diff snpSift_filter.xml @ 4:baf6602903e1

Uploaded
author jjohnson
date Wed, 09 Dec 2015 14:03:26 -0500
parents 796388c291d3
children 675fa55f5c02 824f78c0d0df
line wrap: on
line diff
--- a/snpSift_filter.xml	Thu Oct 23 06:06:25 2014 -0500
+++ b/snpSift_filter.xml	Wed Dec 09 14:03:26 2015 -0500
@@ -1,11 +1,13 @@
-<tool id="snpSift_filter" name="SnpSift Filter" version="4.0.0">
+<tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.0">
     <options sanitize="False" />
     <description>Filter variants using arbitrary expressions</description>
+    <macros>
+        <import>snpSift_macros.xml</import>
+    </macros>
     <expand macro="requirements" />
-    <macros>
-        <import>snpEff_macros.xml</import>
-    </macros>
-    <command>
+    <expand macro="stdio" />
+    <expand macro="version_command" />
+    <command><![CDATA[
         java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse 
         #if $filtering.mode == 'field':
             #if $filtering.replace.pass:
@@ -22,6 +24,7 @@
             #end if
         #end if
          > $output
+]]>
     </command>
     <inputs>
         <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
@@ -57,7 +60,6 @@
     <outputs>
         <data format="vcf" name="output" />
     </outputs>
-    <expand macro="stdio" />
     <tests>
         <test>
         <param name="input" ftype="vcf" value="test01.vcf"/>
@@ -85,7 +87,7 @@
 
         <test>
         <param name="input" ftype="vcf" value="test01.vcf"/>
-        <param name="expr" value="(POS >= 20175) &amp; (POS &lt;= 35549)"/>
+        <param name="expr" value="(POS >= 20175) & (POS <= 35549)"/>
         <param name="mode" value="entries"/>
         <output name="output">
             <assert_contents>
@@ -111,11 +113,11 @@
         </output>
         </test>
     </tests>
-    <help>
+    <help><![CDATA[
 
 **SnpSift filter**
 
-You can filter ia vcf file using arbitrary expressions, for instance "(QUAL > 30) | (exists INDEL) | ( countHet() > 2 )". The actual expressions can be quite complex, so it allows for a lot of flexibility.
+You can filter a VCF file using arbitrary expressions, for instance "(QUAL > 30) | (exists INDEL) | ( countHet() > 2 )". The actual expressions can be quite complex, so it allows for a lot of flexibility.
 
 Some examples:
 
@@ -123,7 +125,7 @@
 
     ::
 
-    ( CHROM = 'chr1' ) &amp; ( POS &gt; 1000000 )  &amp; ( POS &lt; 2000000 )
+    ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 )
 
   - *Filter value is either 'PASS' or it is missing*:
 
@@ -131,11 +133,13 @@
 
     (FILTER = 'PASS') | ( na FILTER )  
 
-  - *I want to filter lines with an EFF of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*:
+  - *I want to filter lines with an ANN annotation EFFECT of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*:
 
     ::
   
-    ( EFF[*].EFFECT = 'frameshift_variant' )
+    ( ANN[*].EFFECT has 'frameshift_variant' )
+
+    **Important** According to the specification, there can be more than one EFFECT separated by & (e.g. 'missense_variant&splice_region_variant', thus using has operator is better than using equality operator (=). For instance 'missense_variant&splice_region_variant' = 'missense_variant' is false, whereas 'missense_variant&splice_region_variant' has 'missense_variant' is true. 
 
   - *I want to filter lines with an EFF of 'FRAME_SHIFT' ( for vcf files using Classic Effect names )*:
 
@@ -147,31 +151,31 @@
 
     ::
 
-    ( QUAL &gt; 30 )
+    ( QUAL > 30 )
 
   - *...but we also want InDels that have quality 20 or more*:
 
     ::
 
-    (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )
+    (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
   
   - *...or any homozygous variant present in more than 3 samples*:
 
     ::
 
-    (countHom() > 3) | (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )
+    (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
   
   - *...or any heterozygous sample with coverage 25 or more*:
 
     ::
 
-    ((countHet() > 0) &amp; (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )
+    ((countHet() > 0) & (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
   
   - *I want to keep samples where the genotype for the first sample is homozygous variant and the genotype for the second sample is reference*:
 
     ::
   
-    (isHom( GEN[0] ) &amp; isVariant( GEN[0] ) &amp; isRef( GEN[1] ))
+    (isHom( GEN[0] ) & isVariant( GEN[0] ) & isRef( GEN[1] ))
 
 
 **For information regarding HGVS and Sequence Ontology terms versus classic names**:
@@ -185,5 +189,6 @@
 
 @CITATION_SECTION@
 
+]]>
     </help>
 </tool>