annotate table_annovar.xml @ 5:7d2a81d29ca4 draft

Uploaded

<tool id="table_annovar" name="ANNOVAR Annotate VCF" version="0.1">
    <description>with functional information using ANNOVAR</description>

    <requirements>
        <requirement type="package">annovar</requirement>
        <requirement type="set_environment">SCRIPT_PATH</requirement>
    </requirements>

    <command>
        ## Convert VCF to AV input format.
        convert2annovar.pl -format vcf4 -includeinfo ${input} > input.avinput

        ## Variant annotation; make sure to include entry in indexes table for build database. 

        #set protocol = []
        #set operation = []

        ## Add gene annotations.
        #if $gene_anns:
            #silent protocol.append( str( $gene_anns )  )
            #silent operation.append( ','.join( ['g' for t in range( str($gene_anns).count(',') + 1 )] ) )
        #end if

        ## Add regions.
        #if $regions:
            #silent protocol.append( str( $regions ) )
            #silent operation.append( ','.join( ['r' for t in range( str($regions).count(',') + 1 )] ) )
        #end if

        ## Add filters.
        #if $filters:
            #silent protocol.append( str( $filters ) )
            #silent operation.append( ','.join( ['f' for t in range( str($filters).count(',') + 1 )] ) )
        #end if

        #set protocol = ','.join( $protocol )
        #set operation = ','.join( $operation ) 

        ## Reduce variants.
        ; table_annovar.pl input.avinput ${__get_data_table_entry__('annovar_indexes', 'dbkey', $input.dbkey, 'path')} -protocol ${protocol} -operation ${operation} -nastring NA -buildver ${input.dbkey} --outfile output

        ## Process annotated table to remove "NA" strings from numerical columns and copy to output.
        ; cat output.${input.dbkey}_multianno.txt | \$SCRIPT_PATH/replace_NA.py > ${output}
    </command>

    <inputs>
        <param name="input" type="data" format="vcf" metadata_name="dbkey" label="Variants" help="">
        <validator type="unspecified_build" />
    </param>

    <param name="gene_anns" type="select" multiple="True" optional="True" label="Gene Annotations" help="" >
        <options from_data_table="annovar_indexes">
            <filter type="data_meta" key="dbkey" ref="input" column="1"/>
            <filter type="static_value" name="type" value="gene_ann" column="2"/>
        </options>
    </param>

    <param name="regions" type="select" multiple="True" optional="True" label="Annotation Regions" help="" >
        <options from_data_table="annovar_indexes">
            <filter type="data_meta" key="dbkey" ref="input" column="1"/>
            <filter type="static_value" name="type" value="region" column="2"/>
        </options>
    </param>
    
    <param name="filters" type="select" multiple="True" label="Annotation Databases" help="" >
        <options from_data_table="annovar_indexes">
            <filter type="data_meta" key="dbkey" ref="input" column="1"/>
            <filter type="static_value" name="type" value="filter" column="2"/>
        </options>
    </param>
    </inputs>

    <stdio>
        <regex match=".*" source="both" level="log" description="tool progress"/>
    </stdio>

    <outputs>
        <data name="output" format="tabular"/>
    </outputs>

    <tests>
    </tests>

    <help>
**What it does**

This tool will annotate variants using specified gene annotations, regions, and filtering databases. Input is a VCF dataset, and output is a table of annotations for each variant in the 
VCF dataset.

**ANNOVAR Website and Documentation**

Website: http://www.openbioinformatics.org/annovar/

Paper: http://nar.oxfordjournals.org/content/38/16/e164

**Important Usage Note**

ANNOVAR is open-source and free for non-profit use. If you use it for commercial purposes, please contact BIOBASE ([e-mail]) directly for license related issues. Also see http://www.openbioinformatics.org/annovar/annovar_faq.html#license

    </help>
</tool>