view cluster_butina_matrix.xml @ 0:0007486ac858 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/im-pipelines commit 598dd288a384481b7602a0f6322c5081dc8da5d9"

<tool id="ctb_im_cluster_butina_matrix" name="Butina Cluster Matrix" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@">
    <description>using RDKit</description>
    <macros>
        <import>macros.xml</import>
        <token name="@GALAXY_VERSION@">0</token>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
        cluster_butina_matrix
            -i '$infile'
            -if sdf
            -t '$threshold'
            -mt '$matrix_threshold'
            -d '$descriptor_opts'
            -m '$metric_opts'
            --meta
            -o outp
            -of tsv &>> $logfile &&
        cat outp_metrics.txt &>> $logfile &&
        gzip -d outp.tsv.gz
    ]]></command>
    <inputs>
        <param name="infile" type="data" format="sdf" label="Input file" help="Input file in SDF format"/>
        <param name="threshold" min="0" max="1" type="float" value="0.7" label="Threshold" help="Similarity clustering threshold (1.0 means identical)"/>
        <param name="matrix_threshold" min="0" max="1" type="float" value="0.5" label="Matrix threshold" help="Threshold for outputting values (1.0 means identical)"/>

        <param name="descriptor_opts" type="select" label="Descriptor Options" help="Descriptor or fingerprint type (default rdkit)">
            <option value="rdkit" selected="true">rdkit</option>
            <option value="maccs">maccs</option>
            <option value="morgan2">morgan2</option>
            <option value="morgan3">morgan3</option>
        </param>

        <param name="metric_opts" type="select" label="Similarity metric" help="Default is the Tanimoto coefficient">
            <option value="tanimoto" selected="true">tanimoto</option>
            <option value="asymmetric">asymmetric</option>
            <option value="braunblanquet">braunblanquet</option>
            <option value="cosine">cosine</option>
            <option value="dice">dice</option>
            <option value="kulczynski">kulczynski</option>
            <option value="mcconnaughey">mcconnaughey</option>
            <option value="rogotgoldberg">rogotgoldberg</option>
            <option value="russel">russel</option>
            <option value="sokal">sokal</option>
        </param>
    </inputs>

    <expand macro="outputs" output_format="tsv" filetype="tabular"/>

    <tests>
        <test>
            <param name="infile" value="Kinase_inhibs.sdf" ftype="sdf"/>
            <param name="descriptor_opts" value="rdkit"/>
            <param name="metric_opts" value="tanimoto"/>
            <param name="threshold" value="0.6"/>
            <param name="matrix_threshold" value="0.5"/>
            <output name="outfile" ftype="tabular" file="cluster_butina_matrix_output1.tsv"/>
            <output name="logfile">
                <assert_contents>
                    <has_text text="Found 30 clusters"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What this tool does**

This tool performs Butina clustering for a set of input molecules, using the chemistry toolkit RDKit, and returns results in tabular format.


-----

.. class:: infomark

**Input**

| - Molecules in `SDF format`_
| - A number of other parameters can be set, including the fingerprint type and the similarity metric to use.

.. _SDF format: http://en.wikipedia.org/wiki/Chemical_table_file


-----

.. class:: infomark

 **Output**

Tabular file containing clusters.

    ]]></help>
    <expand macro="citations"/>
</tool>