Mercurial > repos > devteam > vcfannotategenotypes

changeset 0:c6be83b8883d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Thu, 19 Mar 2015 12:40:45 -0400
parents
children ad57b4feaf87
files macros.xml test-data/vcfannotategenotypes-input2.vcf test-data/vcfannotategenotypes-test1.vcf test-data/vcflib.vcf tool_dependencies.xml vcfannotategenotypes.xml
diffstat 6 files changed, 163 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Thu Mar 19 12:40:45 2015 -0400
@@ -0,0 +1,28 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="8a5602bf07">vcflib</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <xml name="stdio">
+        <stdio>
+            <exit_code range="1:" level="fatal" />
+        </stdio>
+    </xml>
+   	<xml name="citations">
+   	     <citations>
+             <citation type="bibtex">
+@misc{Garrison2015,
+  author = {Garrison, Erik},
+  year = {2015},
+  title = {vcflib},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  url = {https://github.com/ekg/vcflib},
+}
+             </citation>
+   	     </citations>
+   	</xml>
+    <token name="@IS_PART_OF_VCFLIB@">is a part of VCFlib toolkit developed by Erik Garrison (https://github.com/ekg/vcflib).</token>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcfannotategenotypes-input2.vcf	Thu Mar 19 12:40:45 2015 -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	NA00003
+19	111	.	A	C	9.6	.	.	GT:HQ	0|0:10,10	0/1:3,3
+19	112	.	A	G	10	.	.	GT:HQ	0|0:10,10	0/1:3,3
+20	14370	rs6054257	G	A	29	PASS	AF=0.5;DP=14;NS=3;DB;H2	GT:GQ:DP:HQ	0|0:48:1:51,51	1/1:43:5:.,.
+20	17330	.	T	A	3	q10	AF=0.017;DP=11;NS=3	GT:GQ:DP:HQ	0|0:49:3:58,50	0/0:41:3:.,.
+20	1110696	rs6040355	A	G,T	67	PASS	AA=T;AF=0.333,0.667;DP=10;NS=2;DB	GT:GQ:DP:HQ	1|2:21:6:23,27	2/2:35:4:.,.
+20	1230237	.	T	.	47	PASS	AA=T;DP=13;NS=3	GT:GQ:DP:HQ	0|0:54:.:56,60	0/0:61:2:.,.
+20	1234567	microsat1	G	GA,GAC	50	PASS	AA=G;AC=3,1;AN=6;DP=9;NS=3	GT:GQ:DP	0/1:.:4	1/1:40:3
+20	1235237	.	T	.	0	.	.	GT	0/0	.
+X	10	rsTest	AC	A,ATG	10	PASS	.	GT	0	0|2
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcfannotategenotypes-test1.vcf	Thu Mar 19 12:40:45 2015 -0400
@@ -0,0 +1,33 @@
+##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=added-genotypes.has_variant,Number=0,Type=Flag,Description="True if added-genotypes has a called alternate among samples under comparison.">
+##FORMAT=<ID=added-genotypes,Number=1,Type=String,Description="Genotype from added-genotypes.">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+19	111	.	A	C	9.6	.	added-genotypes.has_variant	GT:HQ:added-genotypes	0|0:10,10:0/0	0|0:10,10:./.	0/1:3,3:0/1
+19	112	.	A	G	10	.	added-genotypes.has_variant	GT:HQ:added-genotypes	0|0:10,10:0/0	0|0:10,10:./.	0/1:3,3:0/1
+20	14370	rs6054257	G	A	29	PASS	AF=0.5;DP=14;NS=3;DB;H2;added-genotypes.has_variant	GT:GQ:DP:HQ:added-genotypes	0|0:48:1:51,51:0/0	1|0:48:8:51,51:./.	1/1:43:5:.,.:1/1
+20	17330	.	T	A	3	q10	AF=0.017;DP=11;NS=3;added-genotypes.has_variant	GT:GQ:DP:HQ:added-genotypes	0|0:49:3:58,50:0/0	0|1:3:5:65,3:./.	0/0:41:3:.,.:0/0
+20	1110696	rs6040355	A	G,T	67	PASS	AA=T;AF=0.333,0.667;DP=10;NS=2;DB;added-genotypes.has_variant	GT:GQ:DP:HQ:added-genotypes	1|2:21:6:23,27:1/2	2|1:2:0:18,2:./.	2/2:35:4:.,.:2/2
+20	1230237	.	T	.	47	PASS	AA=T;DP=13;NS=3;added-genotypes.has_variant	GT:GQ:DP:HQ:added-genotypes	0|0:54:.:56,60:0/0	0|0:48:4:51,51:./.	0/0:61:2:.,.:0/0
+20	1234567	microsat1	G	GA,GAC	50	PASS	AA=G;AC=3,1;AN=6;DP=9;NS=3;added-genotypes.has_variant	GT:GQ:DP:added-genotypes	0/1:.:4:0/1	0/2:17:2:./.	1/1:40:3:1/1
+20	1235237	.	T	.	0	.	added-genotypes.has_variant	GT:added-genotypes	0/0:0/0	0|0:./.	.
+X	10	rsTest	AC	A,ATG	10	PASS	added-genotypes.has_variant	GT:added-genotypes	0:0	0/1:./.	0|2:0/2
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcflib.vcf	Thu Mar 19 12:40:45 2015 -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	Thu Mar 19 12:40:45 2015 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="vcflib" version="8a5602bf07">
+        <repository changeset_revision="7e67466b033e" name="package_vcflib_8a5602bf07" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcfannotategenotypes.xml	Thu Mar 19 12:40:45 2015 -0400
@@ -0,0 +1,34 @@
+<tool id="vcfannotategenotypes" name="VCFannotateGenotypes:" version="0.0.3">
+  <description>Annotate genotypes in a VCF dataset using genotypes from another VCF dataset</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
+  <expand macro="requirements"></expand>
+  <expand macro="stdio" />
+  <command>vcfannotategenotypes "${tag_option}" "${input1}" "${input2}" > "${out_file1}"</command>
+  <inputs>
+    <param format="vcf" name="input1" type="data" label="Annotate genotypes in" help="First VCF dataset"/>
+    <param format="vcf" name="input2" type="data" label="using genotypes from" help="Second VCF dataset"/>
+    <param name="tag_option" size="20" type="text" value="added-genotypes" label="Mark genotypes added to the first dataset with this tag" help="Annotation tag"/>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="out_file1" />
+  </outputs>
+ <tests>
+    <test>
+      <param name="tag_option" value="added-genotypes"/>
+      <param name="input1" value="vcflib.vcf"/>
+      <param name="input2" value="vcfannotategenotypes-input2.vcf"/>
+      <output name="out_file1" file="vcfannotategenotypes-test1.vcf" />
+    </test>
+    </tests>
+<help>
+
+Annotates genotypes in the **First** dataset with genotypes from the **Second** adding the genotype as another flag to each sample filled in the first file. **Annotation-tag** is the name of the sample flag which is added to store the annotation.  Also adds a 'has\_variant' flag for sites where the second file has a variant.
+
+-----
+
+Vcfannotate @IS_PART_OF_VCFLIB@
+</help>
+  <expand macro="citations" />
+</tool>