comparison featurecounts.xml @ 13:386220cf6877 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/featurecounts commit 2bd06c2b43c295fb4cf172c4f156fed5475855a4

12:b714f4620411

<tool id="featurecounts" name="featureCounts" version="1.6.0.4" 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>

                $pe_parameters.only_both_ends
                $pe_parameters.exclude_chimerics

        '${alignment}'

        ## Removal of comment
        && grep -v "^#" "output"

        #if $format.value != "tabdel_short":
            ## and remove column-header line
            | tail -n+2
        #else
            ## update header
            | sed --expression='s|${alignment}|${alignment.element_identifier}|g'
        #end if
        > body.txt
        ## Set the right columns for the tabular formats
        #if $format.value == "tabdel_medium":
            && cut -f 1,7 body.txt > expression_matrix.txt

            ## Paste doesn't allow a non ordered list of columns: -f 1,7,8,6 will only return columns 1,7 and 8
            ## Thus the gene length column (last column) has to be added separately
            && cut -f 6 body.txt > gene_lengths.txt
            && paste expression_matrix.txt gene_lengths.txt > expression_matrix.txt.bak
            && mv -f expression_matrix.txt.bak '${output_medium}'
        #elif $format.value == "tabdel_short" or $format.value == "tabdel_short_noheader":
            && cut -f 1,7 body.txt > '${output_short}'
        #else:
            && cp body.txt '${output_full}'
        #end if

        #if str($include_feature_length_file) == "true":
            && cut -f 1,6 body.txt > '${output_feature_lengths}'
        #end if

        #if str($extended_parameters.exon_exon_junction_read_counting_enabled.count_exon_exon_junction_reads) == "-J":
            #if $format.value != "tabdel_short":
              && tail -n+2 'output.jcounts' > '${output_jcounts}'
            #else:

              && sed --expression='s|${alignment}|${alignment.element_identifier}|g' 'output.jcounts' > '${output_jcounts}'
            #end if
        #end if

        #if $format.value != "tabdel_short":
            && tail -n+2 'output.summary' > '${output_summary}'
        #else:
            && sed --expression='s|${alignment}|${alignment.element_identifier}|g' 'output.summary' > '${output_summary}'
        #end if
    ]]></command>
    <inputs>
        <param name="alignment"
               type="data"
               multiple="false"

        <param name="format"
               type="select"
               label="Output format"
               help="The output format will be tabular, select the preferred columns here">
            <option value="tabdel_short_noheader" selected="true">Gene-ID "\t" read-count (DESeq2 IUC wrapper compatible)</option>
            <option value="tabdel_short">Gene-ID "\t" read-count (MultiQC/edgeR/limma-voom compatible, includes header in output)</option>
            <option value="tabdel_medium">Gene-ID "\t" read-count "\t" gene-length</option>
            <option value="tabdel_full">featureCounts 1.4.0+ default (includes regions provided by the GTF file)</option>
        </param>

        <param name="include_feature_length_file"

        </data>

        <data format="tabular"
              name="output_short"
              label="${tool.name} on ${on_string}">
            <filter>format == "tabdel_short_noheader" or format == "tabdel_short"</filter>
            <actions>
                <action name="column_names" type="metadata" default="Geneid,${alignment.element_identifier}" />
            </actions>
        </data>

                    default="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,${alignment.element_identifier}" />
            </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">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
            </output>
            <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="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">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
            </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">

Alternatively, the featureCounts built-in annotations for genomes hg38, hg19, mm10 and mm9 can be used through selecting the built-in option above. These annotations were downloaded from NCBI RefSeq database and then adapted by merging overlapping exons from the same gene to form a set of disjoint exons for each gene. Genes with the same Entrez gene identifiers were also merged into one gene. See the Subread_ User's Guide for more information.

Output format
-------------
FeatureCounts produces a table containing counted reads, per gene, per row. Optionally the last column can be set to be the effective gene-length. These tables are compatible with the DESeq2 Galaxy wrapper by IUC. Column names are added as metadata object.

.. _Subread: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btt656</citation>

13:386220cf6877

<tool id="featurecounts" name="featureCounts" version="1.6.0.5" 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>

                $pe_parameters.only_both_ends
                $pe_parameters.exclude_chimerics

        '${alignment}'

        ## Remove comment and add sample name to header
        && grep -v "^#" "output" 
        | sed -e 's|${alignment}|${alignment.element_identifier}|g'
        > body.txt
        ## Set the right columns for the tabular formats
        #if $format.value == "tabdel_medium":
            && cut -f 1,7 body.txt > expression_matrix.txt

            ## Paste doesn't allow a non ordered list of columns: -f 1,7,8,6 will only return columns 1,7 and 8
            ## Thus the gene length column (last column) has to be added separately
            && cut -f 6 body.txt > gene_lengths.txt
            && paste expression_matrix.txt gene_lengths.txt > expression_matrix.txt.bak
            && mv -f expression_matrix.txt.bak '${output_medium}'
        #elif $format.value == "tabdel_short":
            && cut -f 1,7 body.txt > '${output_short}'
        #else:
            && cp body.txt '${output_full}'
        #end if

        #if str($include_feature_length_file) == "true":
            && cut -f 1,6 body.txt > '${output_feature_lengths}'
        #end if

        #if str($extended_parameters.exon_exon_junction_read_counting_enabled.count_exon_exon_junction_reads) == "-J":
            && sed -e 's|${alignment}|${alignment.element_identifier}|g' 'output.jcounts' > '${output_jcounts}'
        #end if

        && sed -e 's|${alignment}|${alignment.element_identifier}|g' 'output.summary' > '${output_summary}'
    ]]></command>
    <inputs>
        <param name="alignment"
               type="data"
               multiple="false"

        <param name="format"
               type="select"
               label="Output format"
               help="The output format will be tabular, select the preferred columns here">
            <option value="tabdel_short">Gene-ID "\t" read-count (MultiQC/DESeq2/edgeR/limma-voom compatible)</option>
            <option value="tabdel_medium">Gene-ID "\t" read-count "\t" gene-length</option>
            <option value="tabdel_full">featureCounts 1.4.0+ default (includes regions provided by the GTF file)</option>
        </param>

        <param name="include_feature_length_file"

        </data>

        <data format="tabular"
              name="output_short"
              label="${tool.name} on ${on_string}">
            <filter>format == "tabdel_short"</filter>
            <actions>
                <action name="column_names" type="metadata" default="Geneid,${alignment.element_identifier}" />
            </actions>
        </data>

                    default="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,${alignment.element_identifier}" />
            </actions>
        </data>
    </outputs>
    <tests>
        <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="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.tab">
                <metadata name="column_names" value="Geneid,featureCounts_input1.bam"/>
            </output>
            <output name="output_summary" file="output_1_summary.tab">
                <metadata name="column_names" value="Status,featureCounts_input1.bam"/>
            </output>
            <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>
        <!-- Ensure featureCounts built-in annotation works -->
        <test expect_num_outputs="2">

Alternatively, the featureCounts built-in annotations for genomes hg38, hg19, mm10 and mm9 can be used through selecting the built-in option above. These annotations were downloaded from NCBI RefSeq database and then adapted by merging overlapping exons from the same gene to form a set of disjoint exons for each gene. Genes with the same Entrez gene identifiers were also merged into one gene. See the Subread_ User's Guide for more information.

Output format
-------------
FeatureCounts produces a table containing counted reads, per gene, per row. Optionally the last column can be set to be the effective gene-length. These tables are compatible with the DESeq2, edgeR and limma-voom Galaxy wrappers by IUC.

.. _Subread: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btt656</citation>