comparison raceid_clustering.xml @ 8:f911a64454fb draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/raceid3 commit 455bad7eca54164f95755174904842907846bb42"

7:c4f39bf4a068

<tool id="raceid_clustering" name="Clustering using RaceID" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" >
    <description>performs clustering, outlier detection, dimensional reduction</description>
    <macros>
        <import>macros.xml</import>
        <import>macros_cheetah.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command_config" prog="cluster.R" cheetah="CLUSTER_CHEETAH" out="&#38;&#62; '$outlog'" />

    <inputs>
        <param name="inputrds" type="data" format="rdata" label="Input RaceID RDS" help="Requires the RDS output from the normalisation stage" />
        <section name="clust" title="Clustering" expanded="true" >
            <!-- CompDist -->
            <param name="metric" type="select" label="Distance Metric" >
                <option value="pearson" selected="true" >Pearson</option>
                <option value="spearman">Spearman</option>

            <param name="pvalue" type="float" min="0" max="1" value="0.01" label="P-value Cutoff" help="P-value cutoff for the inference of differential gene expression" />
        </section>
    </inputs>
    <outputs>
        <data name="outpdf" format="pdf" label="${tool.name} on ${on_string}: PDF Report" />
        <data name="outrdat" format="rdata" label="${tool.name} on ${on_string}: RDS" />
        <data name="outassignments" format="tabular" label="${tool.name} on ${on_string}: Cell-to-Cluster assignments" />
        <data name="outgenelist" format="tabular" label="${tool.name} on ${on_string}: Cluster - Genes per Cluster" />
        <data name="outlog" format="txt" label="${tool.name} on ${on_string}: Log" >
            <filter>use_log</filter>
        </data>

                <assert_contents>
                    <has_line_matching expression=".*ENSDARG00000108379\s+1.*" />
                    <has_line_matching expression=".*ENSDARG00000027310\s+8.*" />
                </assert_contents>
            </output>
            <output name="outrdat" value="matrix2.rdat" compare="sim_size" delta="500" />
            <output name="outpdf" value="matrix2.pdf" compare="sim_size" delta="100" />
            <output name="outassignments" >
                <assert_contents>
                    <has_line_matching expression="P1_B1_ATCCAC\s1\s1\sFALSE" />
                </assert_contents>

        * Good stable clusters should near the 0.8 mark, but 0.6 is acceptable, and for a large number of clusters, one or two low scoring clusters are also acceptable.
 * Heatmaps:
     * The initial and final clustering (as determined using random forest)
     * For each of the most differentially expressed genes in each cluster

The tool requires the RData input from the previous filtering / normalisation / confounder removal step to work.


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

8:f911a64454fb

<tool id="raceid_clustering" name="Clustering using RaceID" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@" >
    <description>performs clustering, outlier detection, dimensional reduction</description>
    <macros>
        <import>macros.xml</import>
        <import>macros_cheetah.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command_config" prog="cluster.R" cheetah="CLUSTER_CHEETAH" out="&#38;&#62; '$outlog'" />

    <inputs>
        <param name="inputrds" type="data" format="rds" label="Input RaceID RDS" help="Requires the RDS output from the normalisation stage" />
        <section name="clust" title="Clustering" expanded="true" >
            <!-- CompDist -->
            <param name="metric" type="select" label="Distance Metric" >
                <option value="pearson" selected="true" >Pearson</option>
                <option value="spearman">Spearman</option>

            <param name="pvalue" type="float" min="0" max="1" value="0.01" label="P-value Cutoff" help="P-value cutoff for the inference of differential gene expression" />
        </section>
    </inputs>
    <outputs>
        <data name="outpdf" format="pdf" label="${tool.name} on ${on_string}: PDF Report" />
        <data name="outrdat" format="rds" label="${tool.name} on ${on_string}: RDS" />
        <data name="outassignments" format="tabular" label="${tool.name} on ${on_string}: Cell-to-Cluster assignments" />
        <data name="outgenelist" format="tabular" label="${tool.name} on ${on_string}: Cluster - Genes per Cluster" />
        <data name="outlog" format="txt" label="${tool.name} on ${on_string}: Log" >
            <filter>use_log</filter>
        </data>

                <assert_contents>
                    <has_line_matching expression=".*ENSDARG00000108379\s+1.*" />
                    <has_line_matching expression=".*ENSDARG00000027310\s+8.*" />
                </assert_contents>
            </output>
            <output name="outrdat" value="matrix2.rdat" compare="sim_size" delta="40000" />
            <output name="outpdf" value="matrix2.pdf" compare="sim_size" delta="100" />
            <output name="outassignments" >
                <assert_contents>
                    <has_line_matching expression="P1_B1_ATCCAC\s1\s1\sFALSE" />
                </assert_contents>

        * Good stable clusters should near the 0.8 mark, but 0.6 is acceptable, and for a large number of clusters, one or two low scoring clusters are also acceptable.
 * Heatmaps:
     * The initial and final clustering (as determined using random forest)
     * For each of the most differentially expressed genes in each cluster

The tool requires the RDS input from the previous filtering / normalisation / confounder removal step to work.


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