- galaxy-commits - lists.galaxyproject.org

commit/galaxy-central: jgoecks: Revert Tophat wrapper version #.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/c542aecc6086/ changeset: c542aecc6086 user: jgoecks date: 2012-04-30 17:46:43 summary: Revert Tophat wrapper version #. affected #: 1 file diff -r 62c900962bb5bd943e2717a7ba74162364b18e1e -r c542aecc608617645d31c6ce9775f31a93c10bef tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -1,4 +1,4 @@ -<tool id="tophat" name="Tophat for Illumina" version="0.5"> +<tool id="tophat" name="Tophat for Illumina" version="1.5.0"><description>Find splice junctions using RNA-seq data</description><version_command>tophat --version</version_command> 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.

1 0

commit/galaxy-central: jgoecks: Revert Tophat wrapper due to parameter incompatibility issues.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/62c900962bb5/ changeset: 62c900962bb5 user: jgoecks date: 2012-04-30 17:41:04 summary: Revert Tophat wrapper due to parameter incompatibility issues. affected #: 2 files diff -r fbe02e51b24bdb1d8861920fa984d17b3004f9bd -r 62c900962bb5bd943e2717a7ba74162364b18e1e 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' ) @@ -73,6 +73,21 @@ (options, args) = parser.parse_args() + # output version # of tool + try: + tmp = tempfile.NamedTemporaryFile().name + tmp_stdout = open( tmp, 'wb' ) + proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout ) + tmp_stdout.close() + returncode = proc.wait() + stdout = open( tmp_stdout.name, 'rb' ).readline().strip() + if stdout: + sys.stdout.write( '%s\n' % stdout ) + else: + raise Exception + except: + sys.stdout.write( 'Could not determine Tophat version\n' ) + # Color or base space space = '' if options.color_space: @@ -166,7 +181,7 @@ opts += ' --no-closure-search' if options.microexon_search: opts += ' --microexon-search' - if options.single_paired == 'paired' and options.mate_std_dev: + if options.single_paired == 'paired': 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 fbe02e51b24bdb1d8861920fa984d17b3004f9bd -r 62c900962bb5bd943e2717a7ba74162364b18e1e tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -7,111 +7,150 @@ </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 - #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 + ## Handle reference file. + #if $refGenomeSource.genomeSource == "history": + --own-file=$refGenomeSource.ownFile #else: - --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 $params.indel_search.max_deletion_length - #else: - --no-novel-indels + --indexes-path="${refGenomeSource.index.fields.path}" #end if - ## Supplying junctions parameters. - #if $params.own_junctions.use_junctions == "Yes": - #if $params.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $params.own_junctions.gene_model_ann.gene_annotation_model + ## Are reads single-end or paired? + --single-paired=$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 #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 + #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 #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> - <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> + <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="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> @@ -129,109 +168,221 @@ <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /></when></conditional> - <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> + <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="preSet" /> -  - <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"> + <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" /> +  + <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> + <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" /> + +  + <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> + +  + <conditional name="closure_search"> + <param name="use_search" type="select" label="Use Closure Search"> + <option value="No">No</option><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" /> - -  - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> + </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> +  + <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 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"> + </when> + </conditional> + </when> + <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" /> +  + <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" /> +  + <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> - <when value="No" /> - </conditional> - -  - <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> - -  - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> + <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> + +  + <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> +  + <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> - </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> - </conditional> + <option value="Yes">Yes</option> + </param> + </when> + </conditional> + </when> + </conditional></inputs><outputs> @@ -320,11 +471,11 @@ 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="settingsType" value="preSet" /> + <param name="sPaired" value="single" /> + <param name="sSettingsType" value="preSet" /><output name="junctions" file="tophat_out1j.bed" /><output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" /></test> @@ -335,13 +486,13 @@ 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="settingsType" value="preSet" /> + <param name="pSettingsType" value="preSet" /><output name="junctions" file="tophat_out2j.bed" /><output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" /></test> @@ -349,15 +500,15 @@ <test> - <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="settingsType" value="full"/> + <param name="sPaired" value="single"/> + <param name="sSettingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="anchor_length" value="8"/><param name="splice_mismatches" value="0"/> @@ -395,13 +546,13 @@ 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="settingsType" value="full"/> + <param name="pSettingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="mate_std_dev" value="20"/><param name="anchor_length" value="8"/> @@ -493,15 +644,16 @@ -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 - --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) + --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) --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.

1 0

commit/galaxy-central: greg: Fixes for some requests sent from Galaxy to a tool shed.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/fbe02e51b24b/ changeset: fbe02e51b24b user: greg date: 2012-04-30 17:00:07 summary: Fixes for some requests sent from Galaxy to a tool shed. affected #: 1 file diff -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c -r fbe02e51b24bdb1d8861920fa984d17b3004f9bd lib/galaxy/web/controllers/admin_toolshed.py --- a/lib/galaxy/web/controllers/admin_toolshed.py +++ b/lib/galaxy/web/controllers/admin_toolshed.py @@ -149,7 +149,7 @@ def browse_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%s/repository/browse_valid_repositories?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/browse_valid_repositories?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin @@ -218,14 +218,14 @@ def find_tools_in_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%s/repository/find_tools?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/find_tools?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin def find_workflows_in_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%s/repository/find_workflows?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/find_workflows?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin @@ -318,7 +318,7 @@ shed_tool_conf=shed_tool_conf ) if 'tools' in metadata_dict: # Get the tool_versions from the tool shed for each tool in the installed change set. - url = '%s/repository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ + url = '%srepository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) text = response.read() @@ -367,7 +367,7 @@ repo_info_tuple = decoded_repo_info_dict[ name ] description, repository_clone_url, changeset_revision, ctx_rev = repo_info_tuple owner = get_repository_owner( clean_repository_clone_url( repository_clone_url ) ) - url = '%s/repository/get_readme?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % ( tool_shed_url, name, owner, changeset_revision ) + url = '%srepository/get_readme?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) raw_text = response.read() response.close() 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.

1 0

commit/galaxy-central: 2 new changesets
by Bitbucket 29 Apr '12

29 Apr '12

2 new commits in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1d6324d630ed/ changeset: 1d6324d630ed user: jgoecks date: 2012-04-29 04:21:30 summary: Update Cuffdiff min-alignment-count default. affected #: 1 file diff -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 -r 1d6324d630ed3c9109d6240d7186c9f99d778005 tools/ngs_rna/cuffdiff_wrapper.xml --- a/tools/ngs_rna/cuffdiff_wrapper.xml +++ b/tools/ngs_rna/cuffdiff_wrapper.xml @@ -89,7 +89,7 @@ </conditional><param name="fdr" type="float" value="0.05" label="False Discovery Rate" help="The allowed false discovery rate."/> - <param name="min_alignment_count" type="integer" value="1000" label="Min Alignment Count" help="The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples."/> + <param name="min_alignment_count" type="integer" value="10" label="Min Alignment Count" help="The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples."/><param name="do_normalization" type="select" label="Perform quartile normalization" help="Removes top 25% of genes from FPKM denominator to improve accuracy of differential expression calls for low abundance transcripts."><option value="No">No</option><option value="Yes">Yes</option> https://bitbucket.org/galaxy/galaxy-central/changeset/dd01d42e4da3/ changeset: dd01d42e4da3 user: jgoecks date: 2012-04-30 02:34:39 summary: Merge affected #: 4 files diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c lib/galaxy/datatypes/converters/sam_to_bam.py --- /dev/null +++ b/lib/galaxy/datatypes/converters/sam_to_bam.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python +#Dan Blankenberg + +""" +A wrapper script for converting SAM to BAM, with sorting. +%prog input_filename.sam output_filename.bam +""" + +import sys, optparse, os, tempfile, subprocess, shutil + +CHUNK_SIZE = 2**20 #1mb + + +def cleanup_before_exit( tmp_dir ): + if tmp_dir and os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + (options, args) = parser.parse_args() + + assert len( args ) == 2, 'You must specify the input and output filenames' + input_filename, output_filename = args + + tmp_dir = tempfile.mkdtemp( prefix='tmp-sam_to_bam_converter-' ) + + #convert to SAM + unsorted_bam_filename = os.path.join( tmp_dir, 'unsorted.bam' ) + unsorted_stderr_filename = os.path.join( tmp_dir, 'unsorted.stderr' ) + cmd = 'samtools view -bS "%s" > "%s"' % ( input_filename, unsorted_bam_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( unsorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( unsorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + #sort sam, so indexing will not fail + sorted_stderr_filename = os.path.join( tmp_dir, 'sorted.stderr' ) + sorting_prefix = os.path.join( tmp_dir, 'sorted_bam' ) + cmd = 'samtools sort -o "%s" "%s" > "%s"' % ( unsorted_bam_filename, sorting_prefix, output_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( sorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( sorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + cleanup_before_exit( tmp_dir ) + +if __name__=="__main__": __main__() diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c lib/galaxy/datatypes/converters/sam_to_bam.xml --- a/lib/galaxy/datatypes/converters/sam_to_bam.xml +++ b/lib/galaxy/datatypes/converters/sam_to_bam.xml @@ -1,11 +1,11 @@ -<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="1.0.0"> +<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="2.0.0"> - <command>samtools view -bS $input1 > $output 2> /dev/null </command> + <command interpreter="python">sam_to_bam.py $input1 $output</command><inputs><param name="input1" type="data" format="sam" label="SAM file"/></inputs> diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c 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 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c 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></conditional> - <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" /> -  - <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" /> +  + <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" /> - -  - <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" /> + +  + <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> - -  - <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> -  - <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> + +  + <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> + +  + <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> - </conditional> - </when> - <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" /> -  - <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" /> -  - <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> - -  - <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> -  - <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> - </conditional> - </when> - </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> + </conditional></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> + <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.

1 0

commit/galaxy-central: dan: Have implicit SAM to BAM converter sort the output BAM file so that indexing will not fail.
by Bitbucket 27 Apr '12

27 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/605eb591503a/ changeset: 605eb591503a user: dan date: 2012-04-27 21:33:10 summary: Have implicit SAM to BAM converter sort the output BAM file so that indexing will not fail. affected #: 2 files diff -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 -r 605eb591503a73ed9fdc939f71c14e6c74762673 lib/galaxy/datatypes/converters/sam_to_bam.py --- /dev/null +++ b/lib/galaxy/datatypes/converters/sam_to_bam.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python +#Dan Blankenberg + +""" +A wrapper script for converting SAM to BAM, with sorting. +%prog input_filename.sam output_filename.bam +""" + +import sys, optparse, os, tempfile, subprocess, shutil + +CHUNK_SIZE = 2**20 #1mb + + +def cleanup_before_exit( tmp_dir ): + if tmp_dir and os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + (options, args) = parser.parse_args() + + assert len( args ) == 2, 'You must specify the input and output filenames' + input_filename, output_filename = args + + tmp_dir = tempfile.mkdtemp( prefix='tmp-sam_to_bam_converter-' ) + + #convert to SAM + unsorted_bam_filename = os.path.join( tmp_dir, 'unsorted.bam' ) + unsorted_stderr_filename = os.path.join( tmp_dir, 'unsorted.stderr' ) + cmd = 'samtools view -bS "%s" > "%s"' % ( input_filename, unsorted_bam_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( unsorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( unsorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + #sort sam, so indexing will not fail + sorted_stderr_filename = os.path.join( tmp_dir, 'sorted.stderr' ) + sorting_prefix = os.path.join( tmp_dir, 'sorted_bam' ) + cmd = 'samtools sort -o "%s" "%s" > "%s"' % ( unsorted_bam_filename, sorting_prefix, output_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( sorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( sorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + cleanup_before_exit( tmp_dir ) + +if __name__=="__main__": __main__() diff -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 -r 605eb591503a73ed9fdc939f71c14e6c74762673 lib/galaxy/datatypes/converters/sam_to_bam.xml --- a/lib/galaxy/datatypes/converters/sam_to_bam.xml +++ b/lib/galaxy/datatypes/converters/sam_to_bam.xml @@ -1,11 +1,11 @@ -<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="1.0.0"> +<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="2.0.0"> - <command>samtools view -bS $input1 > $output 2> /dev/null </command> + <command interpreter="python">sam_to_bam.py $input1 $output</command><inputs><param name="input1" type="data" format="sam" label="SAM file"/></inputs> 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.

1 0

commit/galaxy-central: jgoecks: More cleaning of Tophat wrapper.
by Bitbucket 27 Apr '12

27 Apr '12

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></conditional> - <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" /> -  - <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" /> +  + <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" /> - -  - <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" /> + +  + <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> - -  - <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> -  - <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> + +  + <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> + +  + <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> - </conditional> - </when> - <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" /> -  - <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" /> -  - <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> - -  - <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> -  - <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> - </conditional> - </when> - </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> + </conditional></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> + <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.

1 0

commit/galaxy-central: jgoecks: Skeleton wrapper for Bowtie2.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/51fccbc2e9bc/ changeset: 51fccbc2e9bc user: jgoecks date: 2012-04-26 21:28:17 summary: Skeleton wrapper for Bowtie2. affected #: 5 files diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tool-data/bowtie2_indices.loc.sample --- /dev/null +++ b/tool-data/bowtie2_indices.loc.sample @@ -0,0 +1,37 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Bowtie2 indexed sequences data files. You will +#need to create these data files and then create a bowtie_indices.loc +#file similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bowtie2_indices.loc +#file has this format (longer white space characters are TAB characters): +# +#<unique_build_id><dbkey><display_name><file_base_path> +# +#So, for example, if you had hg18 indexed stored in +#/depot/data2/galaxy/bowtie2/hg18/, +#then the bowtie2_indices.loc entry would look like this: +# +#hg18 hg18 hg18 /depot/data2/galaxy/bowtie2/hg18/hg18 +# +#and your /depot/data2/galaxy/bowtie2/hg18/ directory +#would contain hg18.*.ebwt files: +# +#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 hg18.1.ebwt +#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 hg18.2.ebwt +#-rw-r--r-- 1 james universe 269808 2005-09-13 10:12 hg18.3.ebwt +#...etc... +# +#Your bowtie2_indices.loc file should include an entry per line for each +#index set you have stored. The "file" in the path does not actually +#exist, but it is the prefix for the actual index files. For example: +# +#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/bowtie2/hg18/hg18canon +#hg18full hg18 hg18 Full /depot/data2/galaxy/bowtie2/hg18/hg18full +#/orig/path/hg19 hg19 hg19 /depot/data2/galaxy/bowtie2/hg19/hg19 +#...etc... +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tool_conf.xml.sample --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -336,6 +336,7 @@ <tool file="sr_mapping/lastz_wrapper.xml" /><tool file="sr_mapping/lastz_paired_reads_wrapper.xml" /><tool file="sr_mapping/bowtie_wrapper.xml" /> + <tool file="sr_mapping/bowtie2_wrapper.xml" /><tool file="sr_mapping/bowtie_color_wrapper.xml" /><tool file="sr_mapping/bwa_wrapper.xml" /><tool file="sr_mapping/bwa_color_wrapper.xml" /> diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample +++ b/tool_data_table_conf.xml.sample @@ -25,6 +25,11 @@ <columns>value, dbkey, name, path</columns><file path="tool-data/bowtie_indices.loc" /></table> +  + <table name="bowtie2_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/bowtie2_indices.loc" /> + </table><table name="bowtie_indexes_color" comment_char="#"><columns>value, dbkey, name, path</columns> diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tools/sr_mapping/bowtie2_wrapper.py --- /dev/null +++ b/tools/sr_mapping/bowtie2_wrapper.py @@ -0,0 +1,115 @@ +#!/usr/bin/env python + +import optparse, os, shutil, subprocess, sys, tempfile, fileinput + +def stop_err( msg ): + sys.stderr.write( "%s\n" % msg ) + sys.exit() + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' ) + parser.add_option( '', '--own-file', dest='own_file', help='' ) + parser.add_option( '-D', '--indexes-path', dest='index_path', help='Indexes directory; location of .ebwt and .fa files.' ) + + # Wrapper options. + parser.add_option( '-O', '--output', dest='output' ) + parser.add_option( '-1', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' ) + parser.add_option( '-2', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' ) + parser.add_option( '', '--single-paired', dest='single_paired', help='' ) + parser.add_option( '', '--settings', dest='settings', help='' ) + + (options, args) = parser.parse_args() + + # Creat bowtie index if necessary. + tmp_index_dir = tempfile.mkdtemp() + if options.own_file: + index_path = os.path.join( tmp_index_dir, '.'.join( os.path.split( options.own_file )[1].split( '.' )[:-1] ) ) + try: + os.link( options.own_file, index_path + '.fa' ) + except: + # Bowtie prefers (but doesn't require) fasta file to be in same directory, with .fa extension + pass + cmd_index = 'bowtie2-build -f %s %s' % ( options.own_file, index_path ) + try: + tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name + tmp_stderr = open( tmp, 'wb' ) + proc = subprocess.Popen( args=cmd_index, shell=True, cwd=tmp_index_dir, stderr=tmp_stderr.fileno() ) + returncode = proc.wait() + tmp_stderr.close() + # get stderr, allowing for case where it's very large + tmp_stderr = open( tmp, 'rb' ) + stderr = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stderr.close() + if returncode != 0: + raise Exception, stderr + except Exception, e: + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + stop_err( 'Error indexing reference sequence\n' + str( e ) ) + else: + index_path = options.index_path + + # Build bowtie command. + cmd = 'bowtie2 %s -x %s %s -S %s' + + # Set up reads. + if options.single_paired == 'paired': + reads = " -1 %s -2 %s" % ( options.input1, options.input2 ) + else: + reads = " -U %s" % ( options.input1 ) + + # Set up options. + opts = '-p %s' % ( options.num_threads ) + if options.settings == 'preSet': + pass + else: + pass + + # Final command: + cmd = cmd % ( opts, index_path, reads, options.output ) + print cmd + + # Run + try: + tmp_out = tempfile.NamedTemporaryFile().name + tmp_stdout = open( tmp_out, 'wb' ) + tmp_err = tempfile.NamedTemporaryFile().name + tmp_stderr = open( tmp_err, 'wb' ) + proc = subprocess.Popen( args=cmd, shell=True, cwd=".", stdout=tmp_stdout, stderr=tmp_stderr ) + returncode = proc.wait() + tmp_stderr.close() + # get stderr, allowing for case where it's very large + tmp_stderr = open( tmp_err, 'rb' ) + stderr = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stdout.close() + tmp_stderr.close() + if returncode != 0: + raise Exception, stderr + + # TODO: look for errors in program output. + except Exception, e: + stop_err( 'Error in bowtie2:\n' + str( e ) ) + + # Clean up temp dirs + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + +if __name__=="__main__": __main__() diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tools/sr_mapping/bowtie2_wrapper.xml --- /dev/null +++ b/tools/sr_mapping/bowtie2_wrapper.xml @@ -0,0 +1,109 @@ +<tool id="bowtie2" name="Bowtie2" version="0.1"> +  + <description>is a short-read mapper</description> + <version_command>bowtie2 --version</version_command> + <requirements> + <requirement type="package">bowtie2</requirement> + </requirements> + <command interpreter="python"> + bowtie2_wrapper.py + + ## Change this to accommodate the number of threads you have available. + --num-threads="4" + + ## Outputs. + --output=$output + + ## 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 + #end if + + ## Set params. + --settings=$params.settingsType + </command> + <inputs> + <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="FASTQ file" 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="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastqsanger" name="input2" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> +  + </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> + <option value="history">Use one from the history</option> + </param> + <when value="indexed"> + <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team"> + <options from_data_table="bowtie2_indexes"> + <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="history"> + <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /> + </when> + </conditional> + <conditional name="params"> + <param name="settingsType" type="select" label="Bowtie settings to use" help="You can use the default settings or set custom values for any of Bowtie's parameters."> + <option value="preSet">Use Defaults</option> + <option value="full">Full parameter list</option> + </param> + <when value="preSet" /> +  + <when value="full"> + </when> + </conditional> + </inputs> + + <outputs> + <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads"> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="bowtie2_indexes" 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> + </tests> + + <help> + </help> +</tool> 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.

1 0

commit/galaxy-central: jgoecks: Remove version code from tophat wrappers as this is now handled by <version> tag.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1c8eb226af94/ changeset: 1c8eb226af94 user: jgoecks date: 2012-04-26 20:25:01 summary: Remove version code from tophat wrappers as this is now handled by <version> tag. affected #: 2 files diff -r c16adb4630e58fe4001e488367e27e911d7ec0cb -r 1c8eb226af94b29ef8484c4fbed557282170259e tools/ngs_rna/tophat2_wrapper.py --- a/tools/ngs_rna/tophat2_wrapper.py +++ b/tools/ngs_rna/tophat2_wrapper.py @@ -80,21 +80,6 @@ (options, args) = parser.parse_args() - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = open( tmp_stdout.name, 'rb' ).readline().strip() - if stdout: - sys.stdout.write( '%s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Tophat version\n' ) - # Color or base space space = '' if options.color_space: diff -r c16adb4630e58fe4001e488367e27e911d7ec0cb -r 1c8eb226af94b29ef8484c4fbed557282170259e tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -73,21 +73,6 @@ (options, args) = parser.parse_args() - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = open( tmp_stdout.name, 'rb' ).readline().strip() - if stdout: - sys.stdout.write( '%s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Tophat version\n' ) - # Color or base space space = '' if options.color_space: 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.

1 0

commit/galaxy-central: jgoecks: Fix version references in tophat2 wrapper.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/c16adb4630e5/ changeset: c16adb4630e5 user: jgoecks date: 2012-04-26 19:59:03 summary: Fix version references in tophat2 wrapper. affected #: 1 file diff -r 9884af7d49189f1af3f8ae60931064d2abcc62cc -r c16adb4630e58fe4001e488367e27e911d7ec0cb tools/ngs_rna/tophat2_wrapper.xml --- a/tools/ngs_rna/tophat2_wrapper.xml +++ b/tools/ngs_rna/tophat2_wrapper.xml @@ -1,9 +1,9 @@ <tool id="tophat2" name="Tophat2" version="0.5"><description>Gapped-read mapper for RNA-seq data</description> - <version_command>tophat --version</version_command> + <version_command>tophat2 --version</version_command><requirements> - <requirement type="package">tophat</requirement> + <requirement type="package">tophat2</requirement></requirements><command interpreter="python"> tophat2_wrapper.py 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.

1 0

commit/galaxy-central: jgoecks: Make history export work for optional data inputs.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/9884af7d4918/ changeset: 9884af7d4918 user: jgoecks date: 2012-04-26 19:32:04 summary: Make history export work for optional data inputs. affected #: 1 file diff -r 0a0b01a980eac2f4c98d317bbde3ff572aca13e9 -r 9884af7d49189f1af3f8ae60931064d2abcc62cc lib/galaxy/tools/imp_exp/__init__.py --- a/lib/galaxy/tools/imp_exp/__init__.py +++ b/lib/galaxy/tools/imp_exp/__init__.py @@ -415,8 +415,13 @@ params_dict[ name ] = value job_attrs[ 'params' ] = params_dict - # Get input, output datasets. - input_datasets = [ assoc.dataset.hid for assoc in job.input_datasets ] + # -- Get input, output datasets. -- + + input_datasets = [] + for assoc in job.input_datasets: + # Optional data inputs will not have a dataset. + if assoc.dataset: + input_datasets.append( assoc.dataset.hid ) job_attrs[ 'input_datasets' ] = input_datasets output_datasets = [ assoc.dataset.hid for assoc in job.output_datasets ] job_attrs[ 'output_datasets' ] = output_datasets 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.

1 0