# HG changeset patch
# User anton
# Date 1400090832 14400
# Node ID 491d7d90a68d978f199e5f126f924c62a6992ef2

Uploaded

diff -r 000000000000 -r 491d7d90a68d test-data/vcfdistance-test1.vcf
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcfdistance-test1.vcf	Wed May 14 14:07:12 2014 -0400
@@ -0,0 +1,29 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##ALT=<ID=DEL:ME:ALU,Description="Deletion of ALU element">
+##ALT=<ID=CNV,Description="Copy number variable region">
+##INFO=<ID=BasesToClosestVariant,Number=1,Type=Integer,Description="Number of bases to the closest variant in the file.">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+19	111	.	A	C	9.6	.	BasesToClosestVariant=1	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+19	112	.	A	G	10	.	BasesToClosestVariant=1	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+20	17330	.	T	A	3	q10	AF=0.017;BasesToClosestVariant=1093366;DP=11;NS=3	GT:GQ:DP:HQ	0|0:49:3:58,50	0|1:3:5:65,3	0/0:41:3:.,.
+20	1110696	rs6040355	A	G,T	67	PASS	AA=T;AF=0.333,0.667;BasesToClosestVariant=119541;DP=10;NS=2;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2	2/2:35:4:.,.
+20	1230237	.	T	.	47	PASS	AA=T;BasesToClosestVariant=4330;DP=13;NS=3	GT:GQ:DP:HQ	0|0:54:.:56,60	0|0:48:4:51,51	0/0:61:2:.,.
+20	1234567	microsat1	G	GA,GAC	50	PASS	AA=G;AC=3,1;AN=6;BasesToClosestVariant=670;DP=9;NS=3	GT:GQ:DP	0/1:.:4	0/2:17:2	1/1:40:3
diff -r 000000000000 -r 491d7d90a68d test-data/vcflib.vcf
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcflib.vcf	Wed May 14 14:07:12 2014 -0400
@@ -0,0 +1,31 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##ALT=<ID=DEL:ME:ALU,Description="Deletion of ALU element">
+##ALT=<ID=CNV,Description="Copy number variable region">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+19	111	.	A	C	9.6	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+19	112	.	A	G	10	.	.	GT:HQ	0|0:10,10	0|0:10,10	0/1:3,3
+20	14370	rs6054257	G	A	29	PASS	NS=3;DP=14;AF=0.5;DB;H2	GT:GQ:DP:HQ	0|0:48:1:51,51	1|0:48:8:51,51	1/1:43:5:.,.
+20	17330	.	T	A	3	q10	NS=3;DP=11;AF=0.017	GT:GQ:DP:HQ	0|0:49:3:58,50	0|1:3:5:65,3	0/0:41:3:.,.
+20	1110696	rs6040355	A	G,T	67	PASS	NS=2;DP=10;AF=0.333,0.667;AA=T;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2|1:2:0:18,2	2/2:35:4:.,.
+20	1230237	.	T	.	47	PASS	NS=3;DP=13;AA=T	GT:GQ:DP:HQ	0|0:54:.:56,60	0|0:48:4:51,51	0/0:61:2:.,.
+20	1234567	microsat1	G	GA,GAC	50	PASS	NS=3;DP=9;AA=G;AN=6;AC=3,1	GT:GQ:DP	0/1:.:4	0/2:17:2	1/1:40:3
+20	1235237	.	T	.	.	.	.	GT	0/0	0|0	./.
+X	10	rsTest	AC	A,ATG	10	PASS	.	GT	0	0/1	0|2
diff -r 000000000000 -r 491d7d90a68d tool_dependencies.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed May 14 14:07:12 2014 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="vcflib" version="586c5ae5d57a38dae6b32ea831fb1f7cfa14c9bd">
+        <repository changeset_revision="3d515e915297" name="package_vcflib" owner="anton" toolshed="http://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
diff -r 000000000000 -r 491d7d90a68d vcfdistance.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcfdistance.xml	Wed May 14 14:07:12 2014 -0400
@@ -0,0 +1,32 @@
+<tool id="vcfdistance" name="VCFdistance:" version="0.0.1">
+<requirements>
+    <requirement type="package" version="586c5ae5d57a38dae6b32ea831fb1f7cfa14c9bd">vcflib</requirement>
+</requirements>
+  <description>Calculate distance to the nearest variant</description>
+  <command>cat "${input1}" | vcfdistance > "${out_file1}"</command>
+  <inputs>
+    <param format="vcf" name="input1" type="data" label="First dataset"/>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="input1" value="vcflib.vcf"/>
+      <output name="out_file1" file="vcfdistance-test1.vcf"/>
+    </test>
+    </tests>
+  <help>
+
+Adds a value to each VCF record indicating the distance to the nearest variant in the file.
+
+.. class:: infomark
+
+The dataset used as input to this tool must be coordinate sorted. This can be achieved by either using the VCFsort utility or Galaxy's general purpose sort tool (in this case sort on the first and the second column in ascending order).
+
+----
+
+Vcfdistance is a part of VCFlib toolkit developed by Erik Garrison (https://github.com/ekg/vcflib).                                                                                                                                 
+
+</help>
+</tool>