view gemini_load.xml @ 1:d3c4d0208bb2 draft

Uploaded

<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.0">
    <description>Loading a VCF file into GEMINI</description>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <macros>
        <import>gemini_macros.xml</import>
        <token name="@BINARY@">load</token>
    </macros>
    <command>
<![CDATA[
        gemini 
            --annotation-dir ${annotation_databases.fields.path}
            @BINARY@
            -v "${ infile }"
            -t $annotation_type

            #if $ped:
                -p $ped
            #end if

            $skip_gerp_bp
            $skip_cadd
            $skip_gene_tables
            $no_load_genotypes
            $no_genotypes
            $passonly
            --cores \${GALAXY_SLOTS:-4}

            "${ outfile }"
]]>
    </command>
    <expand macro="stdio" />
    <inputs>
        <param name="infile" type="data" format="vcf" label="VCF file to be loaded in the GEMINI database" />

        <param name="annotation_type" type="select" label="The annotations to be used with the input vcf" help="(-t)">
            <option value="snpEff">snpEff annotated VCF file</option>
            <option value="VEP">VEP annotated VCF file</option>
        </param>
        <param name="ped" type="data" format="tablar" optional="True" label="Sample information file in PED+ format" help="(-p)" />
        <expand macro="annotation_dir" />

        <param name="skip_gerp_bp" type="boolean" truevalue="--skip-gerp-bp" falsevalue="" checked="False" 
            label="Do not load GERP scores at base pair resolution" help="(--skip-gerp-bp)"/>

        <param name="skip_cadd" type="boolean" truevalue="--skip-cadd" falsevalue="" checked="False" 
            label="Do not load CADD scores" help="(--skip-cadd)"/>

        <param name="skip_gene_tables" type="boolean" truevalue="--skip-gene-tables" falsevalue="" checked="False" 
            label="Do not load gene tables" help="(--skip-gene-tables)"/>

        <param name="no_load_genotypes" type="boolean" truevalue="--no-load-genotypes" falsevalue="" checked="False" 
            label="Genotypes exist in the file, but should not be stored" help="(--no-load-genotypes)"/>

        <param name="no_genotypes" type="boolean" truevalue="--no-load-genotypes" falsevalue="" checked="False" 
            label="There are no genotypes in the file" help="e.g. some 1000G VCFs (--no-genotypes)"/>

        <param name="passonly" type="boolean" truevalue="--passonly" falsevalue="" checked="False" 
            label="Keep only variants that pass all filters" help="e.g. some 1000G VCFs (--passonly)"/>

    </inputs>
    <outputs>
        <data name="outfile" format="sqlite" label="${tool.name} on ${on_string}" />
    </outputs>
    <tests>
        <test>
        </test>
    </tests>
    <help>
**What it does**

Before we can use GEMINI to explore genetic variation, we must first load our VCF file into the GEMINI database framework.
We expect you to have first annotated the functional consequence of each variant in your VCF using either VEP or snpEff.

http://gemini.readthedocs.org/en/latest/content/loading.html

@CITATION@
    </help>
    <expand macro="citations"/>
</tool>