Mercurial > repos > anton > vcfsort

changeset 0:75465664959d draft default tip

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 17:10:31 -0400
parents
children
files test-data/vcfsort-test1-input.vcf test-data/vcfsort-test1.vcf vcfsort.xml
diffstat 3 files changed, 87 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcfsort-test1-input.vcf	Wed Jun 11 17:10:31 2014 -0400
@@ -0,0 +1,30 @@
+##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
+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	./.
+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
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcfsort-test1.vcf	Wed Jun 11 17:10:31 2014 -0400
@@ -0,0 +1,30 @@
+##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	./.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcfsort.xml	Wed Jun 11 17:10:31 2014 -0400
@@ -0,0 +1,27 @@
+<tool id="vcfsort" name="VCFsort:" version="0.0.1">
+  <description>Sort VCF dataset by coordinate</description>
+  <command>(grep ^"#" "${input1}"; grep -v ^"#" "${input1}" | LC_ALL=C sort -k1,1 -k2,2n -V) > "${out_file1}"</command>
+  <inputs>
+    <param format="vcf" name="input1" type="data" label="Select VCF dataset"/>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="input1" value="vcfsort-test1-input.vcf"/>
+      <output name="out_file1" file="vcfsort-test1.vcf"/>
+    </test>
+    </tests>
+  <help>
+
+This tool uses native UNIX sort command to order VCF dataset in coordinate order. For technically inclined the command is::
+
+ (grep ^"#" INPUT_file ; grep -v ^"#" INPUT_file | LC_ALL=C sort -k1,1 -k2,2n -V) > OUTPUT_file
+
+.. class:: infomark
+
+The same result can be achieved with the Galaxy's general purpose sort tool (in this case sort on the first and the second column in ascending order).
+
+</help>
+</tool>