comparison fuma.xml @ 9:b21145d59d9c draft default tip

planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/galaxytools-emc/tree/master/tools/fuma commit 7bf6f3629e96bcaaed8770badd11366889efa99c

8:8366a8c82a7a

<?xml version="1.0" encoding="UTF-8"?>
<tool id="fuma" name="FuMa" version="2.11.3-g0">
    <description>match detected fusion genes based on gene names (in particular for RNA-Seq)</description>
    
    <requirements>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package" version="2.11.3">fuma</requirement>
    </requirements>
    
    <version_command>fuma --version 2>&amp;1 | head -n 1</version_command><!-- -V also works, but is not GNU standard -->
    
    <command><![CDATA[
        #import pipes
        
        #set $gene_annotations = []
        #set $samples = []

            
            #set $samples = $samples + [ $sample_name + ":" + str($d['format']) + ":" + str($d['sample'].file_name) ]
            #set $links = $links + [ $sample_name + ":" + str("ga_") + str($i) ]
        #end for
        
        #set $gene_annotations_str = " ".join(gene_annotations)
        #set $samples_str = " ".join(samples)
        #set $links_str = " ".join(links)
        
        fuma 
          -m
            $params.matching_method
          

        #if $params.output_format.value == "list_boolean"
          -f list
        #else
          -f $params.output_format.value
        #end if
          -o $fuma_overview ; 
        
        
        #if $params.output_format.value == "list_boolean"
            fuma-list-to-boolean-list -o tmp.txt $fuma_overview ;
            mv tmp.txt $fuma_overview
        #end if
    ]]></command>
    
    <inputs>
        <repeat name="datasets" title="FusionGene Datasets" min="2">

                <param name="strand_specific_matching" type="hidden" value="--strand-specific-matching" />
                <param name="acceptor_donor_order_specific_matchig" type="hidden" value="--no-acceptor-donor-order-specific-matching" />
                <param name="long_gene_size" type="hidden" value="200000" />
            </when>
            <when value="full">
                <param name="matching_method" type="select" label="Matching method: technique used to match fusion genes based on annotated gene sets" help="Overlap is the most sensitive but also more sensitive for long gene artefacts; subset is the recommended technique and EGM is conservative">
                    <option value="overlap">Overlap</option>
                    <option value="subset" selected="True">Subset</option>
                    <option value="egm">Exact Geneset Matching (EGM)</option>
                </param>
                

                        truevalue="--acceptor-donor-order-specific-matching"
                    falsevalue="--no-acceptor-donor-order-specific-matching"
                    label="Consider fusion genes distinct when the donor and acceptor sites are swapped (A,B) != (B,A)"
                    help="This settings is not recommended when fusion genes detected in DNA-Seq are used" />
                
                <param name="long_gene_size" type="integer" min="0" value="200000" label="Long gene size" help="Gene-name based matching is more sensitive to long genes. This is the gene size used to mark fusion genes spanning a 'long gene' as reported the output. Use 0 to disable this feature (--long-gene-size)" />
                
                <param name="output_format" type="select" label="Output format">
                    <option value="list_boolean" selected="true">List (Boolean)</option>
                    <option value="list">List</option>
                    <option value="summary">Count summary</option>

    <outputs>
        <data format="tabular" name="fuma_overview" label="${tool.name} on ${', '.join([ str(d['sample'].hid)+': '+d['sample'].name for d in $datasets ])}" />
    </outputs>
    
    <tests>
        <test>
            <!-- <repeat name="datasets"> -->
                <param name="datasets_0|sample" value="edgren_chimerascan.txt" ftype="tabular" />
                <param name="datasets_0|format" value="chimerascan" />
                <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            <!-- <repeat name="datasets"> -->
                <param name="datasets_1|sample" value="edgren_defuse.txt" ftype="tabular" />
                <param name="datasets_1|format" value="defuse" />
                <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            <!-- <repeat name="datasets"> -->
                <param name="datasets_2|sample" value="edgren_fusion-map.txt" ftype="tabular" />
                <param name="datasets_2|format" value="fusionmap" />
                <param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            <!-- <repeat name="datasets"> -->
                <param name="datasets_3|sample" value="edgren_true_positives.txt" ftype="tabular" />
                <param name="datasets_3|format" value="fusionmap" />
                <param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            
            <param name="settingsType" value="full" />
            
            <param name="matching_method" value="subset" />
            <param name="strand_specific_matching" value="--strand-specific-matching" />
            <param name="acceptor_donor_order_specific_matchig" value="--acceptor-donor-order-specific-matching" />
            <param name="long_gene_size" value="200000" />
            <param name="output_format" value="list_boolean" />
            
            <output name="fuma_overview" file="edgren_test_01_specifc_matching_output.txt" />
        </test>
        <test>
            <!-- <repeat name="datasets"> -->
                <param name="datasets_0|sample" value="edgren_chimerascan.txt" ftype="tabular" />
                <param name="datasets_0|format" value="chimerascan" />
                <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            <!-- <repeat name="datasets"> -->
                <param name="datasets_1|sample" value="edgren_defuse.txt" ftype="tabular" />
                <param name="datasets_1|format" value="defuse" />
                <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            <!-- <repeat name="datasets"> -->
                <param name="datasets_2|sample" value="edgren_fusion-map.txt" ftype="tabular" />
                <param name="datasets_2|format" value="fusionmap" />
                <param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            <!-- <repeat name="datasets"> -->
                <param name="datasets_3|sample" value="edgren_true_positives.txt" ftype="tabular" />
                <param name="datasets_3|format" value="fusionmap" />
                <param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            <!-- </repeat> -->
            
            <param name="settingsType" value="full" />
            
            <param name="matching_method" value="subset" />
            <param name="strand_specific_matching" value="False" /><!-- Set to false, automatically sets the false value -->
            <param name="acceptor_donor_order_specific_matchig" value="False" /><!-- Set to false, automatically sets the false value -->
            <param name="long_gene_size" value="200000" />
            <param name="output_format" value="list_boolean" />
            
            <output name="fuma_overview" file="edgren_test_02_unspecifc_matching_output.txt" />
        </test>
    </tests>
    
    <help><![CDATA[
============

9:b21145d59d9c

<?xml version="1.0" encoding="UTF-8"?>
<tool id="fuma" name="FuMa" version="3.0.5-g0">
    <description>match detected fusion genes based on gene names (in particular for RNA-Seq)</description>

    <requirements>
        <requirement type="package" version="3.0.5">fuma</requirement>
    </requirements>

    <version_command>fuma --version 2>&amp;1 | head -n 1</version_command><!-- -V also works, but is not GNU standard -->

    <command><![CDATA[
        #import pipes
        
        #set $gene_annotations = []
        #set $samples = []

            
            #set $samples = $samples + [ $sample_name + ":" + str($d['format']) + ":" + str($d['sample'].file_name) ]
            #set $links = $links + [ $sample_name + ":" + str("ga_") + str($i) ]
        #end for
        
        #set $gene_annotations_str = "'"+"' '".join(gene_annotations)+"'"
        #set $samples_str = "'"+"' '".join(samples)+"'"
        #set $links_str = "'"+"' '".join(links)+"'"
        
        fuma 
          -m
            $params.matching_method
          

        #if $params.output_format.value == "list_boolean"
          -f list
        #else
          -f $params.output_format.value
        #end if
          -o '${fuma_overview}'
        
        
        #if $params.output_format.value == "list_boolean"
            && fuma-list-to-boolean-list -o tmp.txt '${fuma_overview}'
            && mv tmp.txt '${fuma_overview}'
        #end if
    ]]></command>
    
    <inputs>
        <repeat name="datasets" title="FusionGene Datasets" min="2">

                <param name="strand_specific_matching" type="hidden" value="--strand-specific-matching" />
                <param name="acceptor_donor_order_specific_matchig" type="hidden" value="--no-acceptor-donor-order-specific-matching" />
                <param name="long_gene_size" type="hidden" value="200000" />
            </when>
            <when value="full">
                <param name="matching_method" type="select" label="Matching method: technique used to match fusion genes based on annotated gene sets"
                       help="Overlap is the most sensitive but also more sensitive for long gene artefacts; subset is the recommended technique and EGM is conservative"
                       argument="-m">
                    <option value="overlap">Overlap</option>
                    <option value="subset" selected="True">Subset</option>
                    <option value="egm">Exact Geneset Matching (EGM)</option>
                </param>
                

                        truevalue="--acceptor-donor-order-specific-matching"
                    falsevalue="--no-acceptor-donor-order-specific-matching"
                    label="Consider fusion genes distinct when the donor and acceptor sites are swapped (A,B) != (B,A)"
                    help="This settings is not recommended when fusion genes detected in DNA-Seq are used" />
                
                <param name="long_gene_size" type="integer" min="0" value="200000" label="Long gene size"
                       help="Gene-name based matching is more sensitive to long genes. This is the gene size used to mark fusion genes spanning a 'long gene' as reported the output. Use 0 to disable this feature"
                       argument="--long-gene-size" />
                
                <param name="output_format" type="select" label="Output format">
                    <option value="list_boolean" selected="true">List (Boolean)</option>
                    <option value="list">List</option>
                    <option value="summary">Count summary</option>

    <outputs>
        <data format="tabular" name="fuma_overview" label="${tool.name} on ${', '.join([ str(d['sample'].hid)+': '+d['sample'].name for d in $datasets ])}" />
    </outputs>
    
    <tests>
        <!-- Large tests, take long
        <test>
            <param name="datasets_0|sample" value="edgren_chimerascan.txt" ftype="tabular" />
            <param name="datasets_0|format" value="chimerascan" />
            <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_1|sample" value="edgren_defuse.txt" ftype="tabular" />
            <param name="datasets_1|format" value="defuse" />
            <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_2|sample" value="edgren_fusion-map.txt" ftype="tabular" />
            <param name="datasets_2|format" value="fusionmap" />
            <param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_3|sample" value="edgren_true_positives.txt" ftype="tabular" />
            <param name="datasets_3|format" value="fusionmap" />
            <param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            
            <param name="settingsType" value="full" />
            
            <param name="matching_method" value="subset" />
            <param name="strand_specific_matching" value=" - - strand-specific-matching" />
            <param name="acceptor_donor_order_specific_matchig" value=" - -acceptor-donor-order-specific-matching" />
            <param name="long_gene_size" value="200000" />
            <param name="output_format" value="list_boolean" />
            
            <output name="fuma_overview" file="edgren_test_01_specifc_matching_output.txt" />
        </test>
        <test>
            <param name="datasets_0|sample" value="edgren_fusion-map.txt" ftype="tabular" />
            <param name="datasets_0|format" value="fusionmap" />
            <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_1|sample" value="edgren_true_positives.txt" ftype="tabular" />
            <param name="datasets_1|format" value="fusionmap" />
            <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_0|sample" value="edgren_chimerascan.txt" ftype="tabular" />
            <param name="datasets_0|format" value="chimerascan" />
            <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            
            <param name="datasets_1|sample" value="edgren_defuse.txt" ftype="tabular" />
            <param name="datasets_1|format" value="defuse" />
            <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            
            <param name="settingsType" value="full" />
            
            <param name="matching_method" value="subset" />
            <param name="strand_specific_matching" value="False" />
            <param name="acceptor_donor_order_specific_matchig" value="False" />
            <param name="long_gene_size" value="200000" />
            <param name="output_format" value="list_boolean" />
            
            <output name="fuma_overview" file="edgren_test_02_unspecifc_matching_output.txt" />
        </test>
        -->
        <test>
            <param name="datasets_0|sample" value="edgren_fusion-map.txt" ftype="tabular" />
            <param name="datasets_0|format" value="fusionmap" />
            <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_1|sample" value="edgren_true_positives.txt" ftype="tabular" />
            <param name="datasets_1|format" value="fusionmap" />
            <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            
            <param name="settingsType" value="full" />
            
            <param name="matching_method" value="subset" />
            <param name="strand_specific_matching" value="--strand-specific-matching" />
            <param name="acceptor_donor_order_specific_matchig" value="--acceptor-donor-order-specific-matching" />
            <param name="long_gene_size" value="200000" />
            <param name="output_format" value="list_boolean" />
            
            <output name="fuma_overview" file="edgren_test_03_specific_matching_output.txt" />
        </test>
        <test>
            <param name="datasets_0|sample" value="edgren_fusion-map.txt" ftype="tabular" />
            <param name="datasets_0|format" value="fusionmap" />
            <param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />

            <param name="datasets_1|sample" value="edgren_true_positives.txt" ftype="tabular" />
            <param name="datasets_1|format" value="fusionmap" />
            <param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
            
            <param name="settingsType" value="full" />
            
            <param name="matching_method" value="subset" />
            <param name="strand_specific_matching" value="False" /><!-- Set to false, automatically sets the false value -->
            <param name="acceptor_donor_order_specific_matchig" value="False" /><!-- Set to false, automatically sets the false value -->
            <param name="long_gene_size" value="200000" />
            <param name="output_format" value="list_boolean" />
            
            <output name="fuma_overview" file="edgren_test_04_unspecific_matching_output.txt" />
        </test>
    </tests>
    
    <help><![CDATA[
============