>From 990eda92a62dc25d0f5792437a82e119c5e3579f Mon Sep 17 00:00:00 2001
From: Roel Janssen <address@hidden>
Date: Tue, 8 Mar 2016 21:06:53 +0100
Subject: [PATCH] gnu: Add bioawk.

* gnu/packages/bioinformatics.scm (bioawk): New variable.
---
 gnu/packages/bioinformatics.scm | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 5d53dc9..4ceec08 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 bison)
   #:use-module (gnu packages compression)
   #:use-module (gnu packages cpio)
   #:use-module (gnu packages curl)
@@ -247,6 +248,43 @@ intervals from multiple files in widely-used genomic file formats such as BAM,
 BED, GFF/GTF, VCF.")
     (license license:gpl2)))
 
+(define-public bioawk
+  (package
+    (name "bioawk")
+    (version "1.0")
+    (source (origin
+      (method url-fetch)
+      (uri (string-append "https://github.com/lh3/bioawk/archive/v"
+                          version ".tar.gz"))
+      (file-name (string-append name "-" version ".tar.gz"))
+      (sha256
+       (base32 "1daizxsk17ahi9n58fj8vpgwyhzrzh54bzqhanjanp88kgrz7gjw"))))
+    (build-system gnu-build-system)
+    (propagated-inputs
+     `(("zlib" ,zlib)))
+    (native-inputs
+     `(("bison" ,bison)))
+    (arguments
+     `(#:parallel-build? #f
+       #:phases
+       (modify-phases %standard-phases
+         (delete 'configure)
+         (delete 'check)
+         (replace
+          'install
+          (lambda* (#:key outputs #:allow-other-keys)
+            (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
+              (install-file "bioawk" bin)))))))
+    (home-page "https://github.com/lh3/bioawk")
+    (synopsis "AWK with bioinformatics extensions")
+    (description "Bioawk is an extension to Brian Kernighan's awk, adding the
+support of several common biological data formats, including optionally gzip'ed
+BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names.  It
+also adds a few built-in functions and an command line option to use TAB as the
+input/output delimiter.  When the new functionality is not used, bioawk is
+intended to behave exactly the same as the original BWK awk.")
+    (license license:x11)))
+
 (define-public python2-pybedtools
   (package
     (name "python2-pybedtools")
-- 
2.5.0