annotate goseq.xml @ 0:ade933eff007 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/goseq commit b7dcd020c6a15fa55f392cc09cbc37580d6e75c4

<tool id="goseq" name="goseq" version="0.2.2">
    <description>tests for overrepresented gene categories</description>
    <requirements>
        <requirement type="package" version="1.3.2">r-optparse</requirement>
        <requirement type="package" version="1.22.0">bioconductor-goseq</requirement>
    </requirements>
    <stdio>
        <regex match="Execution halted"
               source="both"
               level="fatal"
               description="Execution halted." />
        <regex match="Error in"
               source="both"
               level="fatal"
               description="An undefined error occured, please check your input carefully and contact your administrator." />
        <regex match="Fatal error"
               source="both"
               level="fatal"
               description="An undefined error occured, please check your input carefully and contact your administrator." />
    </stdio>
    <command><![CDATA[
        Rscript '$__tool_directory__'/goseq.r --dge_file '$dge_file'
        --length_file '$length_file'
        --category_file '$category_file'
        #if $methods['wallenius']:
        --wallenius_tab '$wallenius_tab'
        #end if
        #if $methods['hypergeometric']:
        --nobias_tab 'nobias_tab'
        #end if
        --repcnt '$methods.repcnt'
        --sampling_tab '$sampling_tab'
        --p_adj_method '$p_adj_method'
        --use_genes_without_cat '$use_genes_without_cat'
        --make_plots '$make_plots'
        --length_bias_plot '$length_bias_plot'
        --sample_vs_wallenius_plot '$sample_vs_wallenius_plot'
    ]]></command>
    <inputs>
        <param name="dge_file" help="A tabular file with gene names in the first column, and TRUE or FALSE in the last column. TRUE means a gene is differentially expressed. See help section for details." label="Differentially expressed gene file" type="data" format="tabular" />
        <param name="length_file" label="Gene length file for length bias correction" help="You can calculate the gene length using the get length and gc content tool" type="data" format="tabular" />
        <param name="category_file" label="Gene category file" help="You can obtain a mapping of gene id to gene ontology using the getgo tool" type="data" format="tabular" />
        <param name="use_genes_without_cat" help="For example, a large number of gene may have no GO term annotated. If this option is set to FALSE, those genes will be ignored in the calculation of p-values. If this option is set to TRUE, then these genes will count towards the total number of genes outside the category being tested"
               label="Count genes without any category?" type="boolean"/>
        <section name="methods" title="Method options" expanded="True">
            <param name="wallenius" type="boolean" checked="true" label="Use wallenius method" help="See help for details" />
            <param name="hypergeometric" type="boolean" checked="false" label="Use hypergeometric method" help="Does not use gene length information. See help for details" />
            <param name="repcnt" help="Draw this many random control gene sets. Set to 0 to not do sampling. Larger values take a long time" label="sampling depth" size="3" type="integer" min="0" max="10000" value="0" />
        </section>
        <param name="p_adj_method" type="select" label="Select a method for multiple hypothesis testing correction">
            <option value="BH" selected="true">Benjamini-Hochberg [FDR] (1995)</option>
            <option value="holm">Holm (1979)</option>
            <option value="hommel">Hommel (1988)</option>
            <option value="hochberg">Hochberg (1988)</option>
            <option value="bonferroni">Bonferroni</option>
            <option value="BY">Benjamini - Yekutieli (2001)</option>
        </param>
        <param help="These plots may help you compare the different p-value estimation methods that goseq can use." label="Produce diagnostic plots?" name="make_plots" type="boolean"></param>
    </inputs>
    <outputs>
        <data name="length_bias_plot" format="pdf" label="length bias plot">
            <filter>make_plots</filter>
            <filter>methods['hypergeometric']</filter>
        </data>
        <data name="sample_vs_wallenius_plot" format="pdf" label="Plot P-value from sampling against wallenius distribution">
            <filter>methods['repcnt'] != 0</filter>
            <filter>methods['wallenius']</filter>
            <filter>make_plots</filter>
        </data>
        <data name="nobias_tab" format="tabular" label="Ranked category list - no length bias correction">
            <filter>methods['hypergeometric']</filter>
        </data>
        <data name="sampling_tab" format="tabular" label="Ranked category list - sampling">
            <filter>methods['repcnt'] != 0</filter>
        </data>
        <data name="wallenius_tab" format="tabular" label="Ranked category list - wallenius method">
            <filter>methods['wallenius']</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="dge_file" value="dge_list.tab" ftype="tabular"/>
            <param name="length_file" value="gene_length.tab" ftype="tabular"/>
            <param name="category_file" value="category.tab" ftype="tabular"/>
            <param name="use_genes_without_cat" value="true" />
            <output name="wallenius_tab" file="wal.tab" compare="re_match"/>
        </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_


        **Input files**

        *DGE list:*
        goseq needs a tabular file with genes in the first column, and TRUE or FALSE in the last column.
        TRUE means the gene should count as differentially expressed, FALSE means it is not differentially expressed.
        You can use the "Compute an expression on every row" tool to create a TRUE / FALSE column for your dataset.

        *Gene length file:*
        goseq needs information about the length of a gene to correct for potential length bias in differentially expressed genes
        using a prodbability weight function (PWF).
        The format of this file is tabular, with gene_id in the first column and length in the second column.
        The "get length and gc content" tool can produce such a file.

        *Gene category file:*
        You will also need a file describing the membership of genes in categories. The format of this file is gene_id in the first column,
        category name in the second column. If you are interested in gene ontology categories you can use the getgo file to retrive
        gene ontologies for model organisms, or you can construct your own file.

        **Method options**

        3 methods, "Wallenius", "Sampling" and "Hypergeometric", can be used to calculate the p-values as follows.

        *"Wallenius"* approximates the true distribution of numbers of members of a category amongst DE genes by the Wallenius non-central hypergeometric distribution.
        This distribution assumes that within a category all genes have the same probability of being chosen.
        Therefore, this approximation works best when the range in probabilities obtained by the probability weighting function is small.

        *"Sampling"* uses random sampling to approximate the true distribution and uses it to calculate the p-values for over (and under) representation of categories.
        Although this is the most accurate method given a high enough value of sampling depth, its use quickly becomes computationally prohibitive.

        *"Hypergeometric"* assumes there is no bias in power to detect differential expression at all and calculates the p-values using a standard hypergeometric distribution.
        Useful if you wish to test the effect of selection bias on your results.

        CAUTION:  "Hypergeometric" should NEVER be used for producing results for biological interpretation.
        If there is genuinely no bias in power to detect DE in your experiment, the PWF will reflect this and the other methods will produce accuracte results.

        .. _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>