comparison high_dim_visu.xml @ 5:569334568afa draft

"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/gsc_high_dimension_visualization commit 1b98c85982a2a9f9df4b318f672b9b68cff66a93"

4:8e17c31c536a

<tool id="high_dimensions_visualisation" name="Generate PCA, tSNE and HCPC" version="0.9.4">
    <description>from highly dimensional expression data</description>
    <requirements>
        <requirement type="package" version="1.6.2=r35h6115d3f_0">r-optparse</requirement>
        <requirement type="package" version="1.42=r35h6115d3f_0">r-factominer</requirement>
        <requirement type="package" version="1.0.5">r-factoextra</requirement>
        <requirement type="package" version="0.15=r351he1b5a44_0">r-rtsne</requirement>
        <requirement type="package" version="0.4.7=r351h6115d3f_0">r-ggfortify</requirement>
        <requirement type="package" version="1.1.9=r351h0357c0b_0">r-clusterr</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[ 

                --HCPC_itermax '$visualisation.HCPC_itermax'
                --HCPC_min '$visualisation.HCPC_min'
                --HCPC_max '$visualisation.HCPC_max'
                --HCPC_clusterCA '$visualisation.HCPC_clusterCA'
                --HCPC_kk '$visualisation.HCPC_kk'
                #if $visualisation.res_clustering == "yes":
                    --HCPC_clust '$HCPC_clust'
                #end if 
            #end if
            

                --PCA_x_axis '$visualisation.PCA_x_axis'
                --PCA_y_axis '$visualisation.PCA_y_axis'
            #end if
            
            #if $visualisation.visu_choice == "HCPC" and $factor_condition.factor_choice == "Yes":
                --mutual_info '$mutual_info'
            #end if            

            --pdf_out '$pdf_out'
            
]]></command>

            </when>
            <when value="HCPC">
                <param name="HCPC_npc" value="5" type="integer" label="Number of principal components to keep"
                       help="The number of dimensions which are kept for HCPC analysis (default=5)" />
                <param name="HCPC_ncluster" value="-1" type="integer" label="Number of clusters in Hierar. Clustering"
                       help="nb.clust, the number of clusters to consider in the hierarchical clustering. (default : -1, let HCPC to optimize the number)" />
				<param name="HCPC_metric"  type="select" label="Dissimilarity metric" help="Metric to be used for calculating dissimilarities between observations, available 'euclidian' or 'manhattan'? " > 
					<option value="euclidian" selected="true">euclidian</option>
					<option value="manhattan">manhattan</option>
				</param>
			    <param name="HCPC_method"  type="select" label="Clustering method" help="Clustering method between 'ward', 'average', 'single', 'complete', 'weighted' " > 
					<option value="ward" selected="true">ward</option>
					<option value="average">average</option>
					<option value="single">single</option>
					<option value="complete">complete</option>
					<option value="weighted">weighted</option>
				</param>
				<param name="HCPC_consol"  type="select" label="k-means consolidation" help="If TRUE, a k-means consolidation is performed" > 
					<option value="TRUE" selected="true">Yes</option>
					<option value="FALSE">False</option>
				</param>
				<param name="HCPC_itermax" value="10" type="integer" label="Maximum number of iterations for consolidation"
                       help=" (default=10)" />
                <param name="HCPC_min" value="3" type="integer" label="min number of clusters"
                       help=" The least possible number of clusters suggested (default=3)" />
                <param name="HCPC_max" value="-1" type="text" label="max number of clusters"
                       help=" The higher possible number of clusters suggested, by default the minimum between 10 and the number of individuals divided by 2. (default=-1)" />
				<param name="HCPC_clusterCA"  type="select" label="clusterCA, Clustering against rows or columns" help="default(rows)" > 
					<option value="rows" selected="true">Rows</option>
					<option value="cols">Columns</option>
				</param>
				 <param name="HCPC_kk" value="-1" type="text" label="kk, Number of clusters used in a Kmeans preprocessing "
                       help="No k-means consolidation is done if a kk value is provided (default=-1)" />
                <param label="Return HCPC clustering table" name="res_clustering" type="select">
                    <option value="no" selected="True">No</option>
                    <option value="yes">Yes</option>
                </param>
            </when>

    <outputs>
        <data name="pdf_out" format="pdf" label="${visualisation.visu_choice} of ${on_string}" />
        <data name="table_coordinates" format="tabular" label="Scatter plot coordinates from ${visualisation.visu_choice} of ${on_string}" >
            <filter>coord == 'yes'</filter>
        </data>
        <data name="mutual_info" format="txt" label="External validation of clustering from ${visualisation.visu_choice} of ${on_string}" >
            <filter>visualisation['visu_choice'] == 'HCPC' and factor_condition['factor_choice'] == 'Yes'</filter>
        </data>
        <data name="HCPC_clust" format="tabular" label="Clustering table from ${visualisation.visu_choice} of ${on_string}" >
            <filter>visualisation['visu_choice'] == 'HCPC' and visualisation['res_clustering'] == 'yes'</filter>
        </data>
    </outputs>
    <tests>
        <!-- test PCA -->
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />
            <param name="visu_choice" value="PCA" />

            <param name="labels" value="yes" />
            <param name="visu_choice" value="HCPC" />
            <param name="HCPC_npc" value="5"/>
            <param name="HCPC_ncluster" value="-1"/>
            <output name="pdf_out" file="hcpc.labels.pdf" compare="sim_size" ftype="pdf"/>
        </test>
        <!-- test factor contrasting on HCPC -->
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="no" />

            <param name="HCPC_ncluster" value="-1"/>
            <param name="res_clustering" value="yes"/>
            <param name="factor_choice" value="Yes" />
            <param name="factor" value="factor.tsv" ftype="txt"/>
            <output name="pdf_out" file="hcpc.nolabels.factor.pdf" compare="sim_size" ftype="pdf"/>
            <output name="mutual_info" file="hcpc.factor.extval.txt" ftype="txt"/>
            <output name="HCPC_clust" file="hcpc.clusters.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="no" />
            <param name="HCPC_npc" value="5"/>
            <param name="HCPC_ncluster" value="-1"/>
            <param name="visu_choice" value="HCPC" />
            <output name="pdf_out" file="hcpc.nolabels.pdf" compare="sim_size" ftype="pdf"/>
        </test>
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />
            <param name="visu_choice" value="HCPC" />

            <param name="HCPC_method" value="average"/>
            <param name="HCPC_metric" value="manhattan"/>
            <param name="HCPC_npc" value="4" />
            <output name="pdf_out" file="hcpc-2.labels.pdf" ftype="pdf"/>
            <output name="table_coordinates" file="hcpc-2.coord.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />
            <param name="visu_choice" value="HCPC" />
            <param name="coord" value="yes" />
            <param name="HCPC_method" value="single"/>
            <param name="HCPC_metric" value="euclidian"/>
            <param name="HCPC_npc" value="4" />
            <param name="HCPC_clusterCA" value="cols" />
            <output name="pdf_out" file="hcpc-3.labels.pdf" compare="sim_size" ftype="pdf"/>
            <output name="table_coordinates" file="hcpc-3.coord.tab" ftype="tabular"/>
        </test>
        <!-- test t-SNE -->
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />

5:569334568afa

<tool id="high_dimensions_visualisation" name="Generate PCA, tSNE and HCPC" version="0.9.5">
    <description>from highly dimensional expression data</description>
    <requirements>
        <requirement type="package" version="1.6.2=r35h6115d3f_0">r-optparse</requirement>
        <requirement type="package" version="1.42=r35h6115d3f_0">r-factominer</requirement>
        <requirement type="package" version="1.0.5">r-factoextra</requirement>
        <requirement type="package" version="0.15=r351he1b5a44_0">r-rtsne</requirement>
        <requirement type="package" version="0.4.7=r351h6115d3f_0">r-ggfortify</requirement>
        <requirement type="package" version="1.1.9=r351h0357c0b_0">r-clusterr</requirement>
        <!--<requirement type="package" version="1.11.6=r351hc070d10_0">r-data.table</requirement>-->
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[ 

                --HCPC_itermax '$visualisation.HCPC_itermax'
                --HCPC_min '$visualisation.HCPC_min'
                --HCPC_max '$visualisation.HCPC_max'
                --HCPC_clusterCA '$visualisation.HCPC_clusterCA'
                --HCPC_kk '$visualisation.HCPC_kk'
                --HCPC_cluster_description '$HCPC_cluster_description'
                #if $visualisation.res_clustering == "yes":
                    --HCPC_clust '$HCPC_clust'
                #end if 
            #end if
            

                --PCA_x_axis '$visualisation.PCA_x_axis'
                --PCA_y_axis '$visualisation.PCA_y_axis'
            #end if
            
            #if $visualisation.visu_choice == "HCPC" and $factor_condition.factor_choice == "Yes":
                --HCPC_mutual_info '$HCPC_mutual_info'
            #end if            

            --pdf_out '$pdf_out'
            
]]></command>

            </when>
            <when value="HCPC">
                <param name="HCPC_npc" value="5" type="integer" label="Number of principal components to keep"
                       help="The number of dimensions which are kept for HCPC analysis (default=5)" />
                <param name="HCPC_ncluster" value="-1" type="integer" label="Number of clusters in Hierar. Clustering"
                       help="nb.clust - an integer. If 0, the tree is cut at the level the user clicks on (not working in Galaxy). If -1, the tree is
                             automatically cut at the suggested level (see details). If a (positive) integer, the tree is cut with nb.cluters clusters." />
				<param name="HCPC_metric"  type="select" label="Dissimilarity metric" help="Metric to be used for calculating dissimilarities between observations, can be 'euclidean' or 'manhattan' " > 
					<option value="euclidean" selected="true">euclidean</option>
					<option value="manhattan">manhattan</option>
				</param>
			    <param name="HCPC_method"  type="select" label="Clustering method" help="character string defining the clustering method.
			           The four methods implemented are 'average' ([unweighted pair-]group [arithMetic] average method, aka ‘UPGMA’),
			           'single' (single linkage), 'complete' (complete linkage), and 'ward' (Ward's method).
			           The default with this Galaxy tool is is 'ward'." > 
					<option value="ward" selected="true">ward</option>
					<option value="average">average</option>
					<option value="single">single</option>
					<option value="complete">complete</option>
				</param>
				<param name="HCPC_consol"  type="select" label="k-means consolidation" help="a boolean. If TRUE, a k-means consolidation is performed
				       (consolidation cannot be performed if kk is used and equals a number)." > 
					<option value="TRUE" selected="true">Yes</option>
					<option value="FALSE">False</option>
				</param>
				<param name="HCPC_itermax" value="10" type="integer" label="Maximum number of iterations for consolidation"
                       help="An integer. The maximum number of iterations for the consolidation. (default=10)" />
                <param name="HCPC_min" value="3" type="integer" label="min number of clusters"
                       help="an integer. The least possible number of clusters suggested. (default=3)" />
                <param name="HCPC_max" value="-1" type="text" label="max number of clusters"
                       help="The higher possible number of clusters suggested, by default the minimum between 10 and the number of individuals divided by 2. (default=-1)" />
				<param name="HCPC_clusterCA"  type="select" label="cluster.CA, Clustering against rows or columns"
				       help="A string equals to 'rows' or 'columns' for the clustering of Correspondence Analysis results.default(rows)"> 
					<option value="rows" selected="true">Rows</option>
					<option value="cols">Columns</option>
				</param>
				 <param name="HCPC_kk" value="Inf" type="text" label="kk, Number of clusters used in a Kmeans preprocessing "
                       help="An integer corresponding to the number of clusters used in a Kmeans preprocessing before the
                             hierarchical clustering; the top of the hierarchical tree is then constructed from this partition.
                             This is very useful if the number of individuals is high. Note that consolidation cannot be performed
                             if kk is different from Inf and some graphics are not drawn. Inf is used by default and no preprocessing
                             is done, all the graphical outputs are then given." />
                <param label="Return HCPC clustering table" name="res_clustering" type="select">
                    <option value="no" selected="True">No</option>
                    <option value="yes">Yes</option>
                </param>
            </when>

    <outputs>
        <data name="pdf_out" format="pdf" label="${visualisation.visu_choice} of ${on_string}" />
        <data name="table_coordinates" format="tabular" label="Scatter plot coordinates from ${visualisation.visu_choice} of ${on_string}" >
            <filter>coord == 'yes'</filter>
        </data>
        <data name="HCPC_mutual_info" format="txt" label="External validation of clustering from ${visualisation.visu_choice} of ${on_string}" >
            <filter>visualisation['visu_choice'] == 'HCPC' and factor_condition['factor_choice'] == 'Yes'</filter>
        </data>
        <data name="HCPC_clust" format="tabular" label="Clustering table from ${visualisation.visu_choice} of ${on_string}" >
            <filter>visualisation['visu_choice'] == 'HCPC' and visualisation['res_clustering'] == 'yes'</filter>
        </data>
        <data name="HCPC_cluster_description" format="tabular" label="Cluster information from ${visualisation.visu_choice}" >
            <filter>visualisation['visu_choice'] == 'HCPC' </filter>
        </data>
    </outputs>
    <tests>
        <!-- test first (for developpers) -->
        <!-- test PCA -->
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />
            <param name="visu_choice" value="PCA" />

            <param name="labels" value="yes" />
            <param name="visu_choice" value="HCPC" />
            <param name="HCPC_npc" value="5"/>
            <param name="HCPC_ncluster" value="-1"/>
            <output name="pdf_out" file="hcpc.labels.pdf" compare="sim_size" ftype="pdf"/>
            <output name="HCPC_cluster_description" file="hcpc.cluster_description.1.tab" ftype="tabular"/>
        </test>
        <!-- test factor contrasting on HCPC -->
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="no" />

            <param name="HCPC_ncluster" value="-1"/>
            <param name="res_clustering" value="yes"/>
            <param name="factor_choice" value="Yes" />
            <param name="factor" value="factor.tsv" ftype="txt"/>
            <output name="pdf_out" file="hcpc.nolabels.factor.pdf" compare="sim_size" ftype="pdf"/>
            <output name="HCPC_mutual_info" file="hcpc.factor.extval.txt" ftype="txt"/>
            <output name="HCPC_clust" file="hcpc.clusters.tab" ftype="tabular"/>
            <output name="HCPC_cluster_description" file="hcpc.cluster_description.1.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="no" />
            <param name="HCPC_npc" value="5"/>
            <param name="HCPC_ncluster" value="-1"/>
            <param name="visu_choice" value="HCPC" />
            <output name="pdf_out" file="hcpc.nolabels.pdf" compare="sim_size" ftype="pdf"/>
            <output name="HCPC_cluster_description" file="hcpc.cluster_description.1.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />
            <param name="visu_choice" value="HCPC" />

            <param name="HCPC_method" value="average"/>
            <param name="HCPC_metric" value="manhattan"/>
            <param name="HCPC_npc" value="4" />
            <output name="pdf_out" file="hcpc-2.labels.pdf" ftype="pdf"/>
            <output name="table_coordinates" file="hcpc-2.coord.tab" ftype="tabular"/>
            <output name="HCPC_cluster_description" file="hcpc.cluster_description.4.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />
            <param name="visu_choice" value="HCPC" />
            <param name="coord" value="yes" />
            <param name="HCPC_method" value="single"/>
            <param name="HCPC_metric" value="euclidean"/>
            <param name="HCPC_npc" value="4" />
            <param name="HCPC_clusterCA" value="cols" />
            <output name="pdf_out" file="hcpc-3.labels.pdf" compare="sim_size" ftype="pdf"/>
            <output name="table_coordinates" file="hcpc-3.coord.tab" ftype="tabular"/>
            <output name="HCPC_cluster_description" file="hcpc.cluster_description.5.tab" ftype="tabular"/>
        </test>
        <!-- test t-SNE -->
        <test>
            <param name="input" value="cpm_input.tsv" ftype="txt"/>
            <param name="labels" value="yes" />