1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/5293f1bf1dba/ changeset: 5293f1bf1dba user: jgoecks date: 2012-04-27 21:22:11 summary: More cleaning of Tophat wrapper. affected #: 2 files diff -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -52,16 +52,16 @@ supplied GFF file. (ignored without -G)") parser.add_option( '', '--no-novel-indels', action="store_true", dest='no_novel_indels', help="Skip indel search. Indel search is enabled by default.") # Types of search. - parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--closure-search', action="store_true", dest='closure_search', help='Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (<= 50bp)') parser.add_option( '', '--no-closure-search', action="store_false", dest='closure_search' ) + parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) + parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) + parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) + parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--coverage-search', action="store_true", dest='coverage_search', help='Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.') parser.add_option( '', '--no-coverage-search', action="store_false", dest='coverage_search' ) parser.add_option( '', '--min-segment-intron', dest='min_segment_intron', help='Minimum intron length that may be found during split-segment search' ) parser.add_option( '', '--max-segment-intron', dest='max_segment_intron', help='Maximum intron length that may be found during split-segment search' ) - parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) - parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) - parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) parser.add_option( '', '--min-coverage-intron', dest='min_coverage_intron', help='Minimum intron length that may be found during coverage search' ) parser.add_option( '', '--max-coverage-intron', dest='max_coverage_intron', help='Maximum intron length that may be found during coverage search' ) @@ -166,7 +166,7 @@ opts += ' --no-closure-search' if options.microexon_search: opts += ' --microexon-search' - if options.single_paired == 'paired': + if options.single_paired == 'paired' and options.mate_std_dev: opts += ' --mate-std-dev %s' % options.mate_std_dev if options.initial_read_mismatches: opts += ' --initial-read-mismatches %d' % int( options.initial_read_mismatches ) diff -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -7,150 +7,111 @@ </requirements><command interpreter="python"> tophat_wrapper.py - ## Change this to accommodate the number of threads you have available. - --num-threads="4" + + ## Change this to accommodate the number of threads you have available. + --num-threads="4" - ## Provide outputs. - --junctions-output=$junctions - --hits-output=$accepted_hits + ## Provide outputs. + --junctions-output=$junctions + --hits-output=$accepted_hits - ## Handle reference file. - #if $refGenomeSource.genomeSource == "history": - --own-file=$refGenomeSource.ownFile + ## Handle reference file. + #if $refGenomeSource.genomeSource == "history": + --own-file=$refGenomeSource.ownFile + #else: + --indexes-path="${refGenomeSource.index.fields.path}" + #end if + + ## Are reads single-end or paired? + --single-paired=$singlePaired.sPaired + + ## First input file always required. + --input1=$input1 + + ## Second input only if input is paired-end. + #if $singlePaired.sPaired == "paired" + --input2=$singlePaired.input2 + -r $singlePaired.mate_inner_distance + --mate-std-dev=$singlePaired.mate_std_dev + #end if + + ## Set params. + --settings=$params.settingsType + #if $params.settingsType == "full": + -a $params.anchor_length + -m $params.splice_mismatches + -i $params.min_intron_length + -I $params.max_intron_length + -g $params.max_multihits + --min-segment-intron $params.min_segment_intron + --max-segment-intron $params.max_segment_intron + --initial-read-mismatches=$params.initial_read_mismatches + --seg-mismatches=$params.seg_mismatches + --seg-length=$params.seg_length + --library-type=$params.library_type + + ## Closure search. + #if $params.closure_search.use_search == "Yes": + --closure-search + --min-closure-exon $params.closure_search.min_closure_exon + --min-closure-intron $params.closure_search.min_closure_intron + --max-closure-intron $params.closure_search.max_closure_intron #else: - --indexes-path="${refGenomeSource.index.fields.path}" + --no-closure-search + #end if + + ## Indel search. + #if $params.indel_search.allow_indel_search == "Yes": + ## --allow-indels + --max-insertion-length $params.indel_search.max_insertion_length + --max-deletion-length $params.indel_search.max_deletion_length + #else: + --no-novel-indels #end if - ## Are reads single-end or paired? - --single-paired=$singlePaired.sPaired - - ## First input file always required. - --input1=$input1 - - ## Set params based on whether reads are single-end or paired. - #if $singlePaired.sPaired == "single": - --settings=$singlePaired.sParams.sSettingsType - #if $singlePaired.sParams.sSettingsType == "full": - -a $singlePaired.sParams.anchor_length - -m $singlePaired.sParams.splice_mismatches - -i $singlePaired.sParams.min_intron_length - -I $singlePaired.sParams.max_intron_length - -g $singlePaired.sParams.max_multihits - --min-segment-intron $singlePaired.sParams.min_segment_intron - --max-segment-intron $singlePaired.sParams.max_segment_intron - --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches - --seg-mismatches=$singlePaired.sParams.seg_mismatches - --seg-length=$singlePaired.sParams.seg_length - --library-type=$singlePaired.sParams.library_type - - ## Indel search. - #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length - --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length - #else: - --no-novel-indels - #end if - - ## Supplying junctions parameters. - #if $singlePaired.sParams.own_junctions.use_junctions == "Yes": - #if $singlePaired.sParams.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $singlePaired.sParams.own_junctions.gene_model_ann.gene_annotation_model - #end if - #if $singlePaired.sParams.own_junctions.raw_juncs.use_juncs == "Yes": - -j $singlePaired.sParams.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why a string cast is necessary, but it is: - #if str($singlePaired.sParams.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs - #end if - #end if - - #if $singlePaired.sParams.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $singlePaired.sParams.closure_search.min_closure_exon - --min-closure-intron $singlePaired.sParams.closure_search.min_closure_intron - --max-closure-intron $singlePaired.sParams.closure_search.max_closure_intron - #else: - --no-closure-search - #end if - #if $singlePaired.sParams.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $singlePaired.sParams.coverage_search.min_coverage_intron - --max-coverage-intron $singlePaired.sParams.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str($singlePaired.sParams.microexon_search) == "Yes": - --microexon-search - #end if + ## Supplying junctions parameters. + #if $params.own_junctions.use_junctions == "Yes": + #if $params.own_junctions.gene_model_ann.use_annotations == "Yes": + -G $params.own_junctions.gene_model_ann.gene_annotation_model #end if - #else: - --input2=$singlePaired.input2 - -r $singlePaired.mate_inner_distance - --settings=$singlePaired.pParams.pSettingsType - #if $singlePaired.pParams.pSettingsType == "full": - --mate-std-dev=$singlePaired.pParams.mate_std_dev - -a $singlePaired.pParams.anchor_length - -m $singlePaired.pParams.splice_mismatches - -i $singlePaired.pParams.min_intron_length - -I $singlePaired.pParams.max_intron_length - -g $singlePaired.pParams.max_multihits - --min-segment-intron $singlePaired.pParams.min_segment_intron - --max-segment-intron $singlePaired.pParams.max_segment_intron - --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches - --seg-mismatches=$singlePaired.pParams.seg_mismatches - --seg-length=$singlePaired.pParams.seg_length - --library-type=$singlePaired.pParams.library_type - - ## Indel search. - #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length - --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length - #else: - --no-novel-indels - #end if - - ## Supplying junctions parameters. - #if $singlePaired.pParams.own_junctions.use_junctions == "Yes": - #if $singlePaired.pParams.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $singlePaired.pParams.own_junctions.gene_model_ann.gene_annotation_model - #end if - #if $singlePaired.pParams.own_junctions.raw_juncs.use_juncs == "Yes": - -j $singlePaired.pParams.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why type cast is necessary, but it is: - #if str($singlePaired.pParams.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs - #end if - #end if - - #if $singlePaired.pParams.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $singlePaired.pParams.closure_search.min_closure_exon - --min-closure-intron $singlePaired.pParams.closure_search.min_closure_intron - --max-closure-intron $singlePaired.pParams.closure_search.max_closure_intron - #else: - --no-closure-search - #end if - #if $singlePaired.pParams.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $singlePaired.pParams.coverage_search.min_coverage_intron - --max-coverage-intron $singlePaired.pParams.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str ($singlePaired.pParams.microexon_search) == "Yes": - --microexon-search - #end if + #if $params.own_junctions.raw_juncs.use_juncs == "Yes": + -j $params.own_junctions.raw_juncs.raw_juncs + #end if + ## TODO: No idea why a string cast is necessary, but it is: + #if str($params.own_junctions.no_novel_juncs) == "Yes": + --no-novel-juncs #end if #end if + + #if $params.coverage_search.use_search == "Yes": + --coverage-search + --min-coverage-intron $params.coverage_search.min_coverage_intron + --max-coverage-intron $params.coverage_search.max_coverage_intron + #else: + --no-coverage-search + #end if + ## TODO: No idea why the type conversion is necessary, but it seems to be. + #if str($params.microexon_search) == "Yes": + --microexon-search + #end if + #end if </command><inputs> - <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + </param> + <when value="single"> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> + </when> + <when value="paired"> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset--forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ dataset--reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> + <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> + </when> + </conditional><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"><option value="indexed">Use a built-in index</option> @@ -168,221 +129,109 @@ <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /></when><!-- history --></conditional><!-- refGenomeSource --> - <conditional name="singlePaired"> - <param name="sPaired" type="select" label="Is this library mate-paired?"> - <option value="single">Single-end</option> - <option value="paired">Paired-end</option> + <conditional name="params"> + <param name="settingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> + <option value="preSet">Use Defaults</option> + <option value="full">Full parameter list</option></param> - <when value="single"> - <conditional name="sParams"> - <param name="sSettingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> - <option value="preSet">Use Defaults</option> - <option value="full">Full parameter list</option> - </param> - <when value="preSet" /> - <!-- Full/advanced params. --> - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> + <when value="preSet" /> + <!-- Full/advanced params. --> + <when value="full"> + <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> + <option value="fr-unstranded">FR Unstranded</option> + <option value="fr-firststrand">FR First Strand</option> + <option value="fr-secondstrand">FR Second Strand</option> + </param> + <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> + <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> + <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> + <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> + <conditional name="indel_search"> + <param name="allow_indel_search" type="select" label="Allow indel search"> + <option value="Yes">Yes</option> + <option value="No">No</option></param> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> - <option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> -alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> - - <!-- Options for supplying own junctions. --> - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> + <when value="No"/> + <when value="Yes"> + <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> + <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> + </when> + </conditional> + alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> + <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> + <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> + <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> + <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> + <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> + <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> + + <!-- Options for supplying own junctions. --> + <conditional name="own_junctions"> + <param name="use_junctions" type="select" label="Use Own Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <conditional name="gene_model_ann"> + <param name="use_annotations" type="select" label="Use Gene Annotation Model"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> + </when> + </conditional> + <conditional name="raw_juncs"> + <param name="use_juncs" type="select" label="Use Raw Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> + </when> + </conditional> + <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"><option value="No">No</option><option value="Yes">Yes</option></param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - <when value="No" /> - </conditional><!-- /own_junctions --> - - <!-- Closure search. --> - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> - <!-- Coverage search. --> - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> + </when> + <when value="No" /> + </conditional><!-- /own_junctions --> + + <!-- Closure search. --> + <conditional name="closure_search"> + <param name="use_search" type="select" label="Use Closure Search"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> + <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> + <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> + </when> + <when value="No" /> + </conditional> + + <!-- Coverage search. --> + <conditional name="coverage_search"> + <param name="use_search" type="select" label="Use Coverage Search"> + <option selected="true" value="Yes">Yes</option><option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when><!-- full --> - </conditional><!-- sParams --> - </when><!-- single --> - <when value="paired"> - <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> - <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> - <conditional name="pParams"> - <param name="pSettingsType" type="select" label="TopHat settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list"> - <option value="preSet">Commonly used</option> - <option value="full">Full parameter list</option></param> - <when value="preSet" /> - <!-- Full/advanced params. --> - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> - </param> - <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> - <option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> - <!-- Options for supplying own junctions. --> - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - <when value="No" /> - </conditional><!-- /own_junctions --> - - <!-- Closure search. --> - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> - <!-- Coverage search. --> - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when><!-- full --> - </conditional><!-- pParams --> - </when><!-- paired --> - </conditional> + <when value="Yes"> + <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> + <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> + </when> + <when value="No" /> + </conditional> + <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + </when><!-- full --> + </conditional><!-- params --></inputs><outputs> @@ -471,11 +320,11 @@ tophat -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="single" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /><param name="genomeSource" value="indexed" /><param name="index" value="tophat_test" /> - <param name="sPaired" value="single" /> - <param name="sSettingsType" value="preSet" /> + <param name="settingsType" value="preSet" /><output name="junctions" file="tophat_out1j.bed" /><output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" /></test> @@ -486,13 +335,13 @@ tophat -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="paired" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="genomeSource" value="history" /><param name="ownFile" ftype="fasta" value="tophat_in1.fasta" /> - <param name="sPaired" value="paired" /> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="mate_inner_distance" value="20" /> - <param name="pSettingsType" value="preSet" /> + <param name="settingsType" value="preSet" /><output name="junctions" file="tophat_out2j.bed" /><output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" /></test> @@ -500,15 +349,15 @@ <test><!-- Tophat commands: bowtie-build -f test-data/tophat_in1.fasta tophat_in1 - tophat -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +closure-search +min-closure-exon 50 +min-closure-intron 50 +max-closure-intro 5000 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger + tophat -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger Replace the + with double-dash Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="single"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/><param name="genomeSource" value="history"/><param name="ownFile" value="tophat_in1.fasta"/> - <param name="sPaired" value="single"/> - <param name="sSettingsType" value="full"/> + <param name="settingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="anchor_length" value="8"/><param name="splice_mismatches" value="0"/> @@ -546,13 +395,13 @@ Replace the + with double-dash Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="paired"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="genomeSource" value="indexed"/><param name="index" value="tophat_test"/> - <param name="sPaired" value="paired"/> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="mate_inner_distance" value="20"/> - <param name="pSettingsType" value="full"/> + <param name="settingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="mate_std_dev" value="20"/><param name="anchor_length" value="8"/> @@ -644,16 +493,15 @@ -j/--raw-juncs [juncs file] Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive. -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G) --no-closure-search Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default. - --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (about or less than 50bp) + --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the + --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. + --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. + --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. expected inner distance between mates is small (about or less than 50bp) --no-coverage-search Disables the coverage based search for junctions. --coverage-search Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity. --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer. - --butterfly-search TopHat will use a slower but potentially more sensitive algorithm to find junctions in addition to its standard search. Consider using this if you expect that your experiment produced a lot of reads from pre-mRNA, that fall within the introns of your transcripts. --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2. --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25. - --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. - --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. - --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50. --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000. --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50. Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.