1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/6af88237056f/ changeset: 6af88237056f user: jgoecks date: 2012-04-20 23:08:55 summary: Basic support for Tophat2. affected #: 4 files diff -r 89786a8d42c1fbbfa84bfcbab07702a942d57d1b -r 6af88237056f0d4c7ae4c3dd5af647cde4830710 test-data/tophat_out2j.bed --- a/test-data/tophat_out2j.bed +++ b/test-data/tophat_out2j.bed @@ -1,3 +1,3 @@ track name=junctions description="TopHat junctions" -test_chromosome 179 400 JUNC00000001 38 + 179 400 255,0,0 2 71,50 0,171 -test_chromosome 350 549 JUNC00000002 30 + 350 549 255,0,0 2 50,49 0,150 +test_chromosome 179 400 JUNC00000001 45 + 179 400 255,0,0 2 71,50 0,171 +test_chromosome 350 550 JUNC00000002 38 + 350 550 255,0,0 2 50,50 0,150 diff -r 89786a8d42c1fbbfa84bfcbab07702a942d57d1b -r 6af88237056f0d4c7ae4c3dd5af647cde4830710 test-data/tophat_out4j.bed --- a/test-data/tophat_out4j.bed +++ b/test-data/tophat_out4j.bed @@ -1,3 +1,3 @@ track name=junctions description="TopHat junctions" -test_chromosome 179 400 JUNC00000001 38 + 179 400 255,0,0 2 71,50 0,171 -test_chromosome 350 549 JUNC00000002 30 + 350 549 255,0,0 2 50,49 0,150 +test_chromosome 179 400 JUNC00000001 45 + 179 400 255,0,0 2 71,50 0,171 +test_chromosome 350 550 JUNC00000002 38 + 350 550 255,0,0 2 50,50 0,150 diff -r 89786a8d42c1fbbfa84bfcbab07702a942d57d1b -r 6af88237056f0d4c7ae4c3dd5af647cde4830710 tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -28,7 +28,6 @@ parser.add_option( '-I', '--max-intron-length', dest='max_intron_length', help='The maximum intron length. 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.' ) parser.add_option( '-g', '--max_multihits', dest='max_multihits', help='Maximum number of alignments to be allowed' ) - parser.add_option( '', '--initial-read-mismatches', dest='initial_read_mismatches', help='Number of mismatches allowed in the initial read mapping' ) parser.add_option( '', '--seg-mismatches', dest='seg_mismatches', help='Number of mismatches allowed in each segment alignment for reads mapped independently' ) parser.add_option( '', '--seg-length', dest='seg_length', help='Minimum length of read segments' ) parser.add_option( '', '--library-type', dest='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.' ) @@ -53,15 +52,10 @@ 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( '', '--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' ) @@ -175,16 +169,10 @@ opts += ' --coverage-search --min-coverage-intron %s --max-coverage-intron %s' % ( options.min_coverage_intron, options.max_coverage_intron ) else: opts += ' --no-coverage-search' - if options.closure_search: - opts += ' --closure-search --min-closure-exon %s --min-closure-intron %s --max-closure-intron %s' % ( options.min_closure_exon, options.min_closure_intron, options.max_closure_intron ) - else: - opts += ' --no-closure-search' if options.microexon_search: opts += ' --microexon-search' 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 ) if options.seg_mismatches: opts += ' --segment-mismatches %d' % int( options.seg_mismatches ) if options.seg_length: diff -r 89786a8d42c1fbbfa84bfcbab07702a942d57d1b -r 6af88237056f0d4c7ae4c3dd5af647cde4830710 tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -1,5 +1,5 @@ <tool id="tophat" name="Tophat for Illumina" version="0.5"> - <!-- Wrapper compatible with Tophat versions 1.3.0 to 1.4.1 --> + <!-- Wrapper compatible with Tophat versions 1.3.0 to 2.0.0 --><description>Find splice junctions using RNA-seq data</description><version_command>tophat --version</version_command><requirements> @@ -38,7 +38,6 @@ -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 @@ -66,14 +65,6 @@ #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 @@ -99,7 +90,6 @@ -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 @@ -127,14 +117,6 @@ #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 @@ -206,7 +188,6 @@ <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" /> @@ -245,19 +226,6 @@ <when value="No" /></conditional><!-- /own_junctions --> - <!-- Closure search. --> - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional><!-- Coverage search. --><conditional name="coverage_search"><param name="use_search" type="select" label="Use Coverage Search"> @@ -312,7 +280,6 @@ <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /><param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /><param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /><param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /><param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /><!-- Options for supplying own junctions. --> @@ -350,19 +317,6 @@ <when value="No" /></conditional><!-- /own_junctions --> - <!-- Closure search. --> - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional><!-- Coverage search. --><conditional name="coverage_search"><param name="use_search" type="select" label="Use Coverage Search"> @@ -500,7 +454,7 @@ <test><!-- Tophat commands: bowtie-build -f test-data/tophat_in1.fasta tophat_in1 - tophat -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +closure-search +min-closure-exon 50 +min-closure-intron 50 +max-closure-intro 5000 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger + tophat -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger Replace the + with double-dash Rename the files in tmp_dir appropriately --> @@ -527,10 +481,6 @@ <param name="use_juncs" value="No" /><param name="no_novel_juncs" value="No" /><param name="use_search" value="Yes" /> - <param name="min_closure_exon" value="50" /> - <param name="min_closure_intron" value="50" /> - <param name="max_closure_intron" value="5000" /> - <param name="use_search" value="Yes" /><param name="min_coverage_intron" value="50" /><param name="max_coverage_intron" value="20000" /><param name="microexon_search" value="Yes" /> @@ -643,17 +593,11 @@ -G/--GTF [GTF 2.2 file] Supply TopHat with a list of gene model annotations. 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. -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) --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.