<tool id="goseq" name="goseq gene ontology analyser" version="0.1.4">
    <description />
    <requirements>
        <requirement type="package" version="3.2.1">R</requirement>
        <requirement type="package" version="1.22.0">goseq</requirement>
    </requirements>
    <command interpreter="Rscript">
        goseq.r --dge_file "$dge_file"
        --p_adj_column "$p_adj_column"
        --cutoff "$p_adj_cutoff"
        #if $source.use_length_file == "yes":
        --length_file "$length_file"
        #end if
        --genome "$genome"
        --gene_id "$gene_id"
        --wallenius_tab "$wallenius_tab"
        --sampling_tab "$sampling_tab"
        --nobias_tab "$nobias_tab"
        --length_bias_plot "$length_bias_plot"
        --sample_vs_wallenius_plot "$sample_vs_wallenius_plot"
        --repcnt "$repcnt"
    </command>
    <inputs>
        <param help="deseq2/edger/limma differential gene expression list" label="DGE list" name="dge_file" type="data" format="tabular" />
        <param help="Select the column that contains the multiple-testing corrected p-value" label="p adjust column" name="p_adj_column" type="data_column" numeric="true" data_ref="dge_file"/>
        <param help="Typically 0.05 after multiple testing correction" max="1" label="Minimum p adjust value to consider genes as differentially expressed" name="p_adj_cutoff" type="float" value="0.05" />
        <conditional name="source">
            <param help="This is needed if the gene length is not available in goseq. e.g. hg38 and mm10." label="Use gene length file?" name="use_length_file" type="select">
                <option value="no">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="yes">
                <param label="Gene length file" name="length_file" type="data" format="tabular" required="false" />
            </when>
            <when value="no">
            </when>
        </conditional>
        <param help="Needed to retrieve gene length for length correction" label="Select the genome source" name="genome" size="3" type="select">
            <options from_data_table="go_genomes"></options>
        </param>
        <param help="Needed for GO analysis" label="Select gene identifier" name="gene_id" type="select">
            <options from_data_table="go_gene_ids"></options>
        </param>
        <param help="Draw this many random control gene sets. Set to 0 to not do sampling. Larger values take a long time" label="sampling depth" name="repcnt" size="3" type="integer" min="0" max="10000" value="0" />
    </inputs>
    <outputs>
        <data format="pdf" label="length bias plot" name="length_bias_plot" />
        <data format="pdf" label="Plot P-value from sampling against wallenius distribution" name="sample_vs_wallenius_plot">
            <filter>repcnt != 0</filter>
        </data>
        <data format="tabular" label="Ranked category list - wallenius" name="wallenius_tab" />
        <data format="tabular" label="Ranked category list - sampling" name="sampling_tab">
            <filter>repcnt != 0</filter>
        </data>
        <data format="tabular" label="Ranked category list - no length bias correction" name="nobias_tab" />
    </outputs>
    <tests>
        <test>
            <param name="dge_file" value="dge_list.tab" ftype="tabular"/>
            <param name="use_length_file" value="no" />
            <param name="p_adj_column" value="2" />
            <param name="genome" value="hg19" />
            <param name="gene_id" value="ensGene" />
            <output name="wallenius_tab" file="wall.tab" compare="contains"/>/>
        </test>
    </tests>
    <help>

        **What it does**

        Detects Gene Ontology and/or other user defined categories which are over/under represented in RNA-seq data.

        Options map closely to the excellent manual_

        .. _manual: https://bioconductor.org/packages/release/bioc/vignettes/goseq/inst/doc/goseq.pdf


    </help>
    <citations>
        <citation type="doi">10.1186/gb-2010-11-2-r14</citation>
    </citations>
</tool>