comparison featurecounts.xml @ 8:2a8bb8223a45 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/featurecounts commit 2228563ac1c2bb236c8ac83d08d2b86e21a39e41

7:3ce1c701b0df

<tool id="featurecounts" name="featureCounts" version="1.5.3" profile="16.04">
    <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description>
    <requirements>
        <requirement type="package" version="1.5.3">subread</requirement>
    </requirements>

    <version_command>featureCounts -v 2&gt;&amp;1 | grep .</version_command>
    <command><![CDATA[
        ## Check whether all alignments are from the same type (bam || sam)

                    #end if
                #end if

                $extended_parameters.long_reads

            -Q  $extended_parameters.mapping_quality
                $extended_parameters.largest_overlap
            --minOverlap  $extended_parameters.min_overlap
                $extended_parameters.read_reduction
                $extended_parameters.primary
                $extended_parameters.ignore_dup

                #if str($extended_parameters.read_extension_5p) != "0"

        #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

               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="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>

                       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>
        
        <param name="format"
               type="select"
               label="Output format"
               help="The output format will be tabular, select the preferred columns here">
            <option value="tabdel_short" selected="true">Gene-ID "\t" read-count (DESeq2 IUC wrapper 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"
               type="boolean"
               truevalue="true"
               falsevalue="false"
               checked="false"

                        <when value="" />
                    </conditional>
                </when>
                <when value="" />
            </conditional>
            
            <param name="only_both_ends"
                   type="boolean"
                   truevalue=" -B"
                   falsevalue=""
                   argument="-B"

                argument="-C"
                checked="true"
                label="Exclude chimeric fragments"
                help="If specified, the chimeric fragments (those fragments that have their two ends aligned to different chromosomes) will NOT be included for summarization. This option is only applicable for paired-end read data." />
        </section>
        
        <section name="extended_parameters" title="Advanced options">
            <param name="gff_feature_type"
                type="text"
                value="exon"
                argument="-t"

            <param name="long_reads" argument="-L" type="boolean" truevalue="-L" falsevalue=""
                   label="Long reads"
                   help="If specified, long reads such as Nanopore and PacBio reads will be counted. Long read counting can only run in one thread and only reads (not read-pairs) can be counted." />

            <param name="largest_overlap"
                   type="boolean"
                   truevalue=" --largestOverlap"
                   falsevalue=""
                   argument="--largestOverlap"

            <param name="min_overlap"
                   type="integer"
                   value="1"
                   argument="--minOverlap"
                   label="Minimum overlap"
                   help="Specify the minimum required number of overlapping bases between a read (or a fragment) and a feature. 1 by default. If a negative value is provided, the read will be extended from both ends." />

            <param name="read_extension_5p"
                   type="integer"
                   value="0"
                   argument="--readExtension5"

                   help="The read is reduced to its 5' most base or 3'most base. Read summarization is then performed based on the single base the the read is reduced to.">
                <option value="" selected="true">Leave the read as it is</option>
                <option value="--read2pos 5">Reduce it to the 5' end</option>
                <option value="--read2pos 3">Reduce it to the 3' end</option>
            </param>
            
            <param name="primary"
                   type="boolean"
                   truevalue=" --primary"
                   falsevalue=""
                   argument="--primary"
                   label="Only count primary alignments"
                   help="If specified, only primary alignments will be counted. Primary and secondary alignments are identified using bit 0x100 in theFlag field of SAM/BAM files. All primary alignments in a dataset will be counted regardless of whether they are from multi-mapping reads or not ('-M' is ignored)." />
            
            <param name="ignore_dup"
                   type="boolean"
                   truevalue=" --ignoreDup"
                   falsevalue=""
                   argument="--ignoreDup"
                   label="Ignore reads marked as duplicate"
                   help="If specified, reads that were marked as duplicates will be ignored. Bit Ox400 in the FLAG field of a SAM/BAM file is used for identifying duplicate reads. In paired end data, the entire read pair will be ignored if at least one end is found to be a duplicate read." />
            
            <param name="count_split_alignments_only"
                   type="boolean"
                   truevalue=" --countSplitAlignmentsOnly"
                   falsevalue=""
                   argument="--countSplitAlignmentsOnly"

            </output>
            <output name="output_feature_lengths" file="output_feature_lengths.tab">
                <metadata name="column_names" value="Feature,Length"/>
            </output>
        </test>
        
    </tests>
    
    <help><![CDATA[
featureCounts
#############

Overview

8:2a8bb8223a45

<tool id="featurecounts" name="featureCounts" version="1.6.0" 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><![CDATA[
        ## Check whether all alignments are from the same type (bam || sam)

                    #end if
                #end if

                $extended_parameters.long_reads

                $extended_parameters.by_read_group

            -Q  $extended_parameters.mapping_quality
                $extended_parameters.largest_overlap
            --minOverlap  $extended_parameters.min_overlap
            --fracOverlap $extended_parameters.frac_overlap
            --fracOverlapFeature $extended_parameters.frac_overlap_feature
                $extended_parameters.read_reduction
                $extended_parameters.primary
                $extended_parameters.ignore_dup

                #if str($extended_parameters.read_extension_5p) != "0"

        #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

               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="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>

                       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>

        <param name="format"
               type="select"
               label="Output format"
               help="The output format will be tabular, select the preferred columns here">
            <option value="tabdel_short" selected="true">Gene-ID "\t" read-count (DESeq2 IUC wrapper 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"
               type="boolean"
               truevalue="true"
               falsevalue="false"
               checked="false"

                        <when value="" />
                    </conditional>
                </when>
                <when value="" />
            </conditional>

            <param name="only_both_ends"
                   type="boolean"
                   truevalue=" -B"
                   falsevalue=""
                   argument="-B"

                argument="-C"
                checked="true"
                label="Exclude chimeric fragments"
                help="If specified, the chimeric fragments (those fragments that have their two ends aligned to different chromosomes) will NOT be included for summarization. This option is only applicable for paired-end read data." />
        </section>

        <section name="extended_parameters" title="Advanced options">
            <param name="gff_feature_type"
                type="text"
                value="exon"
                argument="-t"

            <param name="long_reads" argument="-L" type="boolean" truevalue="-L" falsevalue=""
                   label="Long reads"
                   help="If specified, long reads such as Nanopore and PacBio reads will be counted. Long read counting can only run in one thread and only reads (not read-pairs) can be counted." />

           <param name="by_read_group" argument="--byReadGroup" type="boolean" truevalue="--byReadGroup" falsevalue=""
                  label="Count reads by read group"
                  help="If specified, reads are counted for each read group separately. The 'RG' tag must be present in the input BAM/SAM alignment files." />


            <param name="largest_overlap"
                   type="boolean"
                   truevalue=" --largestOverlap"
                   falsevalue=""
                   argument="--largestOverlap"

            <param name="min_overlap"
                   type="integer"
                   value="1"
                   argument="--minOverlap"
                   label="Minimum bases of overlap"
                   help="Specify the minimum required number of overlapping bases between a read (or a fragment) and a feature. 1 by default. If a negative value is provided, the read will be extended from both ends." />

           <param name="frac_overlap"
                  type="integer"
                  value="0"
                  min="0"
                  max="1"
                  argument="--fracOverlap"
                  label="Minimum fraction (of read) overlapping a feature"
                  help="Specify the minimum required fraction of overlapping bases between a read (or a fragment) and a feature. Value should be within range [0,1]. 0 by default. Number of overlapping bases is counted from both reads if paired end. Both this option and '--minOverlap' need to be satisfied for read assignment." />

              <param name="frac_overlap_feature"
                     type="integer"
                     value="0"
                     min="0"
                     max="1"
                     argument="--fracOverlapFeature"
                     label="Minimum fraction (of feature) overlapping a read"
                     help="Specify the minimum required fraction of bases included in a feature overlapping bases between a read (or a read-pair). Value should be within range [0,1]. 0 by default." />

            <param name="read_extension_5p"
                   type="integer"
                   value="0"
                   argument="--readExtension5"

                   help="The read is reduced to its 5' most base or 3'most base. Read summarization is then performed based on the single base the the read is reduced to.">
                <option value="" selected="true">Leave the read as it is</option>
                <option value="--read2pos 5">Reduce it to the 5' end</option>
                <option value="--read2pos 3">Reduce it to the 3' end</option>
            </param>

            <param name="primary"
                   type="boolean"
                   truevalue=" --primary"
                   falsevalue=""
                   argument="--primary"
                   label="Only count primary alignments"
                   help="If specified, only primary alignments will be counted. Primary and secondary alignments are identified using bit 0x100 in theFlag field of SAM/BAM files. All primary alignments in a dataset will be counted regardless of whether they are from multi-mapping reads or not ('-M' is ignored)." />

            <param name="ignore_dup"
                   type="boolean"
                   truevalue=" --ignoreDup"
                   falsevalue=""
                   argument="--ignoreDup"
                   label="Ignore reads marked as duplicate"
                   help="If specified, reads that were marked as duplicates will be ignored. Bit Ox400 in the FLAG field of a SAM/BAM file is used for identifying duplicate reads. In paired end data, the entire read pair will be ignored if at least one end is found to be a duplicate read." />

            <param name="count_split_alignments_only"
                   type="boolean"
                   truevalue=" --countSplitAlignmentsOnly"
                   falsevalue=""
                   argument="--countSplitAlignmentsOnly"

            </output>
            <output name="output_feature_lengths" file="output_feature_lengths.tab">
                <metadata name="column_names" value="Feature,Length"/>
            </output>
        </test>

    </tests>

    <help><![CDATA[
featureCounts
#############

Overview