Mercurial > repos > anton > vcf2tsv

changeset 0:8e1a693e7a52

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author anton
date Wed, 11 Jun 2014 17:11:55 -0400
parents
children 1258fa7a2744
files test-data/vcf2tsv-test1.tab test-data/vcf2tsv-test2.tab test-data/vcflib.vcf tool_dependencies.xml vcf2tsv.xml
diffstat 5 files changed, 121 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcf2tsv-test1.tab	Wed Jun 11 17:11:55 2014 -0400
@@ -0,0 +1,27 @@
+CHROM	POS	ID	REF	ALT	QUAL	FILTER	AA	AC	AF	AN	DP	NS	DB	H2	SAMPLE	DP	GQ	GT	HQ
+19	111	.	A	C	9.6	.	.	.	.	.	.	.	0	0	NA00001	.	.	0|0	10,10
+19	111	.	A	C	9.6	.	.	.	.	.	.	.	0	0	NA00002	.	.	0|0	10,10
+19	111	.	A	C	9.6	.	.	.	.	.	.	.	0	0	NA00003	.	.	0/1	3,3
+19	112	.	A	G	10	.	.	.	.	.	.	.	0	0	NA00001	.	.	0|0	10,10
+19	112	.	A	G	10	.	.	.	.	.	.	.	0	0	NA00002	.	.	0|0	10,10
+19	112	.	A	G	10	.	.	.	.	.	.	.	0	0	NA00003	.	.	0/1	3,3
+20	14370	rs6054257	G	A	29	PASS	.	.	0.5	.	14	3	1	1	NA00001	1	48	0|0	51,51
+20	14370	rs6054257	G	A	29	PASS	.	.	0.5	.	14	3	1	1	NA00002	8	48	1|0	51,51
+20	14370	rs6054257	G	A	29	PASS	.	.	0.5	.	14	3	1	1	NA00003	5	43	1/1	.,.
+20	17330	.	T	A	3	q10	.	.	0.017	.	11	3	0	0	NA00001	3	49	0|0	58,50
+20	17330	.	T	A	3	q10	.	.	0.017	.	11	3	0	0	NA00002	5	3	0|1	65,3
+20	17330	.	T	A	3	q10	.	.	0.017	.	11	3	0	0	NA00003	3	41	0/0	.,.
+20	1110696	rs6040355	A	G,T	67	PASS	T	.	0.333,0.667	.	10	2	1	0	NA00001	6	21	1|2	23,27
+20	1110696	rs6040355	A	G,T	67	PASS	T	.	0.333,0.667	.	10	2	1	0	NA00002	0	2	2|1	18,2
+20	1110696	rs6040355	A	G,T	67	PASS	T	.	0.333,0.667	.	10	2	1	0	NA00003	4	35	2/2	.,.
+20	1230237	.	T	.	47	PASS	T	.	.	.	13	3	0	0	NA00001	.	54	0|0	56,60
+20	1230237	.	T	.	47	PASS	T	.	.	.	13	3	0	0	NA00002	4	48	0|0	51,51
+20	1230237	.	T	.	47	PASS	T	.	.	.	13	3	0	0	NA00003	2	61	0/0	.,.
+20	1234567	microsat1	G	GA,GAC	50	PASS	G	3,1	.	6	9	3	0	0	NA00001	4	.	0/1	.
+20	1234567	microsat1	G	GA,GAC	50	PASS	G	3,1	.	6	9	3	0	0	NA00002	2	17	0/2	.
+20	1234567	microsat1	G	GA,GAC	50	PASS	G	3,1	.	6	9	3	0	0	NA00003	3	40	1/1	.
+20	1235237	.	T	.	0	.	.	.	.	.	.	.	0	0	NA00001	.	.	0/0	.
+20	1235237	.	T	.	0	.	.	.	.	.	.	.	0	0	NA00002	.	.	0|0	.
+X	10	rsTest	AC	A,ATG	10	PASS	.	.	.	.	.	.	0	0	NA00001	.	.	0	.
+X	10	rsTest	AC	A,ATG	10	PASS	.	.	.	.	.	.	0	0	NA00002	.	.	0/1	.
+X	10	rsTest	AC	A,ATG	10	PASS	.	.	.	.	.	.	0	0	NA00003	.	.	0|2	.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcf2tsv-test2.tab	Wed Jun 11 17:11:55 2014 -0400
@@ -0,0 +1,13 @@
+CHROM	POS	ID	REF	ALT	QUAL	FILTER	AA	AC	AF	AN	DP	NS	DB	H2
+19	111	.	A	C	9.6	.	.	.	.	.	.	.	0	0
+19	112	.	A	G	10	.	.	.	.	.	.	.	0	0
+20	14370	rs6054257	G	A	29	PASS	.	.	0.5	.	14	3	1	1
+20	17330	.	T	A	3	q10	.	.	0.017	.	11	3	0	0
+20	1110696	rs6040355	A	G	67	PASS	T	.	0.333	.	10	2	1	0
+20	1110696	rs6040355	A	T	67	PASS	T	.	0.667	.	10	2	1	0
+20	1230237	.	T	.	47	PASS	T	.	.	.	13	3	0	0
+20	1234567	microsat1	G	GA	50	PASS	G	3	.	6	9	3	0	0
+20	1234567	microsat1	G	GAC	50	PASS	G	1	.	6	9	3	0	0
+20	1235237	.	T	.	0	.	.	.	.	.	.	.	0	0
+X	10	rsTest	AC	A	10	PASS	.	.	.	.	.	.	0	0
+X	10	rsTest	AC	ATG	10	PASS	.	.	.	.	.	.	0	0
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcflib.vcf	Wed Jun 11 17:11:55 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
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Jun 11 17:11:55 2014 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="vcflib" version="586c5ae5d57a38dae6b32ea831fb1f7cfa14c9bd">
+      <repository changeset_revision="7949cc09120a" name="package_vcflib" owner="anton" toolshed="http://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcf2tsv.xml	Wed Jun 11 17:11:55 2014 -0400
@@ -0,0 +1,44 @@
+<tool id="vcf2tsv" name="VCFtoTab-delimited:" version="0.0.1">
+<requirements>
+    <requirement type="package" version="586c5ae5d57a38dae6b32ea831fb1f7cfa14c9bd">vcflib</requirement>
+</requirements>
+  <description>Convert VCF data into TAB-delimited format</description>
+  <command>vcf2tsv ${g_option} -n "${null_filler}" "${input}" > "${out_file1}"</command>
+  <inputs>
+    <param format="vcf" name="input" type="data" label="Select VCF dataset to convert"/>
+    <param name="g_option" type="boolean" checked="true" truevalue="-g" falsevalue="" label="Report data per sample" help="-g option"/>
+    <param name="null_filler" type="select" label="Fill empty fields with" help="-n option" >
+      <option value="">Nothing</option>
+      <option value=".">.</option>
+      <option value="*">*</option>
+      <option value="NULL">NULL</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="tabular" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="g_option" value="true"/>
+      <param name="null_filler" value="."/>
+      <param name="input" value="vcflib.vcf"/>
+      <output name="out_file1" file="vcf2tsv-test1.tab"/>
+    </test>
+   <test>
+      <param name="g_option" value="false"/>
+      <param name="null_filler" value="."/>
+      <param name="input" value="vcflib.vcf"/>
+      <output name="out_file1" file="vcf2tsv-test2.tab"/>
+    </test>
+    </tests>
+  <help>
+
+Converts stdin or given VCF file to tab-delimited format, using null string to replace empty values in the table.
+Specifying "**Report data per sample**" (-g) will output one line per sample with genotype information.
+
+----
+
+Vcf2Tsv is a part of VCFlib toolkit developed by Erik Garrison (https://github.com/ekg/vcflib).    
+
+</help>
+</tool>