comparison Marea/marea_cluster.xml @ 0:23ac9cf12788 draft

Uploaded

0:23ac9cf12788

<tool id="MaREA_cluester" name="MaREA cluster analysis">
    <description>of Reaction Activity Scores</description>
    <requirements>
        <requirement type="package">pandas</requirement>
        <requirement type="package">scikit-learn</requirement>
        <requirement type="package">scipy</requirement>
        <requirement type="package">matplotlib</requirement>
        <requirement type="package">cobrapy</requirement>
        <requirement type="package">python-libsbml</requirement>
    </requirements>
    <command>
        <![CDATA[
      	python $__tool_directory__/marea_cluster.py
        --rules_selector $cond_rule.rules_selector
        #if $cond_rule.rules_selector == 'Custom':
            --custom ${cond_rule.Custom_rules}
        #end if
        --cond_hier $cond_hier.hier
        #if $cond_hier.hier == 'yes':
            --linkage ${cond_hier.linkage}
            --dendro $dendrogram
        #end if
        --k_max $k_max
        --k_min $k_min
        --data $input
        --name $name
      	--none $None
      	--tool_dir $__tool_directory__
        --out_log $log
        --elbow $elbow
        ]]>
    </command>
    <inputs>
        <conditional name="cond_rule">
            <param name="rules_selector" type="select" label="Gene-Protein-Reaction rules:">
                <option value="HMRcore" selected="true">HMRcore rules</option>
                <option value="Recon">Recon 2.2 rules</option>
                <option value="Custom">Custom rules</option>
            </param>
            <when value="Custom">
                <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules"/>
            </when>
        </conditional>
        <param name="input" type="data" format="tabular, csv, tsv" label="RNAseq of all samples"/>
        <param name="name" type="text" label="Output name prefix" value = "dataset"/>
        <param name="k_min" type="integer" size="20" value="3" min="2" max="30" label="min number of clusters (k) to be tested (k-means)"/>
        <param name="k_max" type="integer" size="20" value="3" min="2" max="30" label="max number of clusters (k) to be tested (k-means)"/>
        <param name="None" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" help="if NO is selected (A and NaN) is solved as (NaN)"/>
	<conditional name="cond_hier">
            <param name="hier" type="select" label="Produce dendrogram (hierarchical clustering):">
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="yes">
                <param name="linkage" type="select" label="Linkage type:">
                    <option value="single" selected="true">Single: minimum distance between all observations of two sets</option>
                    <option value="complete">Complete: maximum distance between all observations of two sets</option>
                    <option value="average">Average: average distance between all observations of two sets</option>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="txt" name="log" label="Log"/>
        <data format="pdf" name="dendrogram" label="$name dendrogram">
            <filter>cond_hier['hier'] == 'yes'</filter>
        </data>
        <data format="pdf" name="elbow" label="$name elbow evaluation method"/>
        <collection name="cluster_out" type="list" label="Clusters $k_min - $k_max">
            <discover_datasets pattern="__name_and_ext__" directory="cluster_out"/>
        </collection>
    </outputs>
    <help>

.. class:: warningmark

This tool expects input datasets consisting of tab-delimited columns.

.. class:: infomark

**TIP:** If your data is not TAB delimited, use *Text Manipulation > Convert delimiters to TAB*

    </help>
</tool>