Mercurial > repos > devteam > vcfallelicprimitives

changeset 0:3f4fefbc52c8 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 12:23:24 -0400
parents
children f49b23b41a12
files macros.xml test-data/vcfallelicprimitives-test1.vcf test-data/vcflib.vcf tool_dependencies.xml vcfallelicprimitives.xml
diffstat 5 files changed, 162 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Thu Mar 19 12:23:24 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/vcfallelicprimitives-test1.vcf	Thu Mar 19 12:23:24 2015 -0400
@@ -0,0 +1,35 @@
+##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=TYPE,Number=A,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">
+##INFO=<ID=LEN,Number=A,Type=Integer,Description="allele length">
+##INFO=<ID=Split primitives,Number=0,Type=Flag,Description="The allele was parsed using vcfallelicprimitives.">
+#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	AF=0.5;DP=14;NS=3;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	AF=0.017;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	.	A	G,T	67	PASS	AF=0.333,0.667;LEN=1,1;TYPE=snp,snp;Split primitives	GT	1|2	2|1	2|2
+20	1230237	.	T	.	47	PASS	AA=T;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	.	G	GA,GAC	50	PASS	AC=3,1;LEN=1,2;TYPE=ins,ins;Split primitives	GT	0|1	0|2	1|1
+20	1235237	.	T	.	0	.	.	GT	0/0	0|0	.
+X	10	.	AC	ATC,A	10	PASS	LEN=1,1;TYPE=ins,del;Split primitives	GT	0	0|2	0|1
+X	11	.	C	G	10	PASS	LEN=1;TYPE=snp;Split primitives	GT	0	0|0	0|1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcflib.vcf	Thu Mar 19 12:23:24 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 12:23:24 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/vcfallelicprimitives.xml	Thu Mar 19 12:23:24 2015 -0400
@@ -0,0 +1,62 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tool id="vcfallelicprimitives" name="VcfAllelicPrimitives:" version="0.0.3">
+    <description>Split alleleic primitives (gaps or mismatches) into multiple VCF lines</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"></expand>
+    <expand macro="stdio" />
+    <command>
+        cat "${input}" | vcfallelicprimitives 
+            ${m_option} 
+            -t "${t_option}"
+	    -L "${max_length}" 
+            $keep_info 
+            $keep_geno > "${out_file1}"
+    </command>
+    <inputs>
+        <param format="vcf" name="input" type="data" label="Select VCF dataset"/>
+        <param name="m_option" type="boolean" checked="false" truevalue="--use-mnps" falsevalue="" label="Retain MNPs as separate events" help="--use-mnps option"/>
+        <param name="t_option" size="20" type="text" value="Split primitives" label="Tag records which are split apart of a complex allele with this flag. " help="--tag-parsed option"/>
+	<param name="max_length" type="integer" size="4" value="200" label="Do not manipulate records in which either the ALT or REF is longer than (bp)" help="--max-length option"/>
+        <param name="keep_info" type="boolean" truevalue="--keep-info" falsevalue="" checked="False" 
+            label="Maintain site and allele-level annotations when decomposing" 
+            help="Note that in many cases, such as multisample VCFs, these won't be valid post-decomposition.  For biallelic loci in single-sample VCFs, they should be usable with caution. (--keep-info)"/>
+        <param name="keep_geno" type="boolean" truevalue="--keep-geno" falsevalue="" checked="False" 
+            label="Maintain genotype-level annotations when decomposing" 
+            help="Similar caution should be used for this as for --keep-info. (--keep-geno)"/>
+    </inputs>
+    <outputs>
+        <data format="vcf" name="out_file1" label="${tool.name} on ${on_string}" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="vcflib.vcf"/>
+            <output name="out_file1" file="vcfallelicprimitives-test1.vcf"/>
+        </test>
+    </tests>
+    <help>
+
+If multiple alleleic primitives (gaps or mismatches) are specified in a single VCF record, this tools splits the record into multiple lines, but drops all INFO fields.  
+"Pure" MNPs are split into multiple SNPs unless the -m flag is provided. 
+Genotypes are phased where complex alleles have been decomposed, provided genotypes in the input.
+
+The options are::
+
+    -m, --use-mnps          Retain MNPs as separate events (default: false).
+    -t, --tag-parsed FLAG   Tag records which are split apart of a complex allele with this flag.
+    -L, --max-length LEN    Do not manipulate records in which either the ALT or
+                            REF is longer than LEN (default: 200).
+    -k, --keep-info         Maintain site and allele-level annotations when decomposing.
+                            Note that in many cases, such as multisample VCFs, these won't
+                            be valid post-decomposition.  For biallelic loci in single-sample
+                            VCFs, they should be usable with caution.
+    -g, --keep-geno         Maintain genotype-level annotations when decomposing.  Similar
+                            caution should be used for this as for --keep-info.
+
+----
+
+Vcfallelicprimitives @IS_PART_OF_VCFLIB@
+    </help>
+    <expand macro="citations" />
+</tool>