annotate featurecounts.xml @ 14:85aaf50ad9dc draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/featurecounts commit 650fa1433cf8fbc8689ed35a4d0340fc7a130aca

<tool id="featurecounts" name="featureCounts" version="1.6.0.6" 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}

            -s  $strand_specificity
            -t '$extended_parameters.gff_feature_type'
            -g '$extended_parameters.gff_feature_attribute'
                $extended_parameters.summarization_level
                $extended_parameters.contribute_to_multiple_features
                $extended_parameters.multimapping_enabled.multimapping_counts

                #if str($extended_parameters.multimapping_enabled.multimapping_counts) == " -M":
                    $extended_parameters.multimapping_enabled.fraction
                #end if

                $extended_parameters.exon_exon_junction_read_counting_enabled.count_exon_exon_junction_reads
                #if str($extended_parameters.exon_exon_junction_read_counting_enabled.count_exon_exon_junction_reads) == "-J":
                    #if $extended_parameters.exon_exon_junction_read_counting_enabled.genome:
                        -G '$extended_parameters.exon_exon_junction_read_counting_enabled.genome'
                    #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":
                    --readExtension5 $extended_parameters.read_extension_5p
                #end if

                #if str($extended_parameters.read_extension_3p) != "0":
                    --readExtension3 $extended_parameters.read_extension_3p
                #end if

                $pe_parameters.fragment_counting_enabled.fragment_counting
                #if str($pe_parameters.fragment_counting_enabled.fragment_counting) == " -p":
                    $pe_parameters.fragment_counting_enabled.check_distance_enabled.check_distance
                    #if str($pe_parameters.fragment_counting_enabled.check_distance_enabled.check_distance) == " -P":
                        -d $pe_parameters.fragment_counting_enabled.check_distance_enabled.minimum_fragment_length
                        -D $pe_parameters.fragment_counting_enabled.check_distance_enabled.maximum_fragment_length
                    #end if
                #end if

                $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"
               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. Unless you are using a Gene annotation file from the History, these files must have the database/genome attribute already specified e.g. hg38, not the default: ?" >
        </param>

        <param name="strand_specificity"
               type="select"
               label="Specify strand information"
               argument="-s"
               help="Indicate if the data is stranded and if strand-specific read counting should be performed. Strand setting must be the same as the strand settings used to produce the mapped BAM input(s)">
            <option value="0" selected="true">Unstranded</option>
            <option value="1">Stranded (Forward)</option>
            <option value="2">Stranded (Reverse)</option>
        </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">
                </param>
            </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">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"
               type="boolean"
               truevalue="true"
               falsevalue="false"
               checked="false"
               label="Create gene-length file"
               help="Creates a tabular file that contains the effective (nucleotides used for counting reads) length of the feature; might be useful for estimating FPKM/RPKM" />


        <section name="pe_parameters" title="Options for paired-end reads">
            <conditional name="fragment_counting_enabled">

                <param name="fragment_counting"
                       type="select"
                       argument="-p"
                       checked="true"
                       label="Count fragments instead of reads"
                       help="If specified, fragments (or templates) will be counted instead of reads.">
                    <option value="" selected="true">Disabled; all reads/mates will be counted individually</option>
                    <option value=" -p">Enabled; fragments (or templates) will be counted instead of reads</option>
                </param>

                <when value=" -p">
                    <conditional name="check_distance_enabled">
                        <param name="check_distance"
                            type="boolean"
                            truevalue=" -P"
                            falsevalue=""
                            argument="-P"
                            label="Check paired-end distance"
                            help="If specified, paired-end distance will be checked when assigning fragments to meta-features or features. This option is only applicable when -p (Count fragments instead of reads) is specified. The distance thresholds should be specified using -d and -D (minimum and maximum fragment/template length) options." />
                        <when value=" -P">
                            <param name="minimum_fragment_length"
                                   type="integer"
                                   value="50"
                                   argument="-d"
                                   label="Minimum fragment/template length." />
                            <param name="maximum_fragment_length"
                                   type="integer"
                                   value="600"
                                   argument="-D"
                                   label="Maximum fragment/template length." />
                        </when>
                        <when value="" />
                    </conditional>
                </when>
                <when value="" />
            </conditional>

            <param name="only_both_ends"
                   type="boolean"
                   truevalue=" -B"
                   falsevalue=""
                   argument="-B"
                   label="Only allow fragments with both reads aligned"
                   help="If specified, only fragments that have both ends successfully aligned will be considered for summarization. This option is only applicable for paired-end reads." />

            <param name="exclude_chimerics"
                type="boolean"
                truevalue=" -C"
                falsevalue=""
                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"
                label="GFF feature type filter"
                help="Specify the feature type. Only rows which have the matched matched feature type in the provided GTF annotation file will be included for read counting. `exon' by default." />

            <param name="gff_feature_attribute"
                type="text"
                value="gene_id"
                argument="-g"
                label="GFF gene identifier"
                help="Specify the attribute type used to group features (eg. exons) into meta-features (eg. genes), when GTF annotation is provided. `gene_id' by default. This attribute type is usually the gene identifier. This argument is useful for the meta-feature level summarization." />

            <param name="summarization_level"
                type="boolean"
                truevalue=" -f"
                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"
                help="If specified, reads (or fragments if -p is specified) will be allowed to be assigned to more than one matched meta-feature (or matched feature if -f is specified)" />

            <conditional name="multimapping_enabled">
                <param name="multimapping_counts"
                       type="select"
                       argument="-M"
                       label="Count multi-mapping reads/fragments"
                       help="If specified, multi-mapping reads/fragments will be counted (ie. a multi-mapping read will be counted up to N times if it has N reported mapping locations). The program uses the `NH' tag to find multi-mapping reads.">
                    <option value="" selected="true">Disabled; multi-mapping reads are excluded (default)</option>
                    <option value=" -M">Enabled; multi-mapping reads are included</option>
                </param>
                <when value=" -M">
                    <param name="fraction"
                           type="boolean"
                           truevalue="--fraction"
                           falsevalue=""
                           argument="--fraction"
                           label="Assign fractions to multimapping reads"
                           help="If specified, a fractional count 1/n will be generated for each multi-mapping read, where n is the number of alignments (indica- ted by 'NH' tag) reported for the read. This option must be used together with the '-M' option." />
                </when>
                <when value="" />
            </conditional>

            <param name="mapping_quality"
                   type="integer"
                   value="12"
                   argument="-Q"
                   label="Minimum mapping quality per read"
                   help="The minimum mapping quality score a read must satisfy in order to be counted. For paired-end reads, at least one end should satisfy this criteria. 12 by default." />

            <conditional name="exon_exon_junction_read_counting_enabled">
                <param name="count_exon_exon_junction_reads" argument="-J" type="boolean" truevalue="-J" falsevalue=""
                       label="Exon-exon junctions"
                       help="If specified, reads supporting each exon-exon junction will be counted" />
                <when value="-J">
                    <param name="genome" argument="-G" type="data" format="fasta" optional="true"
                           label="Reference sequence file"
                           help="The FASTA-format file that contains the reference sequences used in read mapping can be used to improve read counting for junctions" />
                </when>
                <when value="" />
            </conditional>

            <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"
                   label="Largest overlap"
                   help="If specified, reads (or fragments) will be assigned to the target that has the largest number of overlapping bases" />

            <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"
                   label="Read 5' extension"
                   help="Reads are extended upstream by ... bases from their 5' end" />

            <param name="read_extension_3p"
                   type="integer"
                   value="0"
                   argument="--readExtension3"
                   label="Read 3' extension"
                   help="Reads are extended upstream by ... bases from their 3' end" />

            <param name="read_reduction"
                   type="select"
                   label="Reduce read to single position"
                   argument="--read2pos"
                   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"
                   label="Ignore unspliced alignments"
                   help="If specified, only split alignments (CIGAR strings containing the letter `N') will be counted. All the other alignments will be ignored. An example of split alignments are exon-spanning reads in RNA-seq data." />
        </section>
    </inputs>
    <outputs>
        <data format="tabular"
              name="output_medium"
              label="${tool.name} on ${on_string}">
            <filter>format == "tabdel_medium"</filter>
            <actions>
                <action name="column_names" type="metadata" default="Geneid,${alignment.element_identifier},Length" />
            </actions>
        </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>

        <data format="tabular"
              name="output_full"
              label="${tool.name} on ${on_string}: count table">
            <filter>format == "tabdel_full"</filter>
            <actions>
                <action name="column_names" type="metadata" default="Geneid,Chr,Start,End,Strand,Length,${alignment.element_identifier}" />
            </actions>
        </data>

        <data format="tabular"
              name="output_summary"
              label="${tool.name} on ${on_string}: summary">
            <actions>
                <action name="column_names" type="metadata" default="Status,${alignment.element_identifier}" />
            </actions>
        </data>

        <data format="tabular"
              name="output_feature_lengths"
              label="${tool.name} on ${on_string}: feature lengths">
            <filter>include_feature_length_file</filter>
            <actions>
                <action name="column_names" type="metadata" default="Feature,Length" />
            </actions>
        </data>

        <data name="output_jcounts" format="tabular"
              label="${tool.name} on ${on_string}: junction counts">
            <filter>extended_parameters['exon_exon_junction_read_counting_enabled']['count_exon_exon_junction_reads']</filter>
            <actions>
                <action name="column_names" type="metadata"
                    default="PrimaryGene,SecondaryGene,Site1_chr,Site1_location,Site1_strand,Site2_chr,Site2_location,Site2_strand,${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="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>
            <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.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">
            <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
#############

Overview
--------
FeatureCounts is a light-weight read counting program written entirely in the C programming language. It can be used to count both gDNA-seq and RNA-seq reads for genomic features in in SAM/BAM files. FeatureCounts is part of the Subread_ package.

Input formats
-------------
Alignments should be provided in either:

 - SAM format, http://samtools.sourceforge.net/samtools.shtml#5
 - BAM format

Annotations for gene regions should be provided in the GFF/GTF format:

 - http://genome.ucsc.edu/FAQ/FAQformat.html#format3
 - http://www.ensembl.org/info/website/upload/gff.html

Alternatively, the featureCounts built-in annotations for genomes hg38, hg19, mm10 and mm9 can be used through selecting the built-in option above. These annotation files are in simplified annotation format (SAF) as shown below. The GeneID column contains Entrez gene identifiers and each entry (row) is taken as a feature (e.g. an exon).

Example - **Built-in annotation format**:

  ======  ====  =======  =======  ======
  GeneID  Chr   Start    End      Strand
  ======  ====  =======  =======  ======
  497097  chr1  3204563  3207049  -
  497097  chr1  3411783  3411982  -
  497097  chr1  3660633  3661579  -
  ======  ====  =======  =======  ======

These annotation files can be found in the `Subread package`_. You can see the version of Subread used by this wrapper in the tool form above under `Options > Requirements`. To create the files, the 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://subread.sourceforge.net/
.. _`Subread User's Guide`: http://bioinf.wehi.edu.au/subread-package/SubreadUsersGuide.pdf
.. _`Subread package`: https://sourceforge.net/projects/subread/files/
    ]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btt656</citation>
    </citations>
</tool>