Mercurial > repos > iuc > rgrnastar
diff rg_rnaStar.xml @ 2:ace9f5a2b40f draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit a89b30e7cbe4e7db22f36773112f7ed833285cb3
author | iuc |
---|---|
date | Fri, 05 Feb 2016 11:56:20 -0500 |
parents | bc685d13b637 |
children | 318b2a9d54dd |
line wrap: on
line diff
--- a/rg_rnaStar.xml Thu Nov 19 05:34:06 2015 -0500 +++ b/rg_rnaStar.xml Fri Feb 05 11:56:20 2016 -0500 @@ -1,4 +1,4 @@ -<tool id="rna_star" name="RNA STAR" version="2.4.0d"> +<tool id="rna_star" name="RNA STAR" version="2.4.0d-2"> <description>Gapped-read mapper for RNA-seq data</description> <requirements> <requirement type="package" version="2.4.0d">rnastar</requirement> @@ -12,86 +12,160 @@ </stdio> <command><![CDATA[ - ## - ## Run STAR. - ## + ## Create temporary index for custom reference #if str($refGenomeSource.genomeSource) == 'history': - mkdir -p tempstargenomedir; STAR --runMode genomeGenerate --genomeDir "tempstargenomedir" --genomeFastaFiles "$refGenomeSource.ownFile" --runThreadN 2 + mkdir -p tempstargenomedir && + STAR + --runMode genomeGenerate + --genomeDir "tempstargenomedir" + --genomeFastaFiles "$refGenomeSource.ownFile" + --runThreadN \${GALAXY_SLOTS:-4} + #if str($refGenomeSource.geneModel) != 'None': - --sjdbOverhang "100" --sjdbGTFfile "$refGenomeSource.geneModel" - #if str($refGenomeSource.geneModel.ext) == 'gff3': - --sjdbGTFtagExonParentTranscript Parent - #end if + --sjdbOverhang "$refGenomeSource.overhang" + --sjdbGTFfile "$refGenomeSource.geneModel" + + #if str($refGenomeSource.geneModel.ext) == 'gff3': + --sjdbGTFtagExonParentTranscript Parent + #end if #end if ; #end if + + + ## Actual alignment STAR - ## Can adjust this as appropriate for the system. - --genomeLoad NoSharedMemory + --runThreadN \${GALAXY_SLOTS:-4} + --genomeLoad NoSharedMemory #if str($refGenomeSource.genomeSource) == 'history': --genomeDir "tempstargenomedir" #else --genomeDir "$refGenomeSource.index.fields.path" #end if - --readFilesIn $singlePaired.input1 - #if str($singlePaired.sPaired) == "paired" - $singlePaired.input2 + + --readFilesIn + #if str($singlePaired.sPaired) == "paired_collection" + "$singlePaired.input.forward" "$singlePaired.input.reverse" + #else + "$singlePaired.input1" + #if str($singlePaired.sPaired) == "paired" + "$singlePaired.input2" + #end if #end if - --runThreadN \${GALAXY_SLOTS:-4} - #if str($params.settingsType) == "full": - --chimSegmentMin $params.chim_segment_min - --chimScoreMin $params.chim_score_min - --seedSearchStartLmax $params.seed_search_start_l_max - --alignSJDBoverhangMin $params.align_sjdb_overhang_min - --outFilterScoreMinOverLread $params.out_filter_score_min_over_l_read + + ## 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.unmapped_opt + --outSAMprimaryFlag $output_params.output_params2.primary_opt + --outSAMmapqUnique "$output_params.output_params2.unique" + --outFilterType $output_params.output_params2.sjfilter_opt + --outFilterMultimapScoreRange "$output_params.output_params2.multiScoreRange" + --outFilterMultimapNmax "$output_params.output_params2.multiNmax" + --outFilterMismatchNmax "$output_params.output_params2.mismatchNmax" + --outFilterMismatchNoverLmax "$output_params.output_params2.mismatchNoverLmax" + --outFilterMismatchNoverReadLmax "$output_params.output_params2.mismatchNoverReadLmax" + --outFilterScoreMin "$output_params.output_params2.scoreMin" + --outFilterScoreMinOverLread "$output_params.output_params2.scoreMinOverLread" + --outFilterMatchNmin "$output_params.output_params2.matchNmin" + --outFilterMatchNminOverLread "$output_params.output_params2.matchNminOverLread" + #end if #end if - ## may or may not need to generate SAM tags and handle non-canonicals for Cufflinks tools. - $outSAMstrandField $outFilterIntronMotifs $outSAMattributes + ## Other parameters + #if str( $params.settingsType ) == "star_fusion": + ## Preset parameters for STAR-Fusion +## --twopass1readsN 100000000 +## --sjdbOverhang 100 + --outReadsUnmapped None + --chimSegmentMin 12 + --chimJunctionOverhangMin 12 + --alignSJDBoverhangMin 10 + --alignMatesGapMax 200000 + --alignIntronMax 200000 + ## --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 + #if str( $params.seed.seed_select ) == "yes": + --seedSearchStartLmax "$params.seed.searchStart" + --seedSearchStartLmaxOverLread "$params.seed.searchStartNorm" + --seedSearchLmax "$params.seed.searchLmax" + --seedMultimapNmax "$params.seed.multimap" + --seedPerReadNmax "$params.seed.readMax" + --seedPerWindowNmax "$params.seed.windowMax" + --seedNoneLociPerWindow "$params.seed.oneSeed" + #end if - ; - ## + ## Alignment parameter options + #if str( $params.align.align_select ) == "yes": + --alignIntronMin "$params.align.intronMin" + --alignIntronMax "$params.align.intronMax" + --alignMatesGapMax "$params.align.gapMax" + --alignSJoverhangMin "$params.align.sjOverhang" + --alignSJDBoverhangMin "$params.align.sjdbOverhang" + --alignSplicedMateMapLmin "$params.align.splicedMate" + --alignSplicedMateMapLminOverLmate "$params.align.splicedMateNorm" + --alignWindowsPerReadNmax "$params.align.windows" + --alignTranscriptsPerWindowNmax "$params.align.transWindow" + --alignTranscriptsPerReadNmax "$params.align.transRead" + --alignEndsType $params.align.endsType_opt + #end if + + ## Chimeric alignment parameter options + #if str( $params.chim.chim_select ) == "yes": + --chimSegmentMin "$params.chim.segmentMin" + --chimScoreMin "$params.chim.scoreMin" + --chimScoreDropMax "$params.chim.scoreDrop" + --chimScoreSeparation "$params.chim.scoreSep" + --chimScoreJunctionNonGTAG "$params.chim.scoreJunction" + --chimJunctionOverhangMin "$params.chim.junctionOverhang" + #end if + + #end if + ## BAM conversion. - ## - + ## Convert aligned reads. - samtools view -Shb Aligned.out.sam | samtools sort - AlignedSorted 2>/dev/null - + && samtools view -@ \${GALAXY_SLOTS:-4} -Shb Aligned.out.sam | samtools sort -@ \${GALAXY_SLOTS:-4} - AlignedSorted 2>/dev/null + ## Convert chimeric reads. - #if str($params.settingsType) == "full" and $params.chim_segment_min > 0: - ; samtools view -Shb Chimeric.out.sam | samtools sort - ChimericSorted 2>/dev/null + #if str($params.settingsType) == "star_fusion" or ( str($params.settingsType) == "full" and str($params.chim.chim_select) == "yes" and int($params.chim.segmentMin) > 0 ): + && samtools view -@ \${GALAXY_SLOTS:-4} -Shb Chimeric.out.sam | samtools sort -@ \${GALAXY_SLOTS:-4} - ChimericSorted 2>/dev/null #end if ]]></command> <inputs> - <param name="jobName" type="text" value="rna-star run" label="Job narrative (added to output names)" - help="Only letters, numbers and underscores (_) will be retained in this field"> - <sanitizer invalid_char=""> - <valid initial="string.letters,string.digits"><add value="_" /> </valid> - </sanitizer> - </param> <!-- FASTQ input(s) and options specifically for paired-end data. --> <conditional name="singlePaired"> - <param name="sPaired" type="select" label="Single ended or mate-pair ended reads in this library?"> + <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</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="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> + <param format="fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file"/> </when> <when value="paired"> - <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" - help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> - <param format="fastqsanger,fastq,fasta" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" - help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file, forward reads"/> + <param format="fastq,fasta" name="input2" type="data" label="RNA-Seq FASTQ/FASTA file, reverse reads"/> + </when> + <when value="paired_collection"> + <param format="fastq,fasta" name="input" type="data_collection" collection_type="paired" label="RNA-Seq FASTQ/FASTA paired reads"/> </when> </conditional> <!-- Genome source. --> <conditional name="refGenomeSource"> - <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> + <param name="genomeSource" 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">Index and use a genome fasta file from my current history</option> + <option value="history">Index and use a genome fasta and GTF file from history</option> </param> <when value="indexed"> <param name="index" type="select" label="Select a reference genome"> @@ -104,220 +178,325 @@ <when value="history"> <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /> <param name="geneModel" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions. Leave blank for none" - optional="true" help="Optional. If supplied, the index file will retain exon junction information for mapping splices" /> + optional="true" help="Optional. If supplied, the index file will retain exon junction information for mapping splices (--sjdbGTFfile)"/> + <param name="overhang" type="integer" min="0" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1 (--sjdbOverhang)"/> </when> </conditional> - <param name="outSAMattributes" type="select" label="Include extra sam attributes for downstream processing"> - <option value="--outSAMattributes Standard">Standard - eg for old Samtools downstream</option> - <option value="--outSAMattributes All" selected="true">All modern Samtools attributes - see below</option> + + <!-- 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 name="outSAMattributes" type="select" label="Extra SAM attributes to include" help="See "Extra SAM attributes" below (--outSAMattributes)"> + <option value="Standard" selected="true">Standard</option> + <option value="All">All</option> + <option value="None">None</option> + </param> + <param name="outSAMstrandField" type="select" label="Include strand field flag XS" help="For Cufflinks compatibility with unstranded RNA-seq data, this option is required (--outSAMstrandField)"> + <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 name="outFilterIntronMotifs" type="select" label="Filter alignments containing non-canonical junctions" help="For Cufflinks compatibility, removing alignments with non-canonical junctions is recommended (--outFilterIntronMotifs)"> + <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> - <param name="outSAMstrandField" type="select" label="Include extra sam attributes for downstream processing"> - <option value="--outSAMstrandField intronMotif" selected="true">Add XS for cufflinks</option> - <option value="">No XS added to sam output</option> - </param> - <param name="outFilterIntronMotifs" type="select" label="Canonical junction preparation for unstranded data (--outFilterIntronMotifs)"> - <option value="">No special handling - all non-canonical junctions passed through</option> - <option value="--outFilterIntronMotifs RemoveNoncanonical" selected="true">Remove all non-canonical junctions for eg cufflinks</option> - <option value="--outFilterIntronMotifs RemoveNoncanonicalUnannotated">Remove only unannotated non-canonical junctions for eg cufflinks</option> - </param> - <!-- Parameter settings. --> + + <!-- 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 name="unmapped_opt" type="boolean" truevalue="Within" falsevalue="None" checked="false" label="Would you like unmapped reads included in the SAM?" help="(--outSAMunmapped)"/> + <param name="primary_opt" type="boolean" truevalue="AllBestScore" falsevalue="OneBestScore" checked="false" label="Would you like all alignments with the best score labeled primary?" help="(--outSAMprimaryFlag)"/> + <param name="unique" type="integer" value="255" min="0" max="255" label="MAPQ value for unique mappers" help="(--outSAMmapqUnique)"/> + <param name="sjfilter_opt" type="boolean" truevalue="BySJout" falsevalue="Normal" checked="false" label="Would you like to keep only reads that contain junctions that passed filtering?" help="(--outFilterType)"/> + <param name="multiScoreRange" type="integer" value="1" min="0" label="Score range below the maximum score for multimapping alignments" help="(--outFilterMultimapScoreRange)"/> + <param name="multiNmax" 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 (--outFilterMultimapNmax)"/> + <param name="mismatchNmax" 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 (--outFilterMismatchNmax)"/> + <param name="mismatchNoverLmax" 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 (--outFilterMismatchNoverLmax)"/> + <param name="mismatchNoverReadLmax" 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 (--outFilterMismatchNoverReadLmax)"/> + <param name="scoreMin" type="integer" value="0" min="0" label="Minimum alignment score" help="Alignments must have scores higher than this value to be output (--outFilterScoreMin)"/> + <param name="scoreMinOverLread" 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 (--outFilterScoreMinOverLread)"/> + <param name="matchNmin" 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 (--outFilterMatchNmin)"/> + <param name="matchNminOverLread" 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 (--outFilterMatchNminOverLread)"/> + </when> + <when value="no"/> + </conditional> + + </when> + <when value="no"/> + </conditional> + + <!-- Other parameter settings. --> <conditional name="params"> - <param name="settingsType" type="select" label="Settings to use" help="You can use the default settings or set custom values for any STAR parameter."> - <option value="preSet" selected="true">Use Defaults</option> - <option value="full">Full parameter list</option> - </param> - <when value="preSet" /> - <!-- Full/advanced params. --> - <when value="full"> - <param name="chim_segment_min" type="integer" min="0" value="0" label="Minimum chimeric segment length (--chimSegmentMin)" /> - <param name="chim_score_min" type="integer" min="0" value="0" label="Minimum total (summed) score of the chimeric segments (--chimScoreMin)" /> - <param name="seed_search_start_l_max" type="integer" min="0" value="50" label="Defines the search start point through the read - the read is split into pieces no longer than this value (--seedSearchStartLmax)" /> - <param name="align_sjdb_overhang_min" type="integer" value="1" label="Minimum overhang for annotated junctions (--alignSJDBoverhangMin)" /> - <param name="out_filter_score_min_over_l_read" type="float" value="0.66" label="OutFilterScoreMin normalized to read length; sum of mates’ lengths for paired-end reads (--outFilterScoreMinOverLread)" /> - </when> + <param name="settingsType" type="select" label="Other parameters (seed, alignment, 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"> + + <!-- Seed parameters --> + <conditional name="seed"> + <param name="seed_select" type="select" label="Would you like to set seed parameters?"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <param name="searchStart" type="integer" min="1" value="50" label="Search start point through the read" help="(--seedSearchStartLmax)"/> + <param name="searchStartNorm" type="float" min="0" value="1.0" label="Search start point through the read, normalized to read length" help="(--seedSearchStartLmaxOverLread)"/> + <param name="searchLmax" type="integer" min="0" value="0" label="Maximum length of seeds" help="Default of 0 indicates no maximum length (--seedSearchLmax)"/> + <param name="multimap" type="integer" min="1" value="10000" label="Maximum number of mappings to use a piece in stitching" help="(--seedMultimapNmax)"/> + <param name="readMax" type="integer" min="1" value="1000" label="Maximum number of seeds per read" help="(--seedPerReadNmax)"/> + <param name="windowMax" type="integer" min="1" value="50" label="Maximum number of seeds per window" help="(--seedPerWindowNmax)"/> + <param name="oneSeed" type="integer" min="1" value="10" label="Maximum number of one seed loci per window" help="(--seedNoneLociPerWindow)"/> + </when> + <when value="no"/> + </conditional> + + <!-- Alignment parameters --> + <conditional name="align"> + <param name="align_select" type="select" label="Would you like to set alignment parameters?"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <param name="intronMin" type="integer" min="0" value="21" label="Minimum intron size" help="(--alignIntronMin)"/> + <param name="intronMax" type="integer" min="0" value="0" label="Maximum intron size" help="(--alignIntronMax)"/> + <param name="gapMax" type="integer" min="0" value="0" label="Maximum gap between two mates" help="(--alignMatesGapMax)"/> + <param name="sjOverhang" type="integer" min="1" value="5" label="Minimum overhang for spliced alignments" help="(--alignSJoverhangMin)"/> + <param name="sjdbOverhang" type="integer" min="1" value="3" label="Minimum overhang for annotated spliced alignments" help="(--alignSJDBoverhangMin)"/> + <param name="splicedMate" type="integer" min="0" value="0" label="Minimum mapped length for a read mate that is spliced" help="(--alignSplicedMateMapLmin)"/> + <param name="splicedMateNorm" type="float" min="0" value="0.66" label="Minimum mapped length for a read mate that is spliced, normalized to mate length" help="(--alignSplicedMateMapLminOverLmate)"/> + <param name="windows" type="integer" min="1" value="10000" label="Maximum number of windows per read" help="(--alignWindowsPerReadNmax)"/> + <param name="transWindow" type="integer" min="1" value="100" label="Maximum number of transcripts per window" help="(--alignTranscriptsPerWindowNmax)"/> + <param name="transRead" type="integer" min="1" value="10000" label="Maximum number of different alignments per read to consider" help="(--alignTranscriptsPerReadNmax)"/> + <param name="endsType_opt" type="boolean" truevalue="EndToEnd" falsevalue="Local" checked="false" label="Use end-to-end read alignments, with no soft-clipping?" help="(--alignEndsType)"/> + </when> + <when value="no"/> + </conditional> + + <!-- Chimeric alignment parameters --> + <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 name="segmentMin" type="integer" min="0" value="0" label="Minimum length of chimeric segment" help="Default of 0 means no chimeric output (--chimSegmentMin)"/> + <param name="scoreMin" type="integer" min="0" value="0" label="Minimum total (summed) score of chimeric segments" help="(--chimScoreMin)"/> + <param name="scoreDrop" type="integer" min="0" value="20" label="Maximum difference of chimeric score from read length" help="(--chimScoreDropMax)"/> + <param name="scoreSep" type="integer" min="0" value="10" label="Minimum difference between the best chimeric score and the next one" help="(--chimScoreSeparation)"/> + <param name="scoreJunction" type="integer" value="-1" label="Penalty for a non-GT/AG chimeric junction" help="(--chimScoreJunctionNonGTAG)"/> + <param name="junctionOverhang" type="integer" min="0" value="20" label="Minimum overhang for a chimeric junction" help="(--chimJunctionOverhangMin)"/> + </when> + <when value="no"/> + </conditional> + + </when> </conditional> + </inputs> <outputs> - <data format="txt" name="output_log" label="${jobName}.log" from_work_dir="Log.final.out"/> - <data format="interval" name="chimeric_junctions" label="${jobName}_starchimjunc.bed" from_work_dir="Chimeric.out.junction"> - <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter> - <actions> - <conditional name="refGenomeSource.genomeSource"> - <when value="indexed"> - <action type="metadata" name="dbkey"> - <option type="from_data_table" name="rnastar_index" column="1" offset="0"> - <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> - <filter type="param_value" ref="refGenomeSource.index" column="0"/> - </option> - </action> - </when> - <when value="history"> - <action type="metadata" name="dbkey"> - <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> - </action> - </when> - </conditional> - </actions> - </data> - <data format="bam" name="chimeric_reads" label="${jobName}_starmappedchim.bam" - from_work_dir="ChimericSorted.bam"> - <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter> - <actions> - <conditional name="refGenomeSource.genomeSource"> - <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.index" column="0"/> - </option> - </action> - </when> - <when value="history"> - <action type="metadata" name="dbkey"> - <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> - </action> - </when> - </conditional> - </actions> + <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 ${on_string}: starchimjunc" from_work_dir="Chimeric.out.junction"> + <filter>params['settingsType'] == "star_fusion" or ( params['settingsType'] == "full" and params['chim']['chim_select'] == "yes" and params['chim']['segmentMin'] > 0 )</filter> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="rnastar_index" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> </data> - <data format="interval" name="splice_junctions" label="${jobName}_starsplicejunct.bed" - from_work_dir="SJ.out.tab"> - <actions> - <conditional name="refGenomeSource.genomeSource"> - <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.index" column="0"/> - </option> - </action> - </when> - <when value="history"> - <action type="metadata" name="dbkey"> - <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> - </action> - </when> - </conditional> - </actions> + + <data format="bam" name="chimeric_reads" label="${tool.name} on ${on_string}: starmappedchim.bam" from_work_dir="ChimericSorted.bam"> + <filter>params['settingsType'] == "star_fusion" or ( params['settingsType'] == "full" and params['chim']['chim_select'] == "yes" and params['chim']['segmentMin'] > 0 )</filter> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="rnastar_index" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> </data> - <data format="bam" name="mapped_reads" label="${jobName}_starmapped.bam" - from_work_dir="AlignedSorted.bam"> - <actions> - <conditional name="refGenomeSource.genomeSource"> - <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.index" column="0"/> - </option> - </action> - </when> - <when value="history"> - <action type="metadata" name="dbkey"> - <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> - </action> - </when> - </conditional> - </actions> + + <data format="interval" name="splice_junctions" label="${tool.name} on ${on_string}: starsplicejunct.bed" from_work_dir="SJ.out.tab"> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="rnastar_index" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + + <data format="bam" name="mapped_reads" label="${tool.name} on ${on_string}: starmapped.bam" from_work_dir="AlignedSorted.bam"> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <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.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> </data> </outputs> + <tests> <test> - <param name='input1' value='tophat_in2.fastqsanger' ftype='fastqsanger' /> - <param name='jobName' value='rnastar_test' /> - <param name='genomeSource' value='history' /> - <param name='ownFile' value='tophat_test.fa' /> - <param name='sPaired' value='single' /> - <param name='outSAMattributes' value='--outSAMattributes All' /> - <param name='outSAMstrandField' value='--outSAMstrandField intronMotif' /> - <param name='outFilterIntronMotifs' value='--outFilterIntronMotifs RemoveNoncanonical' /> + <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> + <param name="genomeSource" value="history" /> + <param name="ownFile" 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 = '10'/> - <output name='splice_junctions' file="rnastar_test_splicejunctions.bed"/> - <output name='mapped_reads' file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="200" /> + <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff = "10"/> + <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/> + <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="200" /> </test> <test> - <param name='input1' value='tophat_in2.fastqsanger' ftype='fastqsanger' /> - <param name='jobName' value='rnastar_test' /> - <param name='genomeSource' value='history' /> - <param name='ownFile' value='tophat_test.fa' /> - <param name='sPaired' value='single' /> - <param name='outSAMattributes' value='--outSAMattributes All' /> - <param name='outSAMstrandField' value='--outSAMstrandField intronMotif' /> - <param name='outFilterIntronMotifs' value='--outFilterIntronMotifs RemoveNoncanonical' /> + <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> + <param name="genomeSource" value="history" /> + <param name="ownFile" 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="scoreMinOverLread" value="0.9" /> <param name="settingsType" value="full" /> - - <param name="chim_segment_min" value="0" /> - <param name="chim_score_min" value="0" /> - <param name="seed_search_start_l_max" value="25" /> - <param name="align_sjdb_overhang_min" value="3" /> - <param name="out_filter_score_min_over_l_read" value="0.9" /> + <param name="seed_select" value="yes" /> + <param name="searchStart" value="25" /> - <output name='output_log' file='rnastar_test2.log' compare='diff' lines_diff = '10'/> - <output name='splice_junctions' file="rnastar_test2_splicejunctions.bed"/> - <output name='mapped_reads' file="rnastar_test2_mapped_reads.bam" compare="sim_size" delta="200" /> + <output name="output_log" file="rnastar_test2.log" compare="diff" lines_diff="10"/> + <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> - </tests> -<help> -**What it does** -Runs the rna star gapped aligner. Suited to paired or single end rna-seq. - -8.2: SAM alignments -The number of loci Nmap a read maps to (multi-mapping) is given by NH:i: field. -The mapping quality MAPQ (column 5) is 255 for uniquely mapping reads, and int(-10*log10(1-1/Nmap)) for -multi-mapping reads. This scheme is same as the one used by Tophat and is compatible with Cufflinks. - -For multi-mappers, all alignments except one are marked with 0x100 (secondary alignment) in the FLAG -column 2. The un-marked alignment is either the best one (i.e. highest scoring), or is randomly selected from -the alignments of equal quality. - -8.2.1: Standard SAM attributes -With default --outSAMattributes Standard option the following SAM attributes will be generated: + <test> + <param name="input1" value="test3.fastqsanger" ftype="fastqsanger" /> + <param name="genomeSource" value="history" /> + <param name="ownFile" value="test3.ref.fa" /> + <param name="sPaired" value="single" /> -Column 12: NH: number of loci a read (pair) maps to -Column 13: IH: alignment index for all alignments of a read -Column 14: aS: alignment score -Column 15: nM: number of mismatches (does not include indels) - -8.2.2: Extra SAM attrbiutes -If --outSAMattributes All option is used, the following additional attributes will be output: - -Column 16: jM:B:c,M1,M2,... Intron motifs for all junctions (i.e. N in CIGAR): -0: non-canonical; 1:GT/AG, 2: CT/AC, 3: GC/AG, 4: CT/GC, 5: AT/AC, 6: GT/AT. - -If splice junctions database is used, and a junction is annotated, 20 is added to its motif value. -Column 17: jI:B:I,Start1,End1,Start2,End2,... Start and End of introns for all junctions (1-based) - -Note, that samtools 0.1.18 or later have to be used with these extra attributes. - - -8.2.3: XS SAM strand attribute for Cufflinks/Cuffdiff + <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="genomeSource" value="history" /> + <param name="ownFile" 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="seed_select" value="yes" /> + <param name="align_select" value="yes" /> + <param name="chim_select" value="yes" /> + + <!-- Uses default settings, should be similar to test1, but tests the parameters --> + <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="10"/> + <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/> + <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" /><!-- header is 434 bytes larger --> + </test> -If you have un-stranded RNA-seq data, and wish to run Cufflinks/Cuffdiff on STAR alignments, you will -need to run STAR with --outSAMstrandField intronMotif option, which will generate the XS -strand attribute for all alignments that contain splice junctions. The spliced alignments that have undefined -strand (i.e. containing only non-canonical junctions) will be suppressed. + </tests> + <help> +**What it does** + +This tool runs STAR, an ultrafast universal RNA-seq aligner. -If you have stranded RNA-seq data, you do not need to use any specific STAR options. Instead, you need -to run Cufflinks with the library option --library-type options. For example, cufflinks with -library-type fr-firststrand should be used for the b +**Extra SAM attributes** + +The Standard option includes the following four attributes:: -It is recommended to remove the non-canonical junctions for Cufflinks runs using b + 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:: ---outFilterIntronMotifs RemoveNoncanonical -filter out alignments that contain non-canonical junctions - -OR + 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 ---outFilterIntronMotifs RemoveNoncanonicalUnannotated -filter out alignments that contain non-canonical unannotated junctions -when using annotated splice junctions database. The annotated non- -canonical junctions will be kept. +**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** @@ -341,13 +520,13 @@ .. _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> -<citations> - <citation type="doi">10.1093/bioinformatics/bts635</citation> -</citations> + <citations> + <citation type="doi">10.1093/bioinformatics/bts635</citation> + </citations> </tool> -