annotate goenrichment.xml @ 1:5ace5c7d1a86 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/goenrichment commit f88b350b77f77b559803a9bb8f9f1219950d0f9f

<tool id="goenrichment" name="GOEnrichment" version="2.0.1">
    <description>performs GO enrichment analysis of a set of gene products</description>
    <requirements>
        <requirement type="package" version="2.0.1">goenrichment</requirement>
    </requirements>
    <command detect_errors="exit_code">goenrichment 
--go '${go}'
--annotation '${annotation}'
--study '${study}'
#if str($population) != 'None'
--population '${population}'
#end if
--correction ${correction}
$summarize
$singletons
$relations
--graph_format $graph
--cut_off $cutoff
--mf_result '${mf_result}'
--bp_result '${bp_result}'
--cc_result '${cc_result}'
--mf_graph '${mf_graph}'
--bp_graph '${bp_graph}'
--cc_graph '${cc_graph}'
    </command>
    <inputs>
        <param name="go" type="data" format="obo,owl" label="Gene Ontology File" help="Gene Ontology file in OBO or OWL format (see http://geneontology.org/page/download-ontology)"/>
        <param name="annotation" type="data" format="tabular,txt" label="Gene Product Annotation File" help="Tabular file containing annotations from gene products to GO terms (in GAF or BLAST2GO format, or a simple two-column table)"/>
        <param name="study" type="data" format="txt" label="Study Set File" help="File containing the gene products corresponding to the study set (one per line)"/>
        <param name="population" type="data" format="txt" optional="true" label="Population Set File (Optional)" help="File containing the gene products corresponding to the population set (one per line). If no file is submitted, the population set will be the set of all gene products listed in the annotation file."/>
        <param name="correction" type="select" label="Multiple Test Correction" help="The multiple test correction method to use (Benjamini-Hochberg is recommended).">
            <option value="Benjamini-Hochberg" selected="true"/>
            <option value="SDA"/>
            <option value="Bonferroni-Holm"/>
            <option value="Sidak"/>
            <option value="Bonferroni"/>
        </param>
        <param name="cutoff" type="select" label="P-Value Cut-Off" help="The corrected p-value (or q-value) cut-off to apply for the graph output.">
            <option value="1.0"/>
            <option value="0.1"/>
            <option value="0.05"/>
            <option value="0.01" selected="true"/>
        </param>
        <param name="graph" type="select" label="Output Graph Format" help="The format of the output graphs (png, svg, or tabular for importing into cytoscape).">
            <option value="png" selected="true"/>
            <option value="svg"/>
            <option value="tabular"/>
        </param>
        <param name="summarize" type="boolean" checked="true" truevalue="--summarize_output" falsevalue="" label="Summarize Output" help="Whether to produce a summarized list of GO terms or the full list of those that are statistically significant"/>
        <param name="singletons" type="boolean" checked="true" truevalue="--ignore_singletons" falsevalue="" label="Exclude Singletons" help="Whether to exclude GO terms that are annotated to a single gene product in the study set"/>
        <param name="relations" type="boolean" checked="false" truevalue="--use_all_relations" falsevalue="" label="Use All Relations" help="Whether to infer annotations through 'part_of' and other non-hierarchical relationships, or only through 'is_a' relations"/>
    </inputs>
    <outputs>
        <data name="mf_result" format="tabular" label="${tool.name} on ${study.name} MF Result File"/>
        <data name="bp_result" format="tabular" label="${tool.name} on ${study.name} BP Result File"/>
        <data name="cc_result" format="tabular" label="${tool.name} on ${study.name} CC Result File"/>
        <data name="mf_graph" format="png" label="${tool.name} on ${study.name} MF Graph File">
            <change_format>
                <when input="graph" value="svg" format="svg"/>
                <when input="graph" value="tabular" format="tabular"/>
            </change_format>
        </data>
        <data name="bp_graph" format="png" label="${tool.name} on ${study.name} BP Graph File">
            <change_format>
                <when input="graph" value="svg" format="svg"/>
                <when input="graph" value="tabular" format="tabular"/>
            </change_format>
        </data>
        <data name="cc_graph" format="png" label="${tool.name} on ${study.name} CC Graph File">
            <change_format>
                <when input="graph" value="svg" format="svg"/>
                <when input="graph" value="tabular" format="tabular"/>
            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="go" ftype="obo" value="go.obo"/>
            <param name="annotation" ftype="txt" value="annotations.tab"/>
            <param name="study" ftype="txt" value="study.txt"/>
            <param name="summarize" value="false"/>
            <output name="mf_result" ftype="tabular" file="MF_result.txt" lines_diff="0"/>
        </test>
        <test>
            <param name="go" ftype="obo" value="go.obo"/>
            <param name="annotation" ftype="txt" value="annotations.tab"/>
            <param name="study" ftype="txt" value="study.txt"/>
            <param name="population" ftype="txt" value="population.txt"/>
            <param name="summarize" value="false"/>
            <output name="mf_result" ftype="tabular" file="MF_result.txt" lines_diff="0"/>
        </test>
    </tests>
    <help>
.. class:: infomark

GOEnrichment is a Java application that can be used to analyze gene product sets (e.g., from microarray or RNAseq experiments) for enriched GO terms.

-----

.. class:: infomark

GOEnrichment requires:

- A Gene Ontology file in either OBO or OWL format (see http://geneontology.org/page/download-ontology).
- A tabular annotation file in GAF (http://geneontology.org/page/download-annotations) format, BLAST2GO format, or a simple two-column table (e.g. from BioMart) with gene product ids in the first column and GO terms in the second one.
- A list of gene products comprising the study set (a flat text file with one gene product per line).
- Optionally, a list of gene products comprising the population set (if none is submitted, the population set will be the set of gene products listed in the annotation file).

-----

.. class:: infomark

GOEnrichment produces a tabular result file and a graph file for each GO type (MF - Molecular Function, BP - Biological Process and CC - Cellular Component):

- The result file is a tabular list of all GO terms present in the study set and their respective p-values.
- The graph file can be either a png image, an svg image, or a text file for importing into cytoscape (together with the result file).

-----

.. class:: infomark

The graph is colored by p-value: terms with p-value above cut-off appear in white; and the color gets darker as the p-value decreases

.. image:: https://github.com/DanFaria/GOEnrichment/raw/master/Scale.png
   :width: 600
   :height: 315

(see the scale at https://github.com/DanFaria/GOEnrichment/blob/master/Scale.png). In addition to the name of each GO term, the graph
shows its frequency in the study set. Dashed edges indicate that one or more intermediate terms were ommited from the graph.

-----

.. class:: warningmark

Gene products listed in either the study or population set files that are not present in the annotation file will be ignored.
    </help>

    <citations>
        <citation type="bibtex">
@misc{githubgoenrichment,
  author = {Faria, Daniel},
  year = {2017},
  title = {GOEnrichment},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/DanFaria/GOEnrichment},
}
        </citation>
    </citations>

</tool>