April 2011 - galaxy-commits - lists.galaxyproject.org

commit/galaxy-central: fubar: an errant == in tool_conf.xml.sample fixed
by Bitbucket 28 Apr '11

28 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/f53f589efb1e/ changeset: r5467:f53f589efb1e user: fubar date: 2011-04-28 15:33:19 summary: an errant == in tool_conf.xml.sample fixed affected #: 1 file (1 byte) --- a/tool_conf.xml.sample Thu Apr 28 09:18:13 2011 -0400 +++ b/tool_conf.xml.sample Thu Apr 28 09:33:19 2011 -0400 @@ -244,7 +244,7 @@ <tool file="picard/rgPicardASMetrics.xml" /><tool file="picard/rgPicardGCBiasMetrics.xml" /><tool file="picard/rgPicardInsertSize.xml" /> - <label text=="bam/sam Cleaning" id="picard-tools" /> + <label text="bam/sam Cleaning" id="picard-tools" /><tool file="picard/picard_AddOrReplaceReadGroups.xml" /><tool file="picard/picard_ReorderSam.xml" /><tool file="picard/picard_ReplaceSamHeader.xml" /> 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 28 Apr '11

28 Apr '11

2 new changesets in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/725deb060e8e/ changeset: r5465:725deb060e8e user: fubar date: 2011-04-28 15:17:50 summary: missing slash in tool_conf.xml.sample fixed affected #: 1 file (2 bytes) --- a/tool_conf.xml.sample Wed Apr 27 17:06:14 2011 -0400 +++ b/tool_conf.xml.sample Thu Apr 28 09:17:50 2011 -0400 @@ -244,7 +244,7 @@ <tool file="picard/rgPicardASMetrics.xml" /><tool file="picard/rgPicardGCBiasMetrics.xml" /><tool file="picard/rgPicardInsertSize.xml" /> - <label text=="bam/sam Cleaning" id="picard-tools"> + <label text=="bam/sam Cleaning" id="picard-tools" /><tool file="picard/picard_AddOrReplaceReadGroups.xml" /><tool file="picard/picard_ReorderSam.xml" /><tool file="picard/picard_ReplaceSamHeader.xml" /> http://bitbucket.org/galaxy/galaxy-central/changeset/c28dc46ede98/ changeset: r5466:c28dc46ede98 user: fubar date: 2011-04-28 15:18:13 summary: branch merge affected #: 3 files (2.1 KB) --- a/datatypes_conf.xml.sample Thu Apr 28 09:17:50 2011 -0400 +++ b/datatypes_conf.xml.sample Thu Apr 28 09:18:13 2011 -0400 @@ -66,8 +66,7 @@ </datatype><datatype extension="gff" type="galaxy.datatypes.interval:Gff" display_in_upload="true"><converter file="gff_to_bed_converter.xml" target_datatype="bed"/> - <converter file="gff_to_bgzip_converter.xml" target_datatype="bgzip"/> - <converter file="gff_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/> + <converter file="gff_to_interval_index_converter.xml" target_datatype="interval_index"/><converter file="gff_to_summary_tree_converter.xml" target_datatype="summary_tree"/><display file="ensembl/ensembl_gff.xml" inherit="True"/> @@ -75,10 +74,7 @@ <datatype extension="gff3" type="galaxy.datatypes.interval:Gff3" display_in_upload="true"/><datatype extension="gif" type="galaxy.datatypes.images:Image" mimetype="image/gif"/><datatype extension="gmaj.zip" type="galaxy.datatypes.images:Gmaj" mimetype="application/zip"/> - <datatype extension="gtf" type="galaxy.datatypes.interval:Gtf" display_in_upload="true"> - <converter file="gff_to_bgzip_converter.xml" target_datatype="bgzip"/> - <converter file="gff_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/> - </datatype> + <datatype extension="gtf" type="galaxy.datatypes.interval:Gtf" display_in_upload="true"/><datatype extension="html" type="galaxy.datatypes.images:Html" mimetype="text/html"/><datatype extension="interval" type="galaxy.datatypes.interval:Interval" display_in_upload="true"><converter file="interval_to_bed_converter.xml" target_datatype="bed"/> --- a/lib/galaxy/datatypes/interval.py Thu Apr 28 09:17:50 2011 -0400 +++ b/lib/galaxy/datatypes/interval.py Thu Apr 28 09:18:13 2011 -0400 @@ -772,7 +772,7 @@ return False def get_track_type( self ): - return "FeatureTrack", {"data": "tabix", "index": "summary_tree"} + return "FeatureTrack", {"data": "interval_index", "index": "summary_tree"} class Gff3( Gff ): --- a/lib/galaxy/visualization/tracks/data_providers.py Thu Apr 28 09:17:50 2011 -0400 +++ b/lib/galaxy/visualization/tracks/data_providers.py Thu Apr 28 09:18:13 2011 -0400 @@ -360,13 +360,7 @@ f = open( self.original_dataset.file_name ) return f, BigWigFile(file=f) -class TabixDataProvider( TracksDataProvider ): - """ - Tabix index data provider for the Galaxy track browser. - """ - - col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } - +class FilterableMixin: def get_filters( self ): """ Returns a dataset's filters. """ @@ -422,12 +416,19 @@ filters = [ { 'name': 'Score', 'type': 'int', 'index': filter_col } ] return filters + +class TabixDataProvider( TracksDataProvider, FilterableMixin ): + """ + Tabix index data provider for the Galaxy track browser. + """ + + col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } def get_iterator( self, chrom, start, end ): - if end >= 2<<29: + start, end = int(start), int(end) + if end >= (2<<29): end = (2<<29 - 1) # Tabix-enforced maximum - start, end = int(start), int(end) - + bgzip_fname = self.dependencies['bgzip'].file_name # if os.path.getsize(self.converted_dataset.file_name) == 0: @@ -447,24 +448,64 @@ iterator = self.get_iterator( chrom, start, end ) return self.process_data(iterator, **kwargs) -class GffDataProvider( TabixDataProvider ): - # FIXME: Doesn't implement write_data_to_file - def process_data( self, iterator, **kwargs ): +class GffDataProvider( TracksDataProvider, FilterableMixin ): + col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } + + def write_data_to_file( self, chrom, start, end, filename ): + source = open( self.original_dataset.file_name ) + index = Indexes( self.converted_dataset.file_name ) + out = open( filename, 'w' ) + for start, end, offset in index.find(chrom, start, end): + source.seek( offset ) + + reader = GFFReaderWrapper( source, fix_strand=True ) + feature = reader.next() + for interval in feature.intervals: + out.write(interval.raw_line + '\n') + out.close() + + def get_data( self, chrom, start, end, **kwargs ): + start, end = int(start), int(end) + source = open( self.original_dataset.file_name ) + index = Indexes( self.converted_dataset.file_name ) + results = [] count = 0 - rval = [] message = None - for feature in GFFReaderWrapper( iterator, fix_strand=True ): + + # If chrom is not found in indexes, try removing the first three + # characters (e.g. 'chr') and see if that works. This enables the + # provider to handle chrome names defined as chrXXX and as XXX. + chrom = str(chrom) + if chrom not in index.indexes and chrom[3:] in index.indexes: + chrom = chrom[3:] + + # + # Build data to return. Payload format is: + # [ <guid/offset>, <start>, <end>, <name>, <score>, <strand>, <thick_start>, + # <thick_end>, <blocks> ] + # + # First three entries are mandatory, others are optional. + # + filter_cols = from_json_string( kwargs.get( "filter_cols", "[]" ) ) + no_detail = ( "no_detail" in kwargs ) + for start, end, offset in index.find(chrom, start, end): if count >= MAX_VALS: message = ERROR_MAX_VALS % "features" break count += 1 + source.seek( offset ) + # TODO: can we use column metadata to fill out payload? + # TODO: use function to set payload data - payload = package_gff_feature( feature ) - hashed = hash("\t".join(feature.fields)) - payload.insert( 0, hashed ) - rval.append( payload ) - - return { 'data': rval, 'message': message } + # GFF dataset. + reader = GFFReaderWrapper( source, fix_strand=True ) + feature = reader.next() + payload = package_gff_feature( feature, no_detail, filter_cols ) + payload.insert( 0, offset ) + + results.append( payload ) + + return { 'data': results, 'message': message } class BedDataProvider( TabixDataProvider ): """ @@ -611,7 +652,8 @@ # type. First key is converted dataset type; if result is another dict, second key # is original dataset type. TODO: This needs to be more flexible. dataset_type_name_to_data_provider = { - "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, Gff: GffDataProvider, Gtf: GffDataProvider, "default" : TabixDataProvider }, + "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, "default" : TabixDataProvider }, + "interval_index": { Gff: GffDataProvider, Gtf: GffDataProvider }, "bai": BamDataProvider, "summary_tree": SummaryTreeDataProvider, "bigwig": BigWigDataProvider, 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: kanwei: trackster: Restore interval_index as Gff indexer for now due to sorting issues
by Bitbucket 27 Apr '11

27 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/760d34e6c692/ changeset: r5464:760d34e6c692 user: kanwei date: 2011-04-28 01:08:31 summary: trackster: Restore interval_index as Gff indexer for now due to sorting issues affected #: 3 files (2.1 KB) --- a/datatypes_conf.xml.sample Wed Apr 27 17:33:08 2011 -0400 +++ b/datatypes_conf.xml.sample Wed Apr 27 19:08:31 2011 -0400 @@ -66,8 +66,7 @@ </datatype><datatype extension="gff" type="galaxy.datatypes.interval:Gff" display_in_upload="true"><converter file="gff_to_bed_converter.xml" target_datatype="bed"/> - <converter file="gff_to_bgzip_converter.xml" target_datatype="bgzip"/> - <converter file="gff_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/> + <converter file="gff_to_interval_index_converter.xml" target_datatype="interval_index"/><converter file="gff_to_summary_tree_converter.xml" target_datatype="summary_tree"/><display file="ensembl/ensembl_gff.xml" inherit="True"/> @@ -75,10 +74,7 @@ <datatype extension="gff3" type="galaxy.datatypes.interval:Gff3" display_in_upload="true"/><datatype extension="gif" type="galaxy.datatypes.images:Image" mimetype="image/gif"/><datatype extension="gmaj.zip" type="galaxy.datatypes.images:Gmaj" mimetype="application/zip"/> - <datatype extension="gtf" type="galaxy.datatypes.interval:Gtf" display_in_upload="true"> - <converter file="gff_to_bgzip_converter.xml" target_datatype="bgzip"/> - <converter file="gff_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/> - </datatype> + <datatype extension="gtf" type="galaxy.datatypes.interval:Gtf" display_in_upload="true"/><datatype extension="html" type="galaxy.datatypes.images:Html" mimetype="text/html"/><datatype extension="interval" type="galaxy.datatypes.interval:Interval" display_in_upload="true"><converter file="interval_to_bed_converter.xml" target_datatype="bed"/> --- a/lib/galaxy/datatypes/interval.py Wed Apr 27 17:33:08 2011 -0400 +++ b/lib/galaxy/datatypes/interval.py Wed Apr 27 19:08:31 2011 -0400 @@ -772,7 +772,7 @@ return False def get_track_type( self ): - return "FeatureTrack", {"data": "tabix", "index": "summary_tree"} + return "FeatureTrack", {"data": "interval_index", "index": "summary_tree"} class Gff3( Gff ): --- a/lib/galaxy/visualization/tracks/data_providers.py Wed Apr 27 17:33:08 2011 -0400 +++ b/lib/galaxy/visualization/tracks/data_providers.py Wed Apr 27 19:08:31 2011 -0400 @@ -360,13 +360,7 @@ f = open( self.original_dataset.file_name ) return f, BigWigFile(file=f) -class TabixDataProvider( TracksDataProvider ): - """ - Tabix index data provider for the Galaxy track browser. - """ - - col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } - +class FilterableMixin: def get_filters( self ): """ Returns a dataset's filters. """ @@ -422,6 +416,13 @@ filters = [ { 'name': 'Score', 'type': 'int', 'index': filter_col } ] return filters + +class TabixDataProvider( TracksDataProvider, FilterableMixin ): + """ + Tabix index data provider for the Galaxy track browser. + """ + + col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } def get_iterator( self, chrom, start, end ): start, end = int(start), int(end) @@ -447,24 +448,64 @@ iterator = self.get_iterator( chrom, start, end ) return self.process_data(iterator, **kwargs) -class GffDataProvider( TabixDataProvider ): - # FIXME: Doesn't implement write_data_to_file - def process_data( self, iterator, **kwargs ): +class GffDataProvider( TracksDataProvider, FilterableMixin ): + col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } + + def write_data_to_file( self, chrom, start, end, filename ): + source = open( self.original_dataset.file_name ) + index = Indexes( self.converted_dataset.file_name ) + out = open( filename, 'w' ) + for start, end, offset in index.find(chrom, start, end): + source.seek( offset ) + + reader = GFFReaderWrapper( source, fix_strand=True ) + feature = reader.next() + for interval in feature.intervals: + out.write(interval.raw_line + '\n') + out.close() + + def get_data( self, chrom, start, end, **kwargs ): + start, end = int(start), int(end) + source = open( self.original_dataset.file_name ) + index = Indexes( self.converted_dataset.file_name ) + results = [] count = 0 - rval = [] message = None - for feature in GFFReaderWrapper( iterator, fix_strand=True ): + + # If chrom is not found in indexes, try removing the first three + # characters (e.g. 'chr') and see if that works. This enables the + # provider to handle chrome names defined as chrXXX and as XXX. + chrom = str(chrom) + if chrom not in index.indexes and chrom[3:] in index.indexes: + chrom = chrom[3:] + + # + # Build data to return. Payload format is: + # [ <guid/offset>, <start>, <end>, <name>, <score>, <strand>, <thick_start>, + # <thick_end>, <blocks> ] + # + # First three entries are mandatory, others are optional. + # + filter_cols = from_json_string( kwargs.get( "filter_cols", "[]" ) ) + no_detail = ( "no_detail" in kwargs ) + for start, end, offset in index.find(chrom, start, end): if count >= MAX_VALS: message = ERROR_MAX_VALS % "features" break count += 1 + source.seek( offset ) + # TODO: can we use column metadata to fill out payload? + # TODO: use function to set payload data - payload = package_gff_feature( feature ) - hashed = hash("\t".join(feature.fields)) - payload.insert( 0, hashed ) - rval.append( payload ) - - return { 'data': rval, 'message': message } + # GFF dataset. + reader = GFFReaderWrapper( source, fix_strand=True ) + feature = reader.next() + payload = package_gff_feature( feature, no_detail, filter_cols ) + payload.insert( 0, offset ) + + results.append( payload ) + + return { 'data': results, 'message': message } class BedDataProvider( TabixDataProvider ): """ @@ -611,7 +652,8 @@ # type. First key is converted dataset type; if result is another dict, second key # is original dataset type. TODO: This needs to be more flexible. dataset_type_name_to_data_provider = { - "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, Gff: GffDataProvider, Gtf: GffDataProvider, "default" : TabixDataProvider }, + "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, "default" : TabixDataProvider }, + "interval_index": { Gff: GffDataProvider, Gtf: GffDataProvider }, "bai": BamDataProvider, "summary_tree": SummaryTreeDataProvider, "bigwig": BigWigDataProvider, 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: kanwei: trackster: Fix incorrect "end" calculation
by Bitbucket 27 Apr '11

27 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/cacc1f179af3/ changeset: r5463:cacc1f179af3 user: kanwei date: 2011-04-27 23:33:08 summary: trackster: Fix incorrect "end" calculation affected #: 1 file (14 bytes) --- a/lib/galaxy/visualization/tracks/data_providers.py Wed Apr 27 17:06:14 2011 -0400 +++ b/lib/galaxy/visualization/tracks/data_providers.py Wed Apr 27 17:33:08 2011 -0400 @@ -424,10 +424,10 @@ return filters def get_iterator( self, chrom, start, end ): - if end >= 2<<29: + start, end = int(start), int(end) + if end >= (2<<29): end = (2<<29 - 1) # Tabix-enforced maximum - start, end = int(start), int(end) - + bgzip_fname = self.dependencies['bgzip'].file_name # if os.path.getsize(self.converted_dataset.file_name) == 0: 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: fubar: uncommented new tools in tool_conf.xml.sample so buildbot can find them and explanation when insertsizemetrics fails
by Bitbucket 27 Apr '11

27 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/0d4ece99a476/ changeset: r5462:0d4ece99a476 user: fubar date: 2011-04-27 23:06:14 summary: uncommented new tools in tool_conf.xml.sample so buildbot can find them and explanation when insertsizemetrics fails affected #: 2 files (556 bytes) --- a/tool_conf.xml.sample Wed Apr 27 15:41:25 2011 -0400 +++ b/tool_conf.xml.sample Wed Apr 27 17:06:14 2011 -0400 @@ -236,44 +236,57 @@ <tool file="ncbi_blast_plus/ncbi_tblastx_wrapper.xml" /><tool file="ncbi_blast_plus/blastxml_to_tabular.xml" /></section> - <section name="NGS: QC and manipulation" id="cshl_library_information"> - <label text="Illumina fastq" id="illumina" /> - <tool file="fastq/fastq_groomer.xml" /> - <tool file="fastq/fastq_paired_end_splitter.xml" /> - <tool file="fastq/fastq_paired_end_joiner.xml" /> - <tool file="fastq/fastq_stats.xml" /> - <label text="Roche-454 data" id="454" /> - <tool file="metag_tools/short_reads_figure_score.xml" /> - <tool file="metag_tools/short_reads_trim_seq.xml" /> - <tool file="fastq/fastq_combiner.xml" /> - <label text="AB-SOLiD data" id="solid" /> - <tool file="next_gen_conversion/solid2fastq.xml" /> - <tool file="solid_tools/solid_qual_stats.xml" /> - <tool file="solid_tools/solid_qual_boxplot.xml" /> - <label text="Generic FASTQ manipulation" id="generic_fastq" /> - <tool file="fastq/fastq_filter.xml" /> - <tool file="fastq/fastq_trimmer.xml" /> - <tool file="fastq/fastq_trimmer_by_quality.xml" /> - <tool file="fastq/fastq_masker_by_quality.xml" /> - <tool file="fastq/fastq_manipulation.xml" /> - <tool file="fastq/fastq_to_fasta.xml" /> - <tool file="fastq/fastq_to_tabular.xml" /> - <tool file="fastq/tabular_to_fastq.xml" /> - <label text="FASTX-Toolkit for FASTQ data" id="fastx_toolkit" /> - <tool file="fastx_toolkit/fastq_quality_converter.xml" /> - <tool file="fastx_toolkit/fastx_quality_statistics.xml" /> - <tool file="fastx_toolkit/fastq_quality_boxplot.xml" /> - <tool file="fastx_toolkit/fastx_nucleotides_distribution.xml" /> - <tool file="fastx_toolkit/fastq_to_fasta.xml" /> - <tool file="fastx_toolkit/fastq_quality_filter.xml" /> - <tool file="fastx_toolkit/fastq_to_fasta.xml" /> - <tool file="fastx_toolkit/fastx_artifacts_filter.xml" /> - <tool file="fastx_toolkit/fastx_barcode_splitter.xml" /> - <tool file="fastx_toolkit/fastx_clipper.xml" /> - <tool file="fastx_toolkit/fastx_collapser.xml" /> - <tool file="fastx_toolkit/fastx_renamer.xml" /> - <tool file="fastx_toolkit/fastx_reverse_complement.xml" /> - <tool file="fastx_toolkit/fastx_trimmer.xml" /> + <section name="NGS: QC and manipulation" id="NGS_QC"> + <label text="FastQC: fastq/sam/bam" id="fastqcsambam" /> + <tool file="rgenetics/rgFastQC.xml" /> + <label text="QC/Metrics for sam/bam" id="qcsambam"/> + <tool file="picard/picard_BamIndexStats.xml" /> + <tool file="picard/rgPicardASMetrics.xml" /> + <tool file="picard/rgPicardGCBiasMetrics.xml" /> + <tool file="picard/rgPicardInsertSize.xml" /> + <label text=="bam/sam Cleaning" id="picard-tools"> + <tool file="picard/picard_AddOrReplaceReadGroups.xml" /> + <tool file="picard/picard_ReorderSam.xml" /> + <tool file="picard/picard_ReplaceSamHeader.xml" /> + <tool file="picard/rgPicardFixMate.xml" /> + <tool file="picard/rgPicardMarkDups.xml" /> + <label text="Illumina fastq" id="illumina" /> + <tool file="fastq/fastq_groomer.xml" /> + <tool file="fastq/fastq_paired_end_splitter.xml" /> + <tool file="fastq/fastq_paired_end_joiner.xml" /> + <tool file="fastq/fastq_stats.xml" /> + <label text="Roche-454 data" id="454" /> + <tool file="metag_tools/short_reads_figure_score.xml" /> + <tool file="metag_tools/short_reads_trim_seq.xml" /> + <tool file="fastq/fastq_combiner.xml" /> + <label text="AB-SOLiD data" id="solid" /> + <tool file="next_gen_conversion/solid2fastq.xml" /> + <tool file="solid_tools/solid_qual_stats.xml" /> + <tool file="solid_tools/solid_qual_boxplot.xml" /> + <label text="Generic FASTQ manipulation" id="generic_fastq" /> + <tool file="fastq/fastq_filter.xml" /> + <tool file="fastq/fastq_trimmer.xml" /> + <tool file="fastq/fastq_trimmer_by_quality.xml" /> + <tool file="fastq/fastq_masker_by_quality.xml" /> + <tool file="fastq/fastq_manipulation.xml" /> + <tool file="fastq/fastq_to_fasta.xml" /> + <tool file="fastq/fastq_to_tabular.xml" /> + <tool file="fastq/tabular_to_fastq.xml" /> + <label text="FASTX-Toolkit for FASTQ data" id="fastx_toolkit" /> + <tool file="fastx_toolkit/fastq_quality_converter.xml" /> + <tool file="fastx_toolkit/fastx_quality_statistics.xml" /> + <tool file="fastx_toolkit/fastq_quality_boxplot.xml" /> + <tool file="fastx_toolkit/fastx_nucleotides_distribution.xml" /> + <tool file="fastx_toolkit/fastq_to_fasta.xml" /> + <tool file="fastx_toolkit/fastq_quality_filter.xml" /> + <tool file="fastx_toolkit/fastq_to_fasta.xml" /> + <tool file="fastx_toolkit/fastx_artifacts_filter.xml" /> + <tool file="fastx_toolkit/fastx_barcode_splitter.xml" /> + <tool file="fastx_toolkit/fastx_clipper.xml" /> + <tool file="fastx_toolkit/fastx_collapser.xml" /> + <tool file="fastx_toolkit/fastx_renamer.xml" /> + <tool file="fastx_toolkit/fastx_reverse_complement.xml" /> + <tool file="fastx_toolkit/fastx_trimmer.xml" /></section> + <!-- - <section name="NGS: QC and manipulation" id="cshl_library_information"> - <label text="FastQC: fastq/sam/bam" /> - <tool file="rgenetics/rgFastQC.xml" /> - <label text="QC/Metrics for sam/bam" /> - <tool file="picard/picard_BamIndexStats.xml" /> - <tool file="picard/rgPicardASMetrics.xml" /> - <tool file="picard/rgPicardGCBiasMetrics.xml" /> - <tool file="picard/rgPicardInsertSize.xml" /> - </section> - <section name="NGS: bam/sam Cleaning" id="picard-tools"> - <tool file="picard/picard_AddOrReplaceReadGroups.xml" /> - <tool file="picard/picard_ReorderSam.xml" /> - <tool file="picard/picard_ReplaceSamHeader.xml" /> - <tool file="picard/rgPicardFixMate.xml" /> - <tool file="picard/rgPicardMarkDups.xml" /> - </section> - <section name="Genome Diversity" id="gd"><tool file="genome_diversity/extract_primers.xml" /> --- a/tools/picard/picard_wrapper.py Wed Apr 27 15:41:25 2011 -0400 +++ b/tools/picard/picard_wrapper.py Wed Apr 27 17:06:14 2011 -0400 @@ -526,7 +526,10 @@ cl2 = ['mogrify', '-format jpg -resize x400 %s' % pdfpath] s,stdouts = pic.runCL(cl=cl2,output_dir=opts.outdir) else: - s = 'Unable to find expected pdf file %s\n' % pdfpath + s = 'Unable to find expected pdf file %s<br/>\n' % pdfpath + s += This <b>always happens if single ended data was provided</b> to this tool,\n' + s += 'so please double check that your input data really is paired-end NGS data.<br/>\n' + s += 'If your input was paired data this may be a bug worth reporting to the galaxy-bugs list\n<br/>' stdouts = '' lf = open(pic.log_filename,'a') lf.write(s) 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: kanwei: Fix GTF for trackster
by Bitbucket 27 Apr '11

27 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/ed5aea827a26/ changeset: r5461:ed5aea827a26 user: kanwei date: 2011-04-27 21:41:25 summary: Fix GTF for trackster affected #: 2 files (226 bytes) --- a/datatypes_conf.xml.sample Wed Apr 27 12:41:57 2011 -0400 +++ b/datatypes_conf.xml.sample Wed Apr 27 15:41:25 2011 -0400 @@ -75,7 +75,10 @@ <datatype extension="gff3" type="galaxy.datatypes.interval:Gff3" display_in_upload="true"/><datatype extension="gif" type="galaxy.datatypes.images:Image" mimetype="image/gif"/><datatype extension="gmaj.zip" type="galaxy.datatypes.images:Gmaj" mimetype="application/zip"/> - <datatype extension="gtf" type="galaxy.datatypes.interval:Gtf" display_in_upload="true"/> + <datatype extension="gtf" type="galaxy.datatypes.interval:Gtf" display_in_upload="true"> + <converter file="gff_to_bgzip_converter.xml" target_datatype="bgzip"/> + <converter file="gff_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/> + </datatype><datatype extension="html" type="galaxy.datatypes.images:Html" mimetype="text/html"/><datatype extension="interval" type="galaxy.datatypes.interval:Interval" display_in_upload="true"><converter file="interval_to_bed_converter.xml" target_datatype="bed"/> --- a/lib/galaxy/visualization/tracks/data_providers.py Wed Apr 27 12:41:57 2011 -0400 +++ b/lib/galaxy/visualization/tracks/data_providers.py Wed Apr 27 15:41:25 2011 -0400 @@ -611,7 +611,7 @@ # type. First key is converted dataset type; if result is another dict, second key # is original dataset type. TODO: This needs to be more flexible. dataset_type_name_to_data_provider = { - "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, Gff: GffDataProvider, "default" : TabixDataProvider }, + "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, Gff: GffDataProvider, Gtf: GffDataProvider, "default" : TabixDataProvider }, "bai": BamDataProvider, "summary_tree": SummaryTreeDataProvider, "bigwig": BigWigDataProvider, 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: fubar: Large push with modifications to the Picard tools recently added plus 5 new ones
by Bitbucket 27 Apr '11

27 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/cef47f0ab8f2/ changeset: r5460:cef47f0ab8f2 user: fubar date: 2011-04-27 18:41:57 summary: Large push with modifications to the Picard tools recently added plus 5 new ones and tests Also includes fastqc which is a very comprehensive QC report generator for sam/bam and fastq affected #: 42 files (22.5 KB) Diff too large to display. 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: When label text for a static option in a SelectToolParameter is not provided, default to using the 'value'.
by Bitbucket 26 Apr '11

26 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/14bce81c0a30/ changeset: r5459:14bce81c0a30 user: dan date: 2011-04-26 17:25:54 summary: When label text for a static option in a SelectToolParameter is not provided, default to using the 'value'. affected #: 1 file (9 bytes) --- a/lib/galaxy/tools/parameters/basic.py Mon Apr 25 19:01:39 2011 -0400 +++ b/lib/galaxy/tools/parameters/basic.py Tue Apr 26 11:25:54 2011 -0400 @@ -576,7 +576,7 @@ value = option.get( "value" ) self.legal_values.add( value ) selected = string_as_bool( option.get( "selected", False ) ) - self.static_options.append( ( option.text, value, selected ) ) + self.static_options.append( ( option.text or value, value, selected ) ) self.is_dynamic = ( ( self.dynamic_options is not None ) or ( self.options is not None ) ) def get_options( self, trans, other_values ): if self.options: 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: kanwei: Update pysam
by Bitbucket 25 Apr '11

25 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/ab056c49b927/ changeset: r5458:ab056c49b927 user: kanwei date: 2011-04-26 01:01:39 summary: Update pysam affected #: 1 file (0 bytes) --- a/eggs.ini Mon Apr 25 18:59:37 2011 -0400 +++ b/eggs.ini Mon Apr 25 19:01:39 2011 -0400 @@ -70,7 +70,7 @@ bx_python = _494c2d1d68b3 GeneTrack = _dev_48da9e998f0caf01c5be731e926f4b0481f658f0 SQLAlchemy = _dev_r6498 -pysam = _kanwei_6255075f4401 +pysam = _kanwei_5844008a1735 ; dependency source urls, necessary for scrambling. for an explanation, see ; the wiki page above 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: kanwei: trackster:
by Bitbucket 25 Apr '11

25 Apr '11

1 new changeset in galaxy-central: http://bitbucket.org/galaxy/galaxy-central/changeset/95b2802c2a38/ changeset: r5457:95b2802c2a38 user: kanwei date: 2011-04-26 00:59:37 summary: trackster: - Make GFF, Bed and Vcf use Tabix data provider instead of interval_index. PLEASE UPDATE with new entries in datatypes_conf.xml.sample - Refactoring for data providers affected #: 7 files (4.2 KB) --- a/datatypes_conf.xml.sample Mon Apr 25 17:21:21 2011 -0400 +++ b/datatypes_conf.xml.sample Mon Apr 25 18:59:37 2011 -0400 @@ -20,9 +20,7 @@ <display file="genetrack.xml" /></datatype> - <datatype extension="bedgraph" type="galaxy.datatypes.interval:BedGraph" display_in_upload="true"> - <converter file="bedgraph_to_array_tree_converter.xml" target_datatype="array_tree"/> - </datatype> + <datatype extension="bedgraph" type="galaxy.datatypes.interval:BedGraph" display_in_upload="true" /><datatype extension="bedstrict" type="galaxy.datatypes.interval:BedStrict" /><datatype extension="bed6" type="galaxy.datatypes.interval:Bed6"><converter file="bed_to_genetrack_converter.xml" target_datatype="genetrack"/> @@ -68,7 +66,8 @@ </datatype><datatype extension="gff" type="galaxy.datatypes.interval:Gff" display_in_upload="true"><converter file="gff_to_bed_converter.xml" target_datatype="bed"/> - <converter file="gff_to_interval_index_converter.xml" target_datatype="interval_index"/> + <converter file="gff_to_bgzip_converter.xml" target_datatype="bgzip"/> + <converter file="gff_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/><converter file="gff_to_summary_tree_converter.xml" target_datatype="summary_tree"/><display file="ensembl/ensembl_gff.xml" inherit="True"/> @@ -119,14 +118,14 @@ <datatype extension="memexml" type="galaxy.datatypes.xml:MEMEXml" display_in_upload="true"/><datatype extension="blastxml" type="galaxy.datatypes.xml:BlastXml" display_in_upload="true"/><datatype extension="vcf" type="galaxy.datatypes.tabular:Vcf" display_in_upload="true"> - <converter file="vcf_to_interval_index_converter.xml" target_datatype="interval_index"/> + <converter file="vcf_to_bgzip_converter.xml" target_datatype="bgzip"/> + <converter file="vcf_to_tabix_converter.xml" target_datatype="tabix" depends_on="bgzip"/><converter file="vcf_to_summary_tree_converter.xml" target_datatype="summary_tree"/></datatype><datatype extension="wsf" type="galaxy.datatypes.wsf:SnpFile" display_in_upload="true"/><datatype extension="velvet" type="galaxy.datatypes.assembly:Velvet" display_in_upload="false"/><datatype extension="wig" type="galaxy.datatypes.interval:Wiggle" display_in_upload="true"><converter file="wig_to_bigwig_converter.xml" target_datatype="bigwig"/> - <converter file="wiggle_to_array_tree_converter.xml" target_datatype="array_tree"/><converter file="wiggle_to_simple_converter.xml" target_datatype="interval"/></datatype> --- a/lib/galaxy/datatypes/converters/bgzip.py Mon Apr 25 17:21:21 2011 -0400 +++ b/lib/galaxy/datatypes/converters/bgzip.py Mon Apr 25 18:59:37 2011 -0400 @@ -18,6 +18,10 @@ if filetype == "bed": sort_params = ["sort", "-k1,1", "-k2,2n", "-k3,3n"] + elif filetype == "vcf": + sort_params = ["sort", "-k1,1", "-k2,2n"] + elif filetype == "gff": + sort_params = ["sort", "-s", "-k1,1", "-k4,4n"] # stable sort on start column # Skip any lines starting with "#" and "track" grepped = subprocess.Popen(["grep", "-e", "^\"#\"", "-e", "^track", "-v", input_fname], stderr=subprocess.PIPE, stdout=subprocess.PIPE ) after_sort = subprocess.Popen(sort_params, stdin=grepped.stdout, stderr=subprocess.PIPE, stdout=tmpfile ) --- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.py Mon Apr 25 17:21:21 2011 -0400 +++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.py Mon Apr 25 18:59:37 2011 -0400 @@ -1,7 +1,8 @@ #!/usr/bin/env python """ -Uses pysam to bgzip a file +Uses pysam to index a bgzipped interval file with tabix +Supported presets: bed, gff, vcf usage: %prog in_file out_file """ --- a/lib/galaxy/datatypes/interval.py Mon Apr 25 17:21:21 2011 -0400 +++ b/lib/galaxy/datatypes/interval.py Mon Apr 25 18:59:37 2011 -0400 @@ -772,7 +772,7 @@ return False def get_track_type( self ): - return "FeatureTrack", {"data": "interval_index", "index": "summary_tree"} + return "FeatureTrack", {"data": "tabix", "index": "summary_tree"} class Gff3( Gff ): --- a/lib/galaxy/datatypes/tabular.py Mon Apr 25 17:21:21 2011 -0400 +++ b/lib/galaxy/datatypes/tabular.py Mon Apr 25 18:59:37 2011 -0400 @@ -503,4 +503,4 @@ return out def get_track_type( self ): - return "FeatureTrack", {"data": "interval_index", "index": "summary_tree"} + return "FeatureTrack", {"data": "tabix", "index": "summary_tree"} --- a/lib/galaxy/model/__init__.py Mon Apr 25 17:21:21 2011 -0400 +++ b/lib/galaxy/model/__init__.py Mon Apr 25 18:59:37 2011 -0400 @@ -739,7 +739,7 @@ """ # See if we can convert the dataset if target_ext not in self.get_converter_types(): - raise ValueError("Conversion from '%s' to '%s' not possible", self.extension, target_ext) + raise NoConverterException("Conversion from '%s' to '%s' not possible" % (self.extension, target_ext) ) deps = {} # List of string of dependencies @@ -769,7 +769,7 @@ return None deps[dependency] = dep_dataset - except ValueError: + except NoConverterException: raise NoConverterException("A dependency (%s) is missing a converter." % dependency) except KeyError: pass # No deps --- a/lib/galaxy/visualization/tracks/data_providers.py Mon Apr 25 17:21:21 2011 -0400 +++ b/lib/galaxy/visualization/tracks/data_providers.py Mon Apr 25 18:59:37 2011 -0400 @@ -17,6 +17,7 @@ from bx.bbi.bigwig_file import BigWigFile from galaxy.util.lrucache import LRUCache from galaxy.visualization.tracks.summary import * +import galaxy_utils.sequence.vcf from galaxy.datatypes.tabular import Vcf from galaxy.datatypes.interval import Bed, Gff, Gtf from galaxy.datatypes.util.gff_util import parse_gff_attributes @@ -176,53 +177,6 @@ # Check for data. return st.chrom_blocks.get(chrom, None) is not None or (chrom and st.chrom_blocks.get(chrom[3:], None) is not None) -class VcfDataProvider( TracksDataProvider ): - """ - VCF data provider for the Galaxy track browser. - - Payload format: - [ uid (offset), start, end, ID, reference base(s), alternate base(s), quality score] - """ - - col_name_data_attr_mapping = { 'Qual' : { 'index': 6 , 'name' : 'Qual' } } - - def get_data( self, chrom, start, end, **kwargs ): - """ Returns data in region defined by chrom, start, and end. """ - start, end = int(start), int(end) - source = open( self.original_dataset.file_name ) - index = Indexes( self.converted_dataset.file_name ) - results = [] - count = 0 - message = None - - # If chrom is not found in indexes, try removing the first three - # characters (e.g. 'chr') and see if that works. This enables the - # provider to handle chrome names defined as chrXXX and as XXX. - chrom = str(chrom) - if chrom not in index.indexes and chrom[3:] in index.indexes: - chrom = chrom[3:] - - for start, end, offset in index.find(chrom, start, end): - if count >= MAX_VALS: - message = ERROR_MAX_VALS % "features" - break - count += 1 - source.seek(offset) - feature = source.readline().split() - - payload = [ offset, start, end, \ - # ID: - feature[2], \ - # reference base(s): - feature[3], \ - # alternative base(s) - feature[4], \ - # phred quality score - int( feature[5] )] - results.append(payload) - - return { 'data_type' : 'vcf', 'data': results, 'message': message } - class BamDataProvider( TracksDataProvider ): """ Provides access to intervals from a sorted indexed BAM file. @@ -343,83 +297,6 @@ bamfile.close() return { 'data': results, 'message': message } -class ArrayTreeDataProvider( TracksDataProvider ): - """ - Array tree data provider for the Galaxy track browser. - """ - def get_stats( self, chrom ): - f = open( self.converted_dataset.file_name ) - d = FileArrayTreeDict( f ) - try: - chrom_array_tree = d[chrom] - except KeyError: - f.close() - return None - - root_summary = chrom_array_tree.get_summary( 0, chrom_array_tree.levels ) - - level = chrom_array_tree.levels - 1 - desired_summary = chrom_array_tree.get_summary( 0, level ) - bs = chrom_array_tree.block_size ** level - - frequencies = map(int, desired_summary.frequencies) - out = [ (i * bs, freq) for i, freq in enumerate(frequencies) ] - - f.close() - return { 'max': float( max(root_summary.maxs) ), \ - 'min': float( min(root_summary.mins) ), \ - 'frequencies': out, \ - 'total_frequency': sum(root_summary.frequencies) } - - # Return None instead of NaN to pass jQuery 1.4's strict JSON - def float_nan(self, n): - if n != n: # NaN != NaN - return None - else: - return float(n) - - def get_data( self, chrom, start, end, **kwargs ): - if 'stats' in kwargs: - return self.get_stats(chrom) - - f = open( self.converted_dataset.file_name ) - d = FileArrayTreeDict( f ) - - # Get the right chromosome - try: - chrom_array_tree = d[chrom] - except: - f.close() - return None - - block_size = chrom_array_tree.block_size - start = int( start ) - end = int( end ) - resolution = max(1, ceil(float(kwargs['resolution']))) - - level = int( floor( log( resolution, block_size ) ) ) - level = max( level, 0 ) - stepsize = block_size ** level - - # Is the requested level valid? - assert 0 <= level <= chrom_array_tree.levels - - results = [] - for block_start in range( start, end, stepsize * block_size ): - # Return either data point or a summary depending on the level - indexes = range( block_start, block_start + stepsize * block_size, stepsize ) - if level > 0: - s = chrom_array_tree.get_summary( block_start, level ) - if s is not None: - results.extend( zip( indexes, map( self.float_nan, s.sums / s.counts ) ) ) - else: - l = chrom_array_tree.get_leaf( block_start ) - if l is not None: - results.extend( zip( indexes, map( self.float_nan, l ) ) ) - - f.close() - return results - class BBIDataProvider( TracksDataProvider ): """ BBI data provider for the Galaxy track browser. @@ -483,30 +360,13 @@ f = open( self.original_dataset.file_name ) return f, BigWigFile(file=f) -class IntervalIndexDataProvider( TracksDataProvider ): +class TabixDataProvider( TracksDataProvider ): """ - Interval index data provider for the Galaxy track browser. - - Payload format: [ uid (offset), start, end, name, strand, thick_start, thick_end, blocks ] + Tabix index data provider for the Galaxy track browser. """ col_name_data_attr_mapping = { 4 : { 'index': 4 , 'name' : 'Score' } } - def write_data_to_file( self, chrom, start, end, filename ): - source = open( self.original_dataset.file_name ) - index = Indexes( self.converted_dataset.file_name ) - out = open( filename, 'w' ) - for start, end, offset in index.find(chrom, start, end): - source.seek( offset ) - if isinstance( self.original_dataset.datatype, Gff ): - reader = GFFReaderWrapper( source, fix_strand=True ) - feature = reader.next() - for interval in feature.intervals: - out.write(interval.raw_line + '\n') - elif isinstance( self.original_dataset.datatype, Bed ): - out.write( source.readline() ) - out.close() - def get_filters( self ): """ Returns a dataset's filters. """ @@ -563,36 +423,55 @@ return filters -class TabixDataProvider( IntervalIndexDataProvider ): - """ - Tabix index data provider for the Galaxy track browser. - - Payload format: [ uid (offset), start, end, name, strand, thick_start, thick_end, blocks ] - """ - - def get_data( self, chrom, start, end, **kwargs ): + def get_iterator( self, chrom, start, end ): if end >= 2<<29: end = (2<<29 - 1) # Tabix-enforced maximum start, end = int(start), int(end) - # {'bgzip': (<galaxy.model.HistoryDatasetAssociation object at 0x85fbe90>, {})} bgzip_fname = self.dependencies['bgzip'].file_name # if os.path.getsize(self.converted_dataset.file_name) == 0: # return { 'kind': messages.ERROR, 'message': "Tabix converted size was 0, meaning the input file had invalid values." } tabix = ctabix.Tabixfile(bgzip_fname, index_filename=self.converted_dataset.file_name) - results = [] - count = 0 - message = None - # If chrom is not found in indexes, try removing the first three # characters (e.g. 'chr') and see if that works. This enables the # provider to handle chrome names defined as chrXXX and as XXX. chrom = str(chrom) - if chrom not in tabix.contigs and ("chr" + chrom[3:]) in tabix.contigs: + if chrom not in tabix.contigs and chrom.startswith("chr") and (chrom[3:] in tabix.contigs): chrom = chrom[3:] - + + return tabix.fetch(reference=chrom, start=start, end=end) + + def get_data( self, chrom, start, end, **kwargs ): + iterator = self.get_iterator( chrom, start, end ) + return self.process_data(iterator, **kwargs) + +class GffDataProvider( TabixDataProvider ): + # FIXME: Doesn't implement write_data_to_file + def process_data( self, iterator, **kwargs ): + count = 0 + rval = [] + message = None + for feature in GFFReaderWrapper( iterator, fix_strand=True ): + if count >= MAX_VALS: + message = ERROR_MAX_VALS % "features" + break + count += 1 + + payload = package_gff_feature( feature ) + hashed = hash("\t".join(feature.fields)) + payload.insert( 0, hashed ) + rval.append( payload ) + + return { 'data': rval, 'message': message } + +class BedDataProvider( TabixDataProvider ): + """ + Payload format: [ uid (offset), start, end, name, strand, thick_start, thick_end, blocks ] + """ + + def process_data( self, iterator, **kwargs ): # # Build data to return. Payload format is: # [ <guid/offset>, <start>, <end>, <name>, <score>, <strand>, <thick_start>, @@ -602,60 +481,97 @@ # filter_cols = from_json_string( kwargs.get( "filter_cols", "[]" ) ) no_detail = ( "no_detail" in kwargs ) - - for line in tabix.fetch(reference=chrom, start=start, end=end): + count = 0 + rval = [] + message = None + for line in iterator: if count >= MAX_VALS: message = ERROR_MAX_VALS % "features" break count += 1 # TODO: can we use column metadata to fill out payload? # TODO: use function to set payload data - if isinstance( self.original_dataset.datatype, Gff ): - # GFF dataset. - reader = GFFReaderWrapper( source, fix_strand=True ) - feature = reader.next() - payload = package_gff_feature( feature, no_detail, filter_cols ) - payload.insert( 0, offset ) - elif isinstance( self.original_dataset.datatype, Bed ): - # BED dataset. - feature = line.split() - length = len(feature) - # Unique id is just a hash of the line - payload = [ hash(line), int(feature[1]), int(feature[2]) ] + + feature = line.split() + length = len(feature) + # Unique id is just a hash of the line + payload = [ hash(line), int(feature[1]), int(feature[2]) ] + + if no_detail: + rval.append( payload ) + continue + + # Simpler way to add stuff, but type casting is not done. + # Name, score, strand, thick start, thick end. + #end = min( len( feature ), 8 ) + #payload.extend( feature[ 3:end ] ) + + # Name, strand, thick start, thick end. + if length >= 4: + payload.append(feature[3]) + if length >= 6: + payload.append(feature[5]) + if length >= 8: + payload.append(int(feature[6])) + payload.append(int(feature[7])) + + # Blocks. + if length >= 12: + block_sizes = [ int(n) for n in feature[10].split(',') if n != ''] + block_starts = [ int(n) for n in feature[11].split(',') if n != '' ] + blocks = zip( block_sizes, block_starts ) + payload.append( [ ( int(feature[1]) + block[1], int(feature[1]) + block[1] + block[0] ) for block in blocks ] ) + + # Score (filter data) + if length >= 5 and filter_cols and filter_cols[0] == "Score": + payload.append( float(feature[4]) ) - if no_detail: - results.append( payload ) - continue - - # Simpler way to add stuff, but type casting is not done. - # Name, score, strand, thick start, thick end. - #end = min( len( feature ), 8 ) - #payload.extend( feature[ 3:end ] ) - - # Name, strand, thick start, thick end. - if length >= 4: - payload.append(feature[3]) - if length >= 6: - payload.append(feature[5]) - if length >= 8: - payload.append(int(feature[6])) - payload.append(int(feature[7])) + rval.append( payload ) + + return { 'data': rval, 'message': message } + + def write_data_to_file( self, chrom, start, end, filename ): + iterator = self.get_iterator( chrom, start, end ) + out = open( filename, "w" ) + for line in iterator: + out.write( line ) + out.close() + +class VcfDataProvider( TracksDataProvider ): + """ + VCF data provider for the Galaxy track browser. - # Blocks. - if length >= 12: - block_sizes = [ int(n) for n in feature[10].split(',') if n != ''] - block_starts = [ int(n) for n in feature[11].split(',') if n != '' ] - blocks = zip( block_sizes, block_starts ) - payload.append( [ ( int(feature[1]) + block[1], int(feature[1]) + block[1] + block[0] ) for block in blocks ] ) - - # Score (filter data) - if length >= 5 and filter_cols and filter_cols[0] == "Score": - payload.append( float(feature[4]) ) - - results.append( payload ) + Payload format: + [ uid (offset), start, end, ID, reference base(s), alternate base(s), quality score] + """ - return { 'data': results, 'message': message } - + col_name_data_attr_mapping = { 'Qual' : { 'index': 6 , 'name' : 'Qual' } } + + def process_data( self, iterator, **kwargs ): + rval = [] + count = 0 + message = None + + reader = galaxy_utils.sequence.vcf.Reader( iterator ) + for line in reader: + if count >= MAX_VALS: + message = ERROR_MAX_VALS % "features" + break + count += 1 + + feature = line.split() + payload = [ hash(line), vcf_line.pos-1, vcf_line.pos, \ + # ID: + feature[2], \ + # reference base(s): + feature[3], \ + # alternative base(s) + feature[4], \ + # phred quality score + int( feature[5] )] + rval.append(payload) + + return { 'data_type' : 'vcf', 'data': rval, 'message': message } class GFFDataProvider( TracksDataProvider ): """ @@ -695,51 +611,41 @@ # type. First key is converted dataset type; if result is another dict, second key # is original dataset type. TODO: This needs to be more flexible. dataset_type_name_to_data_provider = { - "array_tree": ArrayTreeDataProvider, - "tabix": TabixDataProvider, - "interval_index": { "vcf": VcfDataProvider, "default" : IntervalIndexDataProvider }, + "tabix": { Vcf: VcfDataProvider, Bed: BedDataProvider, Gff: GffDataProvider, "default" : TabixDataProvider }, "bai": BamDataProvider, "summary_tree": SummaryTreeDataProvider, "bigwig": BigWigDataProvider, "bigbed": BigBedDataProvider } -dataset_type_to_data_provider = { - Vcf : VcfDataProvider, -} - def get_data_provider( name=None, original_dataset=None ): """ Returns data provider class by name and/or original dataset. """ - data_provider = None if name: value = dataset_type_name_to_data_provider[ name ] if isinstance( value, dict ): # Get converter by dataset extension; if there is no data provider, # get the default. - data_provider = value.get( original_dataset.ext, value.get( "default" ) ) + data_provider = value.get( original_dataset.datatype.__class__, value.get( "default" ) ) else: data_provider = value elif original_dataset: - # Look for data provider in mapping. - data_provider = dataset_type_to_data_provider.get( original_dataset.datatype.__class__, None ) - if not data_provider: - # Look up data provider from datatype's informaton. - try: - # Get data provider mapping and data provider for 'data'. If - # provider available, use it; otherwise use generic provider. - _ , data_provider_mapping = original_dataset.datatype.get_track_type() - if 'data_standalone' in data_provider_mapping: - data_provider_name = data_provider_mapping[ 'data_standalone' ] - else: - data_provider_name = data_provider_mapping[ 'data' ] - if data_provider_name: - data_provider = get_data_provider( name=data_provider_name, original_dataset=original_dataset ) - else: - data_provider = TracksDataProvider - except: - pass + # Look up data provider from datatype's informaton. + try: + # Get data provider mapping and data provider for 'data'. If + # provider available, use it; otherwise use generic provider. + _ , data_provider_mapping = original_dataset.datatype.get_track_type() + if 'data_standalone' in data_provider_mapping: + data_provider_name = data_provider_mapping[ 'data_standalone' ] + else: + data_provider_name = data_provider_mapping[ 'data' ] + if data_provider_name: + data_provider = get_data_provider( name=data_provider_name, original_dataset=original_dataset ) + else: + data_provider = TracksDataProvider + except: + pass return data_provider def package_gff_feature( feature, no_detail=False, filter_cols=[] ): 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