comparison featurecounts.xml @ 11:e803ca6407c0 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/featurecounts commit 4c095ddb0f2c369d2bf3fc5ca386f6981a2fa0eb

10:46cccc52be5f

<tool id="featurecounts" name="featureCounts" version="1.6.0.2" profile="16.04">
    <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description>
    <requirements>
        <requirement type="package" version="1.6.0">subread</requirement>
    </requirements>

    <version_command>featureCounts -v 2&gt;&amp;1 | grep .</version_command>
    <command detect_errors="exit_code"><![CDATA[
        ## Export fc path for its built-in annotation
        export FC_PATH=\$(command -v featureCounts | sed 's@/bin/featureCounts$@@') &&

        ## Check whether all alignments are from the same type (bam || sam)
        featureCounts

            #if $anno.anno_select=="gtf":
                #if $anno.gtf_source.ref_source=="history":
                    -a '$anno.gtf_source.reference_gene_sets'
                #else:
                    -a '$anno.gtf_source.reference_gene_sets_builtin.fields.path'
                #end if
                -F "GTF"
            #elif $anno.anno_select=="builtin":
                -a \${FC_PATH}/annotation/${anno.genome}_RefSeq_exon.txt
                -F "SAF"
            #end if

            -o "output"
            -T \${GALAXY_SLOTS:-2}

        <param name="alignment"
               type="data"
               multiple="false"
               format="bam,sam"
               label="Alignment file"
               help="The input alignment file(s) where the gene expression has to be counted. The file can have a SAM or BAM format; but ALL files must be in the same format" />
        <conditional name="anno">
            <param name="anno_select" type="select" label="Gene annotation file">
                <option value="builtin">featureCounts built-in</option>
                <option value="gtf">GTF file</option>
            </param>
            <when value="builtin">
                <param name="genome" type="select" label="Select built-in genome" help="Built-in gene annotations for genomes hg38, hg19, mm10 and mm9 are included in featureCounts">
                    <option value="hg38">hg38</option>
                    <option value="hg19">hg19</option>
                    <option value="mm10">mm10</option>
                    <option value="mm9">mm9</option>
                </param>
            </when>
            <when value="gtf">
                <conditional name="gtf_source">
                    <param name="ref_source" type="select" label="Gene annotation file">
                        <option value="cached">locally cached</option>
                        <option value="history">in your history</option>
                    </param>
                    <when value="cached">
                        <param name="reference_gene_sets_builtin" type="select" label="Using locally cached annotation" help="If the annotation file you require is not listed here, please contact the Galaxy administrator">
                            <options from_data_table="gene_sets">
                                <filter type="sort_by" column="1" />
                                <validator type="no_options" message="No annotations are available." />
                            </options>
                        </param>
                    </when>
                    <when value="history">
                        <param name="reference_gene_sets"
                               format="gff,gtf,gff3"
                               type="data"
                               label="Gene annotation file"
                               help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotation file corresponds to the same reference genome as used for the alignment" />
                    </when>
                </conditional>
            </when>
        </conditional>

        <param name="format"
               type="select"

                falsevalue=""
                argument="-f"
                label="On feature level"
                help="If specified, read summarization will be performed at the feature level. By default (-f is not specified), the read summarization is performed at the meta-feature level." />

            <param name ="contribute_to_multiple_features"
                type="boolean"
                truevalue=" -O"
                falsevalue=""
                argument="-O"
                label="Allow read to contribute to multiple features"

            </actions>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" />
            <param name="anno_select" value="gtf"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
            <param name="format" value="tabdel_short_noheader" />
            <param name="include_feature_length_file" value="true"/>
            <param name="ref_source" value="history" />
            <param name="count_exon_exon_junction_reads" value="-J"/>
            <output name="output_short" file="output_1_short.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">

            <output name="output_jcounts" file="output_1_jcounts.tab">
                <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/>
            </output>
        </test>
        <test expect_num_outputs="3">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" />
            <param name="anno_select" value="gtf"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
            <param name="format" value="tabdel_medium" />
            <param name="include_feature_length_file" value="true"/>
            <param name="ref_source" value="history" />
            <output name="output_medium" file="output_1_medium.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam,Length"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
            </output>
        </test>
        <test expect_num_outputs="3">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" />
            <param name="anno_select" value="gtf"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
            <param name="format" value="tabdel_full" />
            <param name="include_feature_length_file" value="true"/>
            <param name="ref_source" value="history" />
            <output name="output_full" file="output_1_full.tab">
                <metadata name="column_names" value="Geneid,Chr,Start,End,Strand,Length,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>

            <output name="output_feature_lengths" file="output_feature_lengths.tab">
                <metadata name="column_names" value="Feature,Length"/>
            </output>
        </test>
        <test expect_num_outputs="4">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" />
            <param name="anno_select" value="gtf"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
            <param name="format" value="tabdel_short" />
            <param name="include_feature_length_file" value="true"/>
            <param name="ref_source" value="history" />
            <param name="count_exon_exon_junction_reads" value="-J"/>
            <output name="output_short" file="output_1_short_with_header.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary_with_header.tab">

            </output>
            <output name="output_jcounts" file="output_1_jcounts_with_header.tab">
                <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/>
            </output>
        </test>
        <!-- Ensure built-in annotation works -->
        <test expect_num_outputs="2">
            <param name="alignment" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" ftype="bam" />
            <param name="anno_select" value="builtin"/>
            <param name="format" value="tabdel_short" />
            <param name="genome" value="hg19" />
            <output name="output_short" file="output_builtin_hg19.tab">
                <metadata name="column_names" value="Geneid,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            </output>
            <output name="output_summary" file="output_summary_builtin_hg19.tab"/>
        </test>
    </tests>

    <help><![CDATA[
featureCounts

11:e803ca6407c0

<tool id="featurecounts" name="featureCounts" version="1.6.0.3" profile="16.04">
    <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description>
    <requirements>
        <requirement type="package" version="1.6.0">subread</requirement>
    </requirements>

    <version_command>featureCounts -v 2&gt;&amp;1 | grep .</version_command>
    <command detect_errors="exit_code"><![CDATA[

        ## Export fc path for its built-in annotation

        export FC_PATH=\$(command -v featureCounts | sed 's@/bin/featureCounts$@@') &&

        ## Check whether all alignments are from the same type (bam || sam)
        featureCounts

            #if $anno.anno_select=="history":
                -a '$anno.reference_gene_sets'
                -F "GTF"
            #elif $anno.anno_select=="cached":
                -a '$anno.reference_gene_sets_builtin.fields.path'
                -F "GTF"
            #elif $anno.anno_select=="builtin":
                -a \${FC_PATH}/annotation/${anno.bgenome}_RefSeq_exon.txt
                -F "SAF"
            #end if

            -o "output"
            -T \${GALAXY_SLOTS:-2}

        <param name="alignment"
               type="data"
               multiple="false"
               format="bam,sam"
               label="Alignment file"
               help="The input alignment file(s) where the gene expression has to be counted. The file can have a SAM or BAM format; but ALL files must be in the same format. These files must have the database/genome attribute already specified e.g. hg38, not the default: ?" >
               <validator type="unspecified_build"/>
        </param>

        <conditional name="anno">
            <param name="anno_select" type="select" label="Gene annotation file">
                <option value="builtin">featureCounts built-in</option>
                <option value="cached" selected="True">locally cached</option>
                <option value="history">in your history</option>
            </param>
            <when value="builtin">
                <param name="bgenome" type="select" label="Select built-in genome" help="Built-in gene annotations for genomes hg38, hg19, mm10 and mm9 are included in featureCounts">
                    <options from_data_table="featurecounts_anno">
                        <filter type="data_meta" key="dbkey" ref="alignment" column="0"/>
                    </options>
                </param>
            </when>
            <when value="cached">
                <param name="reference_gene_sets_builtin" type="select" label="Using locally cached annotation" help="If the annotation file you require is not listed here, please contact the Galaxy administrator">
                    <options from_data_table="gene_sets">
                        <filter type="data_meta" key="dbkey" ref="alignment" column="0"/>
                    </options>
                    <validator type="no_options" message="An annotation file is not available for the build associated with the selected input file"/>
                </param>
            </when>
            <when value="history">
                <param name="reference_gene_sets"
                       format="gff,gtf,gff3"
                       type="data"
                       label="Gene annotation file"
                       help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotation file corresponds to the same reference genome as used for the alignment">
                    <options>
                        <filter type="data_meta" key="dbkey" ref="alignment"/>
                    </options>
                    <validator type="no_options" message="The current history does not include a dataset with the build associated with the selected input file"/>
                </param>
            </when>
        </conditional>

        <param name="format"
               type="select"

                falsevalue=""
                argument="-f"
                label="On feature level"
                help="If specified, read summarization will be performed at the feature level. By default (-f is not specified), the read summarization is performed at the meta-feature level." />

            <param name="contribute_to_multiple_features"
                type="boolean"
                truevalue=" -O"
                falsevalue=""
                argument="-O"
                label="Allow read to contribute to multiple features"

            </actions>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
            <param name="anno_select" value="history"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
            <param name="format" value="tabdel_short_noheader" />
            <param name="include_feature_length_file" value="true"/>
            <param name="count_exon_exon_junction_reads" value="-J"/>
            <output name="output_short" file="output_1_short.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">

            <output name="output_jcounts" file="output_1_jcounts.tab">
                <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/>
            </output>
        </test>
        <test expect_num_outputs="3">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
            <param name="anno_select" value="history"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
            <param name="format" value="tabdel_medium" />
            <param name="include_feature_length_file" value="true"/>
            <output name="output_medium" file="output_1_medium.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam,Length"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
            </output>
        </test>
        <test expect_num_outputs="3">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
            <param name="anno_select" value="history"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
            <param name="format" value="tabdel_full" />
            <param name="include_feature_length_file" value="true"/>
            <output name="output_full" file="output_1_full.tab">
                <metadata name="column_names" value="Geneid,Chr,Start,End,Strand,Length,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>

            <output name="output_feature_lengths" file="output_feature_lengths.tab">
                <metadata name="column_names" value="Feature,Length"/>
            </output>
        </test>
        <test expect_num_outputs="4">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
            <param name="anno_select" value="history"/>
            <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" dbkey="hg38" />
            <param name="format" value="tabdel_short" />
            <param name="include_feature_length_file" value="true"/>
            <param name="count_exon_exon_junction_reads" value="-J"/>
            <output name="output_short" file="output_1_short_with_header.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary_with_header.tab">

            </output>
            <output name="output_jcounts" file="output_1_jcounts_with_header.tab">
                <metadata name="column_names" value="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,featureCounts_input1.bam"/>
            </output>
        </test>
        <!-- Ensure featureCounts built-in annotation works -->
        <test expect_num_outputs="2">
            <param name="alignment" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" ftype="bam" dbkey="hg19" />
            <param name="anno_select" value="builtin"/>
            <param name="format" value="tabdel_short" />
            <output name="output_short" file="output_builtin_hg19.tab">
                <metadata name="column_names" value="Geneid,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            </output>
            <output name="output_summary" file="output_summary_builtin_hg19.tab"/>
        </test>
        <!-- Ensure cached GTFs work -->
        <test expect_num_outputs="3">
            <param name="alignment" value="featureCounts_input1.bam" ftype="bam" dbkey="hg38" />
            <param name="anno_select" value="cached"/>
            <param name="format" value="tabdel_medium" />
            <param name="include_feature_length_file" value="true"/>
            <output name="output_medium" file="output_1_medium.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam,Length"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
            </output>
        </test>
    </tests>

    <help><![CDATA[
featureCounts