<tool id="cfsan_lexmapr2" name="Lexmapr2" version="2.0+galaxy0">
    <description>A Lexicon and Rule-Based Tool for Translating Short Biomedical Specimen Descriptions into Semantic Web Ontology Terms</description>
    <requirements>
        <requirement type="package" version="3.7">python</requirement>
        <requirement type="package">python-dateutil</requirement>
        <requirement type="package">inflection</requirement>
        <requirement type="package">matplotlib</requirement>
        <requirement type="package">pandas</requirement>
        <requirement type="package">nltk</requirement>
        <requirement type="package">requests</requirement>
        <requirement type="package">seaborn</requirement>
        <requirement type="package">pygraphviz</requirement>
    </requirements>
    <version_command>python $__tool_directory__/lexmapr2.py --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
    python $__tool_directory__/lexmapr2.py
    #if ($embl_ont != ""):
        -e $embl_ont
    #end if
    $no_ancestors
    $bins
    $full
    $graph
    #for $in_json in $input_json
        #if $in_json
            -u "$in_json"
        #end if
    #end for
    ]]></command>
    <environment_variables>
        <environment_variable name="NLTK_DATA">$__tool_directory__/nltk_data</environment_variable>
    </environment_variables>
    <inputs>
        <param name="input" type="data" format="csv" label="Input CSV"
            help="First row should be a header and first column should be sample names" />
        <param name="input_json" type="data" format="json" optional="true"
            label="User defined bins in JSON format" />
        <param name="embl_ont" type="text" optional="true" 
            label="User defined comma-separated EMBL Ontology short names" />
        <param name="bins" truevalue="-b" type="boolean" checked="true"
            label="Classify samples into default bins" help="Default: true"/>
        <param name="graph" truevalue="-g" type="boolean" checked="true"
            label="Visualize summary of mapping and binning" help="Default: true"/>
        <param name="full" truevalue="-f" type="boolean" checked="false"
            label="Generate full output format" help="Default: false"/>
        <param name="no_ancestors" truevalue="-a" type="boolean" checked="false"
            label="Remove ancestral terms from output" help="Default: false"/>
    </inputs>
    <outputs>
        <data name="lexmapr2_output" format="tsv" label="Lexmapr2: On ${on_string}" from_work_dir="lexmapr2_output.tsv"/>
        <collection name="plots" type="list" label="Lexmapr2: Plots on ${on_string}">
            <discover_datasets pattern=".*\.png" ext="png" directory="lexmapr_figures"/>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="input" value="test.csv"/>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**Purpose**

Lexmapr2 is a fork of Lexmapr (https://github.com/cidgoh/LexMapr) with the following added functionalitites:

    ::

        - pull ontology accession ids and definitions from EMBL-EBI via the API
        - group mapped results by parent ontologies
        - visualize mapping results


----

.. class:: infomark

**Outputs**

The main output files are:

    ::

        - An tab-seperated file with matched annotations.
        - A list of Lexmapr2 figures in PNG format.

        

  ]]></help>
    <citations>
        <citation type="bibtex">
            @misc{github,
            author = {Penn, Kayla},
            year = {2022},
            title = {LexMapr2},
            publisher = {GitHub},
            journal = {GitHub repository},
            url = {https://github.com/CFSAN-Biostatistics/LexMapr2}}
        </citation>
        <citation type="bibtex">
            @misc{GalaxyToolWrapper,
            author = {Konganti, Kranti},
            year = {2022}}
        </citation>
    </citations>
</tool>