diff filterVCFonAnnotations.xml @ 2:15319113c0a5 draft

Uploaded
author dereeper
date Thu, 12 Feb 2015 15:54:24 -0500
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/filterVCFonAnnotations.xml	Thu Feb 12 15:54:24 2015 -0500
@@ -0,0 +1,207 @@
+<tool id="sniplay_filterVCFonAnnotations" name="Filter VCF on Annotations" version="1.0.0">
+    
+    <!-- [REQUIRED] Tool description displayed after the tool name -->
+    <description> </description>
+    
+    <!-- [OPTIONAL] 3rd party tools, binaries, modules... required for the tool to work -->
+    <requirements>
+        <requirement type="binary">perl</requirement>
+    </requirements>
+    
+    <!-- [OPTIONAL] Command to be executed to get the tool's version string -->
+    <version_command>
+<!--
+        tool_binary -v
+-->
+    </version_command>
+    
+    <!-- [REQUIRED] The command to execute -->
+    <command interpreter="perl">
+	FilterVCFonAnnotations.pl --input $filein --out $fileout 
+	#if str( $genelist ) != "None":
+	--genelist $genelist
+	#end if
+	#if str( $feature ) != "":
+	--feature $feature
+	#end if
+	#if str( $syn ) != "":
+	--syn $syn
+	#end if
+    </command>
+     
+    <!-- [REQUIRED] Input files and tool parameters -->
+    <inputs>
+	<param name="filein" type="data" format="vcf" optional="false" label="VCF input" />
+	<param name="fileout_label" type="text" value="filtered" optional="false" label="Output file name"/>
+	<param name="genelist" type="data" format="txt" optional="true" label="Genelist" default="" help="File listing the genes to be filtered, one line per individu/gene"/>
+	<param name="feature" type="select" label="Genomic feature" optional="true" help="Filter within genomic feature">
+	    <option value="" selected="true">All</option>
+	    <option value="Exon">Exon</option>
+            <option value="INTRON">Intron</option>
+            <option value="UTR_5_PRIME">UTR5prime</option>
+            <option value="UTR_3_PRIME">UTR3prime</option>
+            <option value="DOWNSTREAM">Downstream</option>
+            <option value="UPSTREAM">Upstream</option>
+	    <option value="INTERGENIC">Intergenic</option>
+        </param>
+        <param name="syn" type="select" label="Synonymous type" optional="true" help="Keep only synonymous, non-synonymous SNP">
+            <option value="" selected="true">All</option>
+            <option value="s">Synonymous</option>
+            <option value="n">Non-synonymous</option>
+        </param>
+    </inputs>
+    
+    <!-- [REQUIRED] Output files -->
+    <outputs>
+	<data name="fileout" type="data" format="vcf" label="${fileout_label}.vcf" />
+    </outputs>
+    
+    <!-- [STRONGLY RECOMMANDED] Exit code rules -->
+    <stdio>
+        <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR -->
+        <exit_code range="1:" level="fatal" />
+    </stdio>
+    
+    <!-- [OPTIONAL] Tests to be run manually by the Galaxy admin -->
+    <tests>
+        <!-- [HELP] Test files have to be in the ~/test-data directory -->
+        <test>
+         <param name="filein" value="sample.vcf" />
+         <param name="genelist" value="accession.txt" />
+         <param name="feature" value="INTRON" />
+         <output name="fileout" file="result.vcf" />
+        </test>
+    </tests>
+    
+    <!-- [OPTIONAL] Help displayed in Galaxy -->
+    <help>
+
+.. class:: infomark
+
+**Authors** 
+
+---------------------------------------------------
+
+.. class:: infomark
+
+**Please cite** If you use this tool, please cite Dereeper et al. 2015 in prep.
+
+---------------------------------------------------
+
+======================
+Filter And Convert VCF
+======================
+
+-----------
+Description
+-----------
+
+  Filter VCF file and convert in Fasta, Hapmap and PED
+
+-----------------
+Workflow position
+-----------------
+
+**Upstream tools**
+
+=========== ========================== =======
+Name            output file(s)         format 
+=========== ========================== =======
+=========== ========================== =======
+
+
+**Downstream tools**
+
+=========== ========================== =======
+Name            output file(s)         format
+=========== ========================== =======
+=========== ========================== =======
+
+
+----------
+Input file
+----------
+
+VCF file
+	VCF file with all SNPs
+
+Genelist
+	File listing the genes or individuals to be filtered. Gene_id or accesion number can be put in a file, one line per individual
+	
+
+----------
+Parameters
+----------
+
+Output file name
+	Prefix for the output VCF file
+
+Genomic feature
+        Filter on genomic feature : Exon,INTRON,UTR_3_PRIME,UTR_5_PRIME,DOWNSTREAM,UPSTREAM or INTERGENIC
+
+Synonymous type
+	Keep only synonymous, non-synonymous.
+
+
+------------
+Output files
+------------
+
+VCF file
+	VCF file filtered 
+
+---------------------------------------------------
+
+---------------
+Working example
+---------------
+
+Input files
+===========
+
+VCF file
+---------
+
+::
+
+	#fileformat=VCFv4.1
+	#FILTER=&lt;ID=LowQual,Description="Low quality">
+	#FORMAT=&lt;ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+	[...]
+	CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	CATB1
+	chr1	2209	.	G	T	213.84	.	AC=2;AF=1.00;AN=2;DP=7;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=41.50;MQ0=0;QD=30.55;EFF=DOWNSTREAM(MODIFIER||||Cc01g00020|mRNA||GSCOCT00012438001|),UPSTREAM(MODIFIER||||Cc01g00010|mRNA||GSCOCT00012439001|)	GT:AD:DP:GQ:PL	1/1:0,7:7:18:242,18,0
+
+Genelist
+---------
+
+::
+
+	Cc01g00020
+	Cc01g00010
+
+Parameters
+==========
+
+Output name -> filtered_genelist_intron
+
+Genomic feature -> Intron
+
+Output files
+============
+
+filtered_genelist_intron.vcf
+----------------------------
+
+::
+
+        #fileformat=VCFv4.1
+        #FILTER=&lt;ID=LowQual,Description="Low quality"&gt;
+        #FORMAT=&lt;ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+        [...]
+        CHROM   POS     ID      REF     ALT     QUAL    FILTER  INFO    FORMAT  CATB1
+	chr1	5059	.	C	G	146.84	.	AC=2;AF=1.00;AN=2;DP=8;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=24.14;MQ0=1;QD=18.35;EFF=INTRON(MODIFIER||||Cc01g00020|mRNA||GSCOCT00012438001|),UPSTREAM(MODIFIER||||Cc01g00010|mRNA||GSCOCT00012439001|)	GT:AD:DP:GQ:PL	1/1:0,8:8:18:175,18,0
+
+
+    </help>
+    
+</tool>