diff snpSift_filter.xml @ 0:e1d9f6a0ad53

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/snpSift_filter.xml	Thu Jul 04 10:43:55 2013 -0400
@@ -0,0 +1,127 @@
+<tool id="snpSift_filter" name="SnpSift Filter" version="3.2">
+	<options sanitize="False" />
+	<description>Filter variants using arbitrary expressions</description>
+	<requirements>
+                <requirement type="package" version="3.2">snpEff</requirement>
+	</requirements>
+	<command>
+		java -Xmx6G -jar \$JAVA_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse $pass 
+                #if $filterId and len($filterId.__str__.strip()) > 0:
+			--filterId = "$filterId"
+                #end if
+                #if $addFilter and len($addFilter.__str__.strip()) > 0:
+			--addFilter = "$addFilter"
+                #end if
+                #if $rmFilter and len($rmFilter.__str__.strip()) > 0:
+			--rmFilter = "$rmFilter"
+                #end if
+ 		> $output
+	</command>
+	<inputs>
+		<param format="vcf" name="input" type="data" label="VCF input"/>
+		<param name="expr" type="text" label="Expression" size="120"/>
+		<param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse. Show lines that do not match filter expression"/>
+		<param name="pass" type="boolean" truevalue="--pass" falsevalue="" checked="false" label="Use 'PASS' field instead of filtering out VCF entries"/>
+		<param name="filterId" type="text" value="" optional="true" label="ID for this filter (##FILTER tag in header and FILTER VCF field)." size="10"/>
+		<param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." size="10"/>
+		<param name="rmFilter" type="text" value="" optional="true" label="Remove a string from FILTER VCF field if 'expression' is true (and 'str' is in the field)." size="10"/>
+	</inputs>
+	<configfiles>
+		<configfile name="exprFile">
+		$expr
+		</configfile> 
+	</configfiles>
+
+	<outputs>
+		<data format="vcf" name="output" />
+	</outputs>
+        <stdio>
+          <exit_code range=":-1"  level="fatal"   description="Error: Cannot open file" />
+          <exit_code range="1:"  level="fatal"   description="Error" />
+        </stdio>
+
+        <tests>
+
+            <test>
+                <param name="input" ftype="vcf" value="test01.vcf"/>
+                <param name="expr" value="QUAL >= 50"/>
+                <output name="output">
+                    <assert_contents>
+                        <has_text text="28837706" />
+                        <not_has_text text="NT_166464" />
+                    </assert_contents>
+                </output>
+            </test>
+
+            <test>
+                <param name="input" ftype="vcf" value="test01.vcf"/>
+                <param name="expr" value="(CHROM = '19')"/>
+                <output name="output">
+                    <assert_contents>
+                        <has_text text="3205820" />
+                        <not_has_text text="NT_16" />
+                    </assert_contents>
+                </output>
+            </test>
+
+            <test>
+                <param name="input" ftype="vcf" value="test01.vcf"/>
+                <param name="expr" value="(POS >= 20175) &amp; (POS &lt;= 35549)"/>
+                <output name="output">
+                    <assert_contents>
+                        <has_text text="20175" />
+                        <has_text text="35549" />
+                        <has_text text="22256" />
+                        <not_has_text text="18933" />
+                        <not_has_text text="37567" />
+                    </assert_contents>
+                </output>
+            </test>
+
+            <test>
+                <param name="input" ftype="vcf" value="test01.vcf"/>
+                <param name="expr" value="( DP >= 5 )"/>
+                <output name="output">
+                    <assert_contents>
+                        <has_text text="DP=5;" />
+                        <has_text text="DP=6;" />
+                        <not_has_text text="DP=1;" />
+                    </assert_contents>
+                </output>
+            </test>
+
+        </tests>
+
+	<help>
+
+**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.
+
+Some examples:
+
+  - *I want to filter out samples with quality less than 30*:
+
+    * **( QUAL &gt; 30 )**
+
+  - *...but we also want InDels that have quality 20 or more*:
+
+    * **(( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )**
+
+  - *...or any homozygous variant present in more than 3 samples*:
+
+    * **(countHom() > 3) | (( exists INDEL ) &amp; (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 )**
+
+  - *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] )**
+
+
+For complete details about this tool and epressions that can be used, please go to http://snpeff.sourceforge.net/SnpSift.html#filter
+
+	</help>
+</tool>