Mercurial > repos > devteam > vcffilter

changeset 0:34c3b846e0b6 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 14:27:51 -0400
parents
children e729e584cd6f
files macros.xml test-data/vcffilter-test1.vcf test-data/vcflib.vcf tool_dependencies.xml vcffilter.xml
diffstat 5 files changed, 172 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Thu Mar 19 14:27:51 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/vcffilter-test1.vcf	Thu Mar 19 14:27:51 2015 -0400
@@ -0,0 +1,26 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=myImputationProgramV3.1
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##filter="DP > 10"
+##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	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	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:.,.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/vcflib.vcf	Thu Mar 19 14:27:51 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 14:27:51 2015 -0400
@@ -0,0 +1,9 @@
+<?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>
+    <package name="tabix" version="0.2.6">
+        <repository changeset_revision="3d6beba7393e" name="package_tabix_0_2_6" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vcffilter.xml	Thu Mar 19 14:27:51 2015 -0400
@@ -0,0 +1,78 @@
+<tool id="vcffilter2" name="VCFfilter:" version="0.0.3">
+  <description>filter VCF data in a variety of attributes</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
+  <expand macro="requirements">
+    <requirement type="package" version="0.2.6">tabix</requirement>
+  </expand>
+  <expand macro="stdio" />
+  <command>
+  <!-- This tools depends on tabix functionality, which is currently distributed with Galaxy itself via a pysam egg -->
+    ln -s "${input1}" input1.vcf &amp;&amp;
+    bgzip input1.vcf &amp;&amp;
+    tabix -p vcf input1.vcf.gz &amp;&amp;
+    vcffilter ${filterList} input1.vcf.gz  > "${out_file1}"
+  </command>
+  
+  <inputs>
+    <param name="filterList" size="40" type="text" value="-f &quot;DP &gt; 10&quot;" label="Specify filterting expression" help="See explanation of filtering options below">
+      <sanitizer>
+        <valid initial="string.printable">
+	  <remove value="&apos;"/>
+        </valid>
+        <mapping initial="none">
+          <add source="&apos;" target="__sq__"/>
+        </mapping>
+      </sanitizer>
+    </param>
+    <param format="vcf" name="input1" type="data" label="VCF dataset to filter">
+    </param>
+  </inputs>
+  <outputs>
+    <data format="vcf" name="out_file1" />
+  </outputs>
+ <tests>
+    <test>
+      <param name="filterList" value="-f &quot;DP &gt; 10&quot;"/>
+      <param name="input1" value="vcflib.vcf"/>
+      <output name="out_file1" file="vcffilter-test1.vcf"/>
+    </test>
+</tests> 
+ <help>
+
+You can specify the following options within the **Specify filtering expression** box in any combination::
+
+    -f, --info-filter     specifies a filter to apply to the info fields of records, removes alleles which do not pass the filter
+    -g, --genotype-filter specifies a filter to apply to the genotype fields of records
+    -s, --filter-sites    filter entire records, not just alleles
+    -t, --tag-pass        tag vcf records as positively filtered with this tag, print all records
+    -F, --tag-fail        tag vcf records as negatively filtered with this tag, print all records
+    -A, --append-filter   append the existing filter tag, don't just replace it
+    -a, --allele-tag      apply -t on a per-allele basis.  adds or sets the corresponding INFO field tag
+    -v, --invert          inverts the filter, e.g. grep -v
+    -o, --or              use logical OR instead of AND to combine filters
+    -r, --region          specify a region on which to target the filtering (must be used in conjunction with -f or -g)
+
+Filters are specified in the form {ID} {operator} {value}::
+
+ -f "DP > 10"          # for info fields
+ -g "GT = 1|1"         # for genotype fields
+ -f "CpG"              # for 'flag' fields
+
+Any number of filters may be specified.  They are combined via logical AND unless the --or option is specified. For convenience, you can specify "QUAL" to refer to the quality of the site, even though it does not appear in the INFO fields.  
+
+Operators can be any of: =, !, &lt;, &gt;, pipe, &amp;
+
+
+To restrict output to a specific location use the -r option (must be used in conjunction with -g or -f)::
+
+ -r chr20:14000-15000  # only output calls between positions 14,000 and 15,000 on chromosome 20
+ -r chrX               # only output call on chromosome X
+
+-----
+
+Vcffilter @IS_PART_OF_VCFLIB@
+</help>
+  <expand macro="citations" />
+</tool>