diff covacs_Select_Filtration.xml @ 0:6d8aa1176a94 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/covacs_Select_Filtration.xml	Fri Nov 09 06:03:28 2018 -0500
@@ -0,0 +1,75 @@
+ <tool id="covacs_Select_Filtration" name="covacs_Select_filtration" version="3.8">
+  <description>SelectVariants VariantFiltration wrapper for covacs, use in case of not enough snp or indels error in covacs_VariantRecalibrator</description>
+  <macros>
+  </macros>
+  <requirements>
+  	<requirement type="package" version="3.8" >gatk</requirement>
+  </requirements>
+  <command>
+    <![CDATA[
+	### call the .sh to untar the package 
+        sh $__tool_directory__/mv_untar_gatk.sh &&
+
+	##sym link to run GATK
+
+	ln -s $input1 input1.vcf &&
+	
+	##GATK tool call
+	java -jar  \$CONDA_PREFIX/../../GenomeAnalysisTK.jar
+	-T SelectVariants 
+	-R $ref_file.fields.path
+	-V input1.vcf
+	-selectType $TYPE
+	-o variants_recal.indels.vcf 2>$log 
+		&&
+	java -jar  \$CONDA_PREFIX/../../GenomeAnalysisTK.jar 
+	-T VariantFiltration 
+	-R $ref_file.fields.path
+	-V variants_recal.indels.vcf 
+	--filterExpression "DP<8 || QD < 2.0 || FS > 200.0 || ReadPosRankSum < -20.0" 
+	--filterName "filter_LQ_$TYPE" 
+	-o variants_recal.filtered.small.panel.region.vcf
+
+	2>> $log
+	]]>
+  </command>
+  <inputs>
+    <param format="vcf" name="input1" label="input VCF" type="data" optional="true" />
+    <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
+       <options from_data_table="covacs_gatk_indexes">
+      	 <filter type="sort_by" column="2" />
+       	 <validator type="no_options" message="No indexes are available" />
+       </options>
+       <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
+    </param>
+    <param name="TYPE" type="select" optional="true">
+        <option value="INDEL">INDEL</option>
+        <option value="SNP" selected="true" >SNP</option>
+    </param>	
+  </inputs>
+  <outputs>
+    <data format="vcf" name="recal" from_work_dir="variants_recal.indels.vcf" label="SelectVariants on ${on_string} $TYPE :recal"/>
+    <data format="vcf" name="filtered" from_work_dir="variants_recal.filtered.small.panel.region.vcf" label="VariantFiltration on ${on_string} $TYPE :recal"/>
+    <data format="txt" name="log" label="log"/>
+  </outputs>
+  <help>
+ **IMPORTANT** to get the wrapper ready to start the admin user have to download gatk GATK version 3.8 from the broadinstitute site https://software.broadinstitute.org/gatk/download/archive and then move it in the conda_prefix folder, the path of the conda_prefix is written in the galaxy.ini(or .yml) file 
+
+		**more informations** at https://software.broadinstitute.org/gatk/documentation/tooldocs/3.8-0/org_broadinstitute_gatk_tools_walkers_variantutils_SelectVariants.php , https://software.broadinstitute.org/gatk/documentation/tooldocs/3.8-0/org_broadinstitute_gatk_tools_walkers_filters_VariantFiltration.php
+
+**Implemented options** SelectVariants <![CDATA[ &]]> VariantFiltration
+
+-R 		Reference sequence file
+
+-V 		vcf input
+
+other options are fixed based on covacs pipeline
+
+**description** this step can be used if covacs_indel_snp have not enough data to create the model, it calls SelectVariants and VariantFiltration applying the filter expression --filterExpression <![CDATA["DP<8 || QD < 2.0 || FS > 200.0 || ReadPosRankSum < -20.0"]]> to filter the variants both snp and indels
+
+  </help>
+  <citations>
+        <citation type="doi">10.1186/s12864-018-4508-1</citation>
+  </citations>
+</tool>
+