view cluster.xml @ 29:57e22d15fed9 draft default tip

planemo upload for repository https://github.com/quadram-institute-bioscience/galaxy-tools/tree/master/tools/bin3C commit a5926dec65ac1474e7b79685df5b9330601ef167-dirty

<tool id="cluster" name="cluster" version="@VERSION@">
    <description>Cluster an existing contact map into genome bins</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
        #if $compress:
            gzip < $contact_map > contact_map.p.gz &&
        #else:
            ln -s $contact_map contact_map.p.gz &&
        #end if

        bin3C cluster
        --max-image $max_image
        --min-extent $min_extent
        --min-reflen $min_reflen
        --min-signal $min_signal
        -s 201987356473
        --assembler $assembler
        $no_report
        $no_plot
        $no_fasta
        $only_large
        --fasta $contigs
        --n-iter $iteration
        contact_map.p.gz out
    ]]>    </command>

    <inputs>
        <param name="contact_map" type="data" format="binary" label="Contact map" help="This file is generated from mkmap command" />
        <param name="contigs" type="data" format="fasta,fastq.gz" label="Contigs from that supplied during mkmap" />
        <param name="assembler" label="Assembly software used to create contigs" type="select">
            <option selected="true" value="generic">generic</option>
            <option value="megahit">megahit</option>
            <option value="spades">spades</option>
        </param>
        <param name="max_image" type="integer" min="1" value="4000" label="Maximum image size for plots"/>
        <param name="min_extent" type="integer" min="1" value="50000" label="Minimum cluster extent used in output"/>
        <param name="min_reflen" type="integer" min="1" value="1000" label="Minimum acceptable reference length"/>
        <param name="min_signal" type="integer" min="1" value="5" label="Minimum acceptable signal"/>
        <param name="iteration" type="integer" min="1" value="10" label="Number of iterations for clustering optimisation"/>
        <param name="no_report" type="boolean" truevalue="--no-report" falsevalue="" checked="false" label="Do not generate a cluster report" />
        <param name="no_plot" type="boolean" truevalue="--no-plot" falsevalue="" checked="false" label="Do not generate a clustered heatmap" />
        <param name="no_fasta" type="boolean" truevalue="--no-fasta" falsevalue="" checked="false" label="Do not generate cluster FASTA files" />
        <param name="only_large" type="boolean" truevalue="--only-large" falsevalue="" checked="false" label="Only write FASTA for clusters longer than min_extent" />
        <param name="compress" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Compress contact map before run" help="Only choose when the contact map was not generated by mkmap on Galaxy" />
    </inputs>

    <outputs>
        <data name="log" format="text" label="${tool.name} on ${on_string} Log" from_work_dir="out/bin3C.log"/>
        <data name="clustering_mcl" format="binary" label="${tool.name} on ${on_string} 	Clustering solution in MCL format" from_work_dir="out/clustering.mcl"/>
        <data name="clustering_p_gz" format="binary" label="${tool.name} on ${on_string} Clustering solution as a picked python dictionary" from_work_dir="out/clustering.p.gz"/>
        <data name="clustering_plot" format="png" label="${tool.name} on ${on_string} Heatmap of the contact map after clustering" from_work_dir="out/cluster_plot.png"/>
        <data name="clustering_csv" format="tabular" label="${tool.name} on ${on_string} A per-cluster report of various statistics" from_work_dir="out/cluster_report.csv"/>
        <data name="cm_graph_edges" format="binary" label="${tool.name} on ${on_string} The graph used in clustering in edge list format" from_work_dir="out/cm_graph.edges"/>
        <data name="cm_graph_tree" format="text" label="${tool.name} on ${on_string} Infomap clustering output" from_work_dir="out/cm_graph.tree"/>
        <collection type="list" name="fasta" label="${tool.name} on ${on_string} Per-cluster multi-fasta sequences">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.fna" directory="out/fasta" ext="fna" visible="false" />
        </collection>
    </outputs>

    <help><![CDATA[

    Documentation can be found at `<https://github.com/cerebis/bin3C>`_.

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