>2016-08-30 18:49:21 +0100
committerLeo Famulari <leo@famulari.name>2016-09-10 17:41:38 -0400
commit84be3b9920120e7cc03095baca06d61b7f3fb741 (patch)
tree6f249abd59a8913fb09cc274b6ca435990fdd0c2 /gnu/packages/bioinformatics.scm
parent0e790a7ce0410dc7f991bca4e566fb73004ddd39 (diff)
downloadguix-84be3b9920120e7cc03095baca06d61b7f3fb741.tar
guix-84be3b9920120e7cc03095baca06d61b7f3fb741.tar.gz
gnu: Add mash.
* gnu/packages/bioinformatics.scm (mash): New variable. Signed-off-by: Leo Famulari <leo@famulari.name>
Diffstat (limited to 'gnu/packages/bioinformatics.scm')
-rw-r--r--gnu/packages/bioinformatics.scm57
1 files changed, 57 insertions, 0 deletions
diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 74360832b0..2c28ac0a24 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 +3047,62 @@ 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 and htslib are statically embedded in the final
+ ;; application. Therefore we also list their licenses, below.
+ ("capnproto" ,capnproto)
+ ("htslib" ,htslib)))
+ (inputs
+ `(("gsl" ,gsl)
+ ("zlib" ,zlib)))
+ (supported-systems '("x86_64-linux"))
+ (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.")
+ (license (list license:bsd-3 ; Mash
+ license:expat ; HTSlib and capnproto
+ license:public-domain ; MurmurHash 3
+ license:cpl1.0)))) ; Open Bloom Filter
+
(define-public metabat
(package
(name "metabat")