annotate rg_rnaStar.xml @ 5:99b17b74a8cd draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 528ca3b14c2ca9b7ac18a0f9d80a5f4a235707bf

<tool id="rna_star" name="RNA STAR" version="2.5.2b-1" profile="17.01">
    <description>Gapped-read mapper for RNA-seq data</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    
    <stdio>
        <regex match="FATAL error" source="both" level="fatal"/>
        <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/>
        <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/>
        <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/>
    </stdio>

<!--
    important quote (https://groups.google.com/forum/#!topic/rna-star/q4zGzlPgwXY):
    Hi Gary,

    if you generate the genome with GTF file, and do not specify the value for  - -sjdbOverhang, it will be set to the default 100.
    If you want to be able to set arbitrary value of  - -sjdbOverhang on the fly, you have to generate the genome without annotations (GTF) - then you supply both the  - -sjdbOverhang and GTF file at the mapping step.

    Cheers
    Alex
-->
    <command><![CDATA[
    ## Create temporary index for custom reference
    #if str($refGenomeSource.geneSource) == 'history':
        mkdir -p tempstargenomedir &&
        STAR
            --runMode genomeGenerate
            --genomeDir 'tempstargenomedir'
            --genomeFastaFiles '$refGenomeSource.genomeFastaFiles'
            #if $refGenomeSource.sjdbGTFfile:
                --sjdbGTFfile '$refGenomeSource.sjdbGTFfile'
                --sjdbOverhang '$refGenomeSource.sjdbOverhang'
            #end if
            --runThreadN \${GALAXY_SLOTS:-4}
        &&
    #end if

    STAR
        --runThreadN \${GALAXY_SLOTS:-4}
        --genomeLoad NoSharedMemory
        --genomeDir
        #if str($refGenomeSource.geneSource) == 'history':
            'tempstargenomedir'
            #if $refGenomeSource.sjdbGTFfile:
                --sjdbGTFfile '$refGenomeSource.sjdbGTFfile'
                --sjdbOverhang '$refGenomeSource.sjdbOverhang'
            #end if
        #else
            '${refGenomeSource.GTFconditional.genomeDir.fields.path}'
        #end if

        --readFilesIn
        #if str($singlePaired.sPaired) == "paired_collection"
            '$singlePaired.input.forward' '$singlePaired.input.reverse'

            #if $singlePaired.input.forward.is_of_type("fastq.gz", "fastqsanger.gz"):
                @FASTQ_GZ_OPTION@
            #end if
        #else
            '$singlePaired.input1'
            #if str($singlePaired.sPaired) == "paired"
                '$singlePaired.input2'
            #end if

            #if $singlePaired.input1.is_of_type("fastq.gz", "fastqsanger.gz"):
                @FASTQ_GZ_OPTION@
            #end if
        #end if

        --outSAMtype BAM SortedByCoordinate

        ## Handle difference between indices with/without annotations
        #if str($refGenomeSource.geneSource) == 'indexed':
            #if str($refGenomeSource.GTFconditional.GTFselect) == 'without-gtf':
                #if $refGenomeSource.GTFconditional.sjdbGTFfile:
                    --sjdbOverhang '$refGenomeSource.GTFconditional.sjdbOverhang'
                    --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}'
                    #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3':
                        --sjdbGTFtagExonParentTranscript Parent
                    #end if
                #end if
            #end if
        #end if

        #if $quantMode:
            --quantMode GeneCounts
        #end if

        ## Output parameters
        #if str( $output_params.output_select ) == "yes":
            --outSAMattributes $output_params.outSAMattributes
            --outSAMstrandField $output_params.outSAMstrandField
            --outFilterIntronMotifs $output_params.outFilterIntronMotifs
            #if str( $output_params.output_params2.output_select2 ) == "yes":
                --outSAMunmapped $output_params.output_params2.outSAMunmapped
                --outSAMprimaryFlag $output_params.output_params2.outSAMprimaryFlag
                --outSAMmapqUnique "$output_params.output_params2.outSAMmapqUnique"
                --outFilterType $output_params.output_params2.outFilterType
                --outFilterMultimapScoreRange "$output_params.output_params2.outFilterMultimapScoreRange"
                --outFilterMultimapNmax "$output_params.output_params2.outFilterMultimapNmax"
                --outFilterMismatchNmax "$output_params.output_params2.outFilterMismatchNmax"
                --outFilterMismatchNoverLmax "$output_params.output_params2.outFilterMismatchNoverLmax"
                --outFilterMismatchNoverReadLmax "$output_params.output_params2.outFilterMismatchNoverReadLmax"
                --outFilterScoreMin "$output_params.output_params2.outFilterScoreMin"
                --outFilterScoreMinOverLread "$output_params.output_params2.outFilterScoreMinOverLread"
                --outFilterMatchNmin "$output_params.output_params2.outFilterMatchNmin"
                --outFilterMatchNminOverLread "$output_params.output_params2.outFilterMatchNminOverLread"
            #end if
        #end if

        ## Other parameters
        #if str( $params.settingsType ) == "star_fusion":
            ## Preset parameters for STAR-Fusion
            --outReadsUnmapped None
            --chimSegmentMin 12
            --chimJunctionOverhangMin 12
            --alignSJDBoverhangMin 10
            --alignMatesGapMax 200000
            --alignIntronMax 200000

            ## --twopass1readsN 100000000  
            ## --chimSegmentReadGapMax 3              ## not an option in STAR 2.4.0
            ## --alignSJstitchMismatchNmax 5 -1 5 5   ## not an option in STAR 2.4.0

        #elif str( $params.settingsType ) == "full":
            ## Extended parameter options

            ## Seed parameter options
            --seedSearchStartLmax "$params.seed.seedSearchStartLmax"
            --seedSearchStartLmaxOverLread "$params.seed.seedSearchStartLmaxOverLread"
            --seedSearchLmax "$params.seed.seedSearchLmax"
            --seedMultimapNmax "$params.seed.seedMultimapNmax"
            --seedPerReadNmax "$params.seed.seedPerReadNmax"
            --seedPerWindowNmax "$params.seed.seedPerWindowNmax"
            --seedNoneLociPerWindow "$params.seed.seedNoneLociPerWindow"
        
            ## Alignment parameter options
            --alignIntronMin "$params.align.alignIntronMin"
            --alignIntronMax "$params.align.alignIntronMax"
            --alignMatesGapMax "$params.align.alignMatesGapMax"
            --alignSJoverhangMin "$params.align.alignSJoverhangMin"
            --alignSJDBoverhangMin "$params.align.alignSJDBoverhangMin"
            --alignSplicedMateMapLmin "$params.align.alignSplicedMateMapLmin"
            --alignSplicedMateMapLminOverLmate "$params.align.alignSplicedMateMapLminOverLmate"
            --alignWindowsPerReadNmax "$params.align.alignWindowsPerReadNmax"
            --alignTranscriptsPerWindowNmax "$params.align.alignTranscriptsPerWindowNmax"
            --alignTranscriptsPerReadNmax "$params.align.alignTranscriptsPerReadNmax"
            --alignEndsType $params.align.alignEndsType

            ## Chimeric alignment parameter options
            #if str( $params.chim.chim_select ) == "yes":
                --chimSegmentMin "$params.chim.chimSegmentMin"
                --chimScoreMin "$params.chim.chimScoreMin"
                --chimScoreDropMax "$params.chim.chimScoreDropMax"
                --chimScoreSeparation "$params.chim.chimScoreSeparation"
                --chimScoreJunctionNonGTAG "$params.chim.chimScoreJunctionNonGTAG"
                --chimJunctionOverhangMin "$params.chim.chimJunctionOverhangMin"
            #end if

            ## Limits
            --limitBAMsortRAM "$params.limits.limitBAMsortRAM"
            --limitOutSJoneRead "$params.limits.limitOutSJoneRead"
            --limitOutSJcollapsed "$params.limits.limitOutSJcollapsed"
            --limitSjdbInsertNsj "$params.limits.limitSjdbInsertNsj"

        #end if

    ## Convert chimeric reads.
    #if str($params.settingsType) == "star_fusion" or ( str($params.settingsType) == "full" and str($params.chim.chim_select) == "yes" and int($params.chim.chimSegmentMin) > 0 ):
        &&
        samtools view
            -@ \${GALAXY_SLOTS:-4}
            -Shb Chimeric.out.sam |
        
        samtools sort
            -@ \${GALAXY_SLOTS:-4} - ChimericSorted
    #end if
    ]]></command>

    <inputs>
        <!-- FASTQ input(s) and options specifically for paired-end data. -->
        <conditional name="singlePaired">
            <param name="sPaired" type="select" label="Single-end or paired-end reads">
                <option value="single" selected="true">Single-end</option>
                <option value="paired">Paired-end (as individual datasets)</option>
                <option value="paired_collection">Paired-end (as collection)</option>
            </param>
            <when value="single">
                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file"/>
            </when>
            <when value="paired">
                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file, forward reads"/>
                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" label="RNA-Seq FASTQ/FASTA file, reverse reads"/>
            </when>
            <when value="paired_collection">
                <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input" type="data_collection" collection_type="paired" label="RNA-Seq FASTQ/FASTA paired reads"/>
            </when>
        </conditional>

        <!-- Genome source. -->
        <conditional name="refGenomeSource">
            <param name="geneSource" type="select" label="Custom or built-in reference genome" help="Built-ins were indexed using default options">
                <option value="indexed" selected="True">Use a built-in index</option>
                <option value="history">Use reference genome from history and create temporary index</option>
            </param>
            <when value="indexed">
                <conditional name="GTFconditional">
                    <param name="GTFselect" type="select" label="Reference genome with or without an annotation" help="Must the index have been created WITH a GTF file (if not you can specify one afterward).">
                        <option value="without-gtf">use genome reference without builtin gene-model</option>
                        <option value="with-gtf">use genome reference with builtin gene-model</option>
                    </param>
                    <when value="with-gtf">
                        <param name="genomeDir" argument="--genomeDir" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
                            <options from_data_table="rnastar_index2">
                                <filter type="static_value" column="4" value="1"/>
                                <filter type="sort_by" column="2" />
                                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
                            </options>
                        </param>
                    </when>
                    <when value="without-gtf">
                        <param argument="--genomeDir" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
                            <options from_data_table="rnastar_index2">
                                <filter type="static_value" column="4" value="0"/>
                                <filter type="sort_by" column="2" />
                                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
                            </options>
                        </param>
                        
                        <expand macro="@SJDBOPTIONS@" />
                    </when>
                </conditional>
            </when>
            <when value="history">
                <param argument="--genomeFastaFiles" type="data" format="fasta" label="Select a reference genome" />
                <expand macro="@SJDBOPTIONS@" />
            </when>
        </conditional>
        <param argument="--quantMode" type="boolean" label="Count number of reads per gene" help="column 1: gene ID, column 2: counts for unstranded RNA-seq, column 3: counts for the 1st read strand aligned with RNA , column 4: counts for the 2nd read strand aligned with RNA. This requires either (A) an index that was built with an annotation (GTF or GFF3 file) or (B) having specified an annotation (GTF or GFF3 file above)."/>

        <!-- Output parameter settings. -->
        <conditional name="output_params">
            <param name="output_select" type="select" label="Would you like to set output parameters (formatting and filtering)?">
                <option value="no" selected="true">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="yes">
              <param argument="--outSAMattributes" type="select" label="Extra SAM attributes to include" help="See &quot;Extra SAM attributes&quot; below">
                    <option value="Standard" selected="true">Standard</option>
                    <option value="All">All</option>
                    <option value="None">None</option>
                </param>
                <param argument="--outSAMstrandField" type="select" label="Include strand field flag XS" help="For Cufflinks compatibility with unstranded RNA-seq data, this option is required">
                    <option value="None" selected="true">No</option>
                    <option value="intronMotif">Yes -- and reads with inconsistent and/or non-canonical introns are filtered out</option>
                </param>
                <param argument="--outFilterIntronMotifs" type="select" label="Filter alignments containing non-canonical junctions" help="For Cufflinks compatibility, removing alignments with non-canonical junctions is recommended">
                    <option value="None" selected="true">No</option>
                    <option value="RemoveNoncanonical">Remove alignments with non-canonical junctions</option>
                    <option value="RemoveNoncanonicalUnannotated">Remove alignments with unannotated non-canonical junctions</option>
                </param>
  
              <!-- Additional output parameter settings. -->
              <conditional name="output_params2">
                  <param name="output_select2" type="select" label="Would you like to set additional output parameters (formatting and filtering)?">
                      <option value="no" selected="true">No</option>
                      <option value="yes">Yes</option>
                  </param>
                  <when value="yes">
                      <param argument="--outSAMunmapped" type="boolean" truevalue="Within" falsevalue="None" checked="false" label="Would you like unmapped reads included in the SAM?"/>
                      <param argument="--outSAMprimaryFlag" type="boolean" truevalue="AllBestScore" falsevalue="OneBestScore" checked="false" label="Would you like all alignments with the best score labeled primary?"/>
                      <param argument="--outSAMmapqUnique" type="integer" value="255" min="0" max="255" label="MAPQ value for unique mappers"/>
                      <param argument="--outFilterType" type="boolean" truevalue="BySJout" falsevalue="Normal" checked="false" label="Would you like to keep only reads that contain junctions that passed filtering?"/>
                      <param argument="--outFilterMultimapScoreRange" type="integer" value="1" min="0" label="Score range below the maximum score for multimapping alignments"/>
                      <param argument="--outFilterMultimapNmax" type="integer" value="10" min="1" label="Maximum number of alignments to output a read's alignment results, plus 1" help="Reads with at least this number of alignments will have no alignments output"/>
                      <param argument="--outFilterMismatchNmax" type="integer" value="10" min="0" label="Maximum number of mismatches to output an alignment, plus 1" help="Alignments with at least this number of mismatches will not be output"/>
                      <param argument="--outFilterMismatchNoverLmax" type="float" value="0.3" min="0" max="1" label="Maximum ratio of mismatches to mapped length" help="Alignments with a mismatch ratio of at least this value will not be output"/>
                      <param argument="--outFilterMismatchNoverReadLmax" type="float" value="1" min="0" max="1" label="Maximum ratio of mismatches to read length" help="Alignments with a mismatch ratio of at least this value will not be output"/>
                      <param argument="--outFilterScoreMin" type="integer" value="0" min="0" label="Minimum alignment score" help="Alignments must have scores higher than this value to be output"/>
                      <param argument="--outFilterScoreMinOverLread" type="float" value="0.66" min="0" max="1" label="Minimum alignment score, normalized to read length" help="Alignments must have (normalized) scores higher than this value to be output"/>
                      <param argument="--outFilterMatchNmin" type="integer" value="0" min="0" label="Minimum number of matched bases" help="Alignments must have the number of matched bases higher than this value to be output"/>
                      <param argument="--outFilterMatchNminOverLread" type="float" value="0.66" min="0" max="1" label="Minimum number of matched bases, normalized to read length" help="Alignments must have the (normalized) number of matched bases higher than this value to be output"/>
                  </when>
                  <when value="no"/>
              </conditional>
          </when>
          <when value="no"/>
        </conditional>

        <!-- Other parameter settings. -->
        <conditional name="params">
            <param name="settingsType" type="select" label="Other parameters (seed, alignment, limits and chimeric alignment)">
                <option value="default" selected="true">Use Defaults</option>
                <option value="star_fusion">Use parameters suggested for STAR-Fusion</option>
                <option value="full">Extended parameter list</option>
            </param>
            <when value="default"/>
            <when value="star_fusion"/><!-- Set STAR-fusion parameters automatically -->
  
            <when value="full">
                <section name="seed" title="Seed parameters" expanded="False">
                    <param argument="--seedSearchStartLmax" type="integer" min="1" value="50" label="Search start point through the read"/>
                    <param argument="--seedSearchStartLmaxOverLread" type="float" min="0" value="1.0" label="Search start point through the read, normalized to read length"/>
                    <param argument="--seedSearchLmax" type="integer" min="0" value="0" label="Maximum length of seeds" help="Default of 0 indicates no maximum length"/>
                    <param argument="--seedMultimapNmax" type="integer" min="1" value="10000" label="Maximum number of mappings to use a piece in stitching"/>
                    <param argument="--seedPerReadNmax" type="integer" min="1" value="1000" label="Maximum number of seeds per read"/>
                    <param argument="--seedPerWindowNmax" type="integer" min="1" value="50" label="Maximum number of seeds per window"/>
                    <param argument="--seedNoneLociPerWindow" type="integer" min="1" value="10" label="Maximum number of one seed loci per window"/>
                </section>
    
                <section name="align" title="Alignment parameters" expanded="False">
                    <param argument="--alignIntronMin" name="alignIntronMin" type="integer" min="0" value="21" label="Minimum intron size"/>
                    <param argument="--alignIntronMax" type="integer" min="0" value="0" label="Maximum intron size"/>
                    <param argument="--alignMatesGapMax" type="integer" min="0" value="0" label="Maximum gap between two mates"/>
                    <param argument="--alignSJoverhangMin" type="integer" min="1" value="5" label="Minimum overhang for spliced alignments"/>
                    <param argument="--alignSJDBoverhangMin" type="integer" min="1" value="3" label="Minimum overhang for annotated spliced alignments"/>
                    <param argument="--alignSplicedMateMapLmin" type="integer" min="0" value="0" label="Minimum mapped length for a read mate that is spliced"/>
                    <param argument="--alignSplicedMateMapLminOverLmate" type="float" min="0" value="0.66" label="Minimum mapped length for a read mate that is spliced, normalized to mate length"/>
                    <param argument="--alignWindowsPerReadNmax" type="integer" min="1" value="10000" label="Maximum number of windows per read"/>
                    <param argument="--alignTranscriptsPerWindowNmax" type="integer" min="1" value="100" label="Maximum number of transcripts per window"/>
                    <param argument="--alignTranscriptsPerReadNmax" type="integer" min="1" value="10000" label="Maximum number of different alignments per read to consider"/>
                    <param argument="--alignEndsType" type="boolean" truevalue="EndToEnd" falsevalue="Local" checked="false" label="Use end-to-end read alignments, with no soft-clipping?"/>
                </section>

                <section name="limits" title="Limits" expanded="False">
                    <param argument="--limitBAMsortRAM" type="integer" min="0" value="0" label="Maximum available RAM (in bytes) for sorting" help="If 0, this will be set to the genome index size. This is typically only changed in cases where an error is produced." />
	            <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)" />
	            <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions" />
	            <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly." />
                </section>
    
                <conditional name="chim">
                    <param name="chim_select" type="select" label="Would you like to set chimeric alignment parameters?">
                        <option value="no" selected="true">No</option>
                        <option value="yes">Yes</option>
                    </param>
                    <when value="yes">
                        <param argument="--chimSegmentMin" type="integer" min="0" value="0" label="Minimum length of chimeric segment" help="For small numbers this will cause large number of chimeric alignments. A value of 12 is commonly used. Default of 0 means no chimeric output">
                            <validator type="in_range" min="1" message="To get chimeric reads this value needs to be larger than 0"/>
                        </param>
                        <param argument="--chimScoreMin" type="integer" min="0" value="0" label="Minimum total (summed) score of chimeric segments"/>
                        <param argument="--chimScoreDropMax" type="integer" min="0" value="20" label="Maximum difference of chimeric score from read length"/>
                        <param argument="--chimScoreSeparation" type="integer" min="0" value="10" label="Minimum difference between the best chimeric score and the next one"/>
                        <param argument="--chimScoreJunctionNonGTAG" type="integer" value="-1" label="Penalty for a non-GT/AG chimeric junction"/>
                        <param argument="--chimJunctionOverhangMin" type="integer" min="0" value="20" label="Minimum overhang for a chimeric junction"/>
                    </when>
                    <when value="no"/>
                </conditional>
            </when>
        </conditional>
    </inputs>

    <outputs>
        <data format="txt" name="output_log" label="${tool.name} on ${on_string}: log" from_work_dir="Log.final.out"/>
        <data format="interval" name="chimeric_junctions" label="${tool.name} on ${on_string}: chimeric junctions" from_work_dir="Chimeric.out.junction">
            <filter>params['settingsType'] == "star_fusion" or ( params['settingsType'] == "full" and params['chim']['chim_select'] == "yes" and params['chim']['chimSegmentMin'] > 0 )</filter>
            <actions>
                <conditional name="refGenomeSource.geneSource">
                    <when value="indexed">
                        <action type="metadata" name="dbkey">
                            <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                                <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                                <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
                            </option>
                        </action>
                    </when>
                    <when value="history">
                        <action type="metadata" name="dbkey">
                            <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
                        </action>
                    </when>
                </conditional>
            </actions>
        </data>

        <data format="bam" name="chimeric_reads" label="${tool.name} on ${on_string}: chimeric.bam" from_work_dir="ChimericSorted.bam">
            <filter>params['settingsType'] == "star_fusion" or ( params['settingsType'] == "full" and params['chim']['chim_select'] == "yes" and params['chim']['chimSegmentMin'] > 0 )</filter>
            <actions>
                <conditional name="refGenomeSource.geneSource">
                    <when value="indexed">
                        <action type="metadata" name="dbkey">
                            <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                                <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                                <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
                            </option>
                        </action>
                    </when>
                    <when value="history">
                        <action type="metadata" name="dbkey">
                            <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
                        </action>
                    </when>
                </conditional>
            </actions>
        </data>

        <data format="interval" name="splice_junctions" label="${tool.name} on ${on_string}: splice junctions.bed" from_work_dir="SJ.out.tab">
            <actions>
                <conditional name="refGenomeSource.geneSource">
                    <when value="indexed">
                        <action type="metadata" name="dbkey">
                            <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                                <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                                <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
                            </option>
                        </action>
                    </when>
                    <when value="history">
                        <action type="metadata" name="dbkey">
                            <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
                        </action>
                    </when>
                </conditional>
            </actions>
        </data>

        <data name="mapped_reads" format="bam" label="${tool.name} on ${on_string}: mapped.bam" from_work_dir="Aligned.sortedByCoord.out.bam">
            <actions>
                <conditional name="refGenomeSource.geneSource">
                    <when value="indexed">
                        <action type="metadata" name="dbkey">
                            <option type="from_data_table" name="rnastar_index" column="1" offset="0">
                                <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
                                <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/>
                            </option>
                        </action>
                    </when>
                    <when value="history">
                        <action type="metadata" name="dbkey">
                            <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" />
                        </action>
                    </when>
                </conditional>
            </actions>
        </data>
        
        <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: reads per gene" from_work_dir="ReadsPerGene.out.tab">
            <filter>quantMode is True</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
            <param name="geneSource" value="history" />
            <param name="genomeFastaFiles" value="tophat_test.fa" />
            <param name="sPaired" value="single" />

            <param name="output_select" value="yes" />
            <param name="outSAMattributes" value="All" />
            <param name="outSAMstrandField" value="intronMotif" />
            <param name="settingsType" value="default" />
            
            <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="12"/>
            <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
            <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
        </test>
        <test><!-- tests gtf file and GeneCounts mode -->
            <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
            <param name="geneSource" value="history" />
            <param name="genomeFastaFiles" value="tophat_test.fa" />

            <param name="sjdbOverhang" value="75"/>
            <param name="sjdbGTFfile" value="test1.gtf" ftype="gtf"/>
            <param name="quantMode" value="True"/>

            <param name="sPaired" value="single" />
            <param name="output_select" value="yes" />
            <param name="outSAMattributes" value="All" />
            <param name="outSAMstrandField" value="intronMotif" />
            <param name="settingsType" value="default" />
            
            <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="12"/>
            <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
            <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
            <output name="reads_per_gene" file="tophat_test_reads_per_gene.txt" />
        </test>
        <test>
            <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
            <param name="geneSource" value="history" />
            <param name="genomeFastaFiles" value="tophat_test.fa" />
            <param name="sPaired" value="single" />
            
            <param name="output_select" value="yes" />
            <param name="outSAMattributes" value="All" />
            <param name="outSAMstrandField" value="intronMotif" />
            <param name="outFilterIntronMotifs" value="RemoveNoncanonical" />
            
            <param name="output_select2" value="yes" />
            <param name="outFilterScoreMinOverLread" value="0.9" />
            <param name="settingsType" value="full" />
            <param name="seed_select" value="yes" />
            <param name="seedSearchStartLmax" value="25" />

            <output name="output_log" file="rnastar_test2.log" compare="diff" lines_diff="12"/>
            <output name="splice_junctions" file="rnastar_test2_splicejunctions.bed"/>
            <output name="mapped_reads" file="rnastar_test2_mapped_reads.bam" compare="sim_size" delta="200" />
        </test>
        <test>
            <param name="input1" value="test3.fastqsanger" ftype="fastqsanger" />
            <param name="geneSource" value="history" />
            <param name="genomeFastaFiles" value="test3.ref.fa" />
            <param name="sPaired" value="single" />

            <param name="output_select" value="yes" />
            <param name="outSAMattributes" value="All" />
            <param name="outSAMstrandField" value="intronMotif" />
            <param name="settingsType" value="star_fusion" />

            <output name="chimeric_junctions" file="test3.chimjunc.tabular"/>
        </test>
        <test><!-- tests fastqsanger.gz -->
            <param name="input1" value="test3.fastqsanger.gz" ftype="fastqsanger.gz" />
            <param name="geneSource" value="history" />
            <param name="genomeFastaFiles" value="test3.ref.fa" />
            <param name="sPaired" value="single" />

            <param name="output_select" value="yes" />
            <param name="outSAMattributes" value="All" />
            <param name="outSAMstrandField" value="intronMotif" />
            <param name="settingsType" value="star_fusion" />

            <output name="chimeric_junctions" file="test3.chimjunc.tabular"/>
        </test>
        <test>
            <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
            <param name="geneSource" value="history" />
            <param name="genomeFastaFiles" value="tophat_test.fa" />
            <param name="sPaired" value="single" />

            <param name="output_select" value="yes" />
            <param name="outSAMattributes" value="All" />
            <param name="outSAMstrandField" value="intronMotif" />
            <param name="outFilterIntronMotifs" value="RemoveNoncanonical" />

            <param name="output_select2" value="yes" />
            <param name="settingsType" value="full" />
            <param name="chim_select" value="false" />
            
            <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="12"/>
            <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
            <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
        </test>
    </tests>
    <help>
**What it does**

STAR is an ultrafast universal RNA-seq aligner.

**Extra SAM attributes**

The Standard option includes the following four attributes::

  NH: Number of reported alignments that contain the query in the current record.
  HI: Query hit index, indicating the alignment record is the i-th one stored in SAM
  AS: Local alignment score (paired for paired-end reads)
  nM: Number of mismatches per (paired) alignment

The All option includes the Standard attributes, plus the following four::

  NM: Edit distance to the reference, including ambiguous bases but excluding clipping
  MD: String for mismatching positions
  jM: Intron motifs for all junctions
  jI: Start and end of introns for all junctions

**STAR-Fusion**

STAR-Fusion_ is used to identify candidate fusion transcripts. The recommended_ parameters for running
STAR prior to STAR-Fusion can be pre-selected, with the following exceptions::

  --twopassMode Basic                   # not an option in STAR 2.4.0
  --chimSegmentReadGapMax 3             # not an option in STAR 2.4.0
  --alignSJstitchMismatchNmax 5 -1 5 5  # not an option in STAR 2.4.0

**Attributions**

rna_star - see the web site at rna_star_

For details, please see the rna_starMS_
"STAR: ultrafast universal RNA-seq aligner"
A. Dobin et al, Bioinformatics 2012; doi: 10.1093/bioinformatics/bts635

Galaxy_ (that's what you are using right now!) for gluing everything together

Most of the work for this wrapper XML is Jeremy Goecks' original STAR_ wrapper

Minor tweaks to output names to suit our downstream purposes, toolshed automated dependencies
and odds and ends of other code and documentation comprising this tool was
written by Ross Lazarus and that part is licensed_ the same way as other rgenetics artefacts

.. _STAR: https://bitbucket.org/jgoecks/jeremys-code/raw/fa1930a689b8e2f6b59cc1706e5ba0ed8ad357be/galaxy/tool-wrappers/star.xml
.. _licensed: http://creativecommons.org/licenses/by-nc-nd/3.0/
.. _STAR-Fusion: https://github.com/STAR-Fusion/STAR-Fusion
.. _recommended: https://github.com/STAR-Fusion/STAR-Fusion/wiki#alternatively-running-star-yourself-and-then-running-star-fusion-using-the-existing-outputs
.. _rna_star: https://github.com/alexdobin/STAR
.. _rna_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full
.. _Galaxy: http://getgalaxy.org
    </help>
    <expand macro="citations"/>
</tool>