comparison snpSift_filter.xml @ 14:80da7fae14b8 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f

13:ed810da439cc

<tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.0">
    <description>Filter variants using arbitrary expressions</description>
    <macros>
        <import>snpSift_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <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:
                --pass
                #if $filtering.replace.filterId and len(str($filtering.replace.filterId).strip()) > 0:
                    --filterId "$filtering.replace.filterId"

]]>
    </command>
    <configfiles>
        <configfile name="exprFile">
$expr#slurp
        </configfile> 
    </configfiles>
    <inputs>
        <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
        <param name="expr" type="text" label="Filter criteria" help="Need help? See below a few examples." >
            <sanitizer sanitize="False"/>

        <param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse filter" help="Show lines that do not match filter expression" />
        <conditional name="filtering">
            <param name="mode" type="select" label="Filter mode">
                <option value="entries" selected="true">Retain entries that pass filter, remove other entries</option>
                <option value="field">Change the FILTER field, but retain all entries</option>
            </param> 
            <when value="entries"/>
            <when value="field">
                <conditional name="replace">
                    <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'" 
                           help="appends an ID tag to non-matching entry FILTER "/>
                    <when value="no"/>
                    <when value="yes">
                        <param name="filterId" type="text" value="" optional="true" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)." 
                               help="Default ID is 'SnpSift'"/>
                    </when>
                </conditional>
                <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." />
                <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)." />
            </when>
        </conditional>
    </inputs>

    <outputs>

  - *Filter value is either 'PASS' or it is missing*:

    ::

    (FILTER = 'PASS') | ( na FILTER )  

  - *I want to filter lines with an ANN annotation EFFECT of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*:

    ::
  
    ( 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 )*:

    ::
  
    ( EFF[*].EFFECT = 'FRAME_SHIFT' )

  - *I want to filter out samples with quality less than 30*:

    ::

  - *...but we also want InDels that have quality 20 or more*:

    ::

    (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
  
  - *...or any homozygous variant present in more than 3 samples*:

    ::

    (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
  
  - *...or any heterozygous sample with coverage 25 or more*:

    ::

    ((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] ) & isVariant( GEN[0] ) & isRef( GEN[1] ))


**For information regarding HGVS and Sequence Ontology terms versus classic names**:

14:80da7fae14b8

<tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.1">
    <description>Filter variants using arbitrary expressions</description>
    <macros>
        <import>snpSift_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />

    <command><![CDATA[
        @CONDA_SNPSIFT_JAR_PATH@ &&
        java -Xmx6G -jar "\$SNPSIFT_JAR_PATH/SnpSift.jar" filter -f "$input" -e "$exprFile" $inverse
        #if $filtering.mode == 'field':
            #if $filtering.replace.pass:
                --pass
                #if $filtering.replace.filterId and len(str($filtering.replace.filterId).strip()) > 0:
                    --filterId "$filtering.replace.filterId"

]]>
    </command>
    <configfiles>
        <configfile name="exprFile">
$expr#slurp
        </configfile>
    </configfiles>
    <inputs>
        <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
        <param name="expr" type="text" label="Filter criteria" help="Need help? See below a few examples." >
            <sanitizer sanitize="False"/>

        <param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse filter" help="Show lines that do not match filter expression" />
        <conditional name="filtering">
            <param name="mode" type="select" label="Filter mode">
                <option value="entries" selected="true">Retain entries that pass filter, remove other entries</option>
                <option value="field">Change the FILTER field, but retain all entries</option>
            </param>
            <when value="entries"/>
            <when value="field">
                <conditional name="replace">
                    <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'"
                           help="appends an ID tag to non-matching entry FILTER "/>
                    <when value="no"/>
                    <when value="yes">
                        <param name="filterId" type="text" value="" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)." help="Default ID is 'SnpSift'"/>
                    </when>
                </conditional>
                <param name="addFilter" type="text" value="" label="Add a string to FILTER VCF field if 'expression' is true." />
                <param name="rmFilter" type="text" value="" label="Remove a string from FILTER VCF field if 'expression' is true (and 'str' is in the field)." />
            </when>
        </conditional>
    </inputs>

    <outputs>

  - *Filter value is either 'PASS' or it is missing*:

    ::

    (FILTER = 'PASS') | ( na FILTER )

  - *I want to filter lines with an ANN annotation EFFECT of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*:

    ::

    ( 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 )*:

    ::

    ( EFF[*].EFFECT = 'FRAME_SHIFT' )

  - *I want to filter out samples with quality less than 30*:

    ::

  - *...but we also want InDels that have quality 20 or more*:

    ::

    (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )

  - *...or any homozygous variant present in more than 3 samples*:

    ::

    (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )

  - *...or any heterozygous sample with coverage 25 or more*:

    ::

    ((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] ) & isVariant( GEN[0] ) & isRef( GEN[1] ))


**For information regarding HGVS and Sequence Ontology terms versus classic names**: