| Previous changeset 3:ecb36112b056 (2015-11-11) Next changeset 5:0145969324c4 (2017-06-22) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/gops/subtract commit 4e2052686dfe8003f867449e0affff96398b2a62 |
|
modified:
tool_dependencies.xml |
|
added:
utils/__init__.py utils/gff_util.py utils/odict.py |
| b |
| diff -r ecb36112b056 -r 7a2a604ae9c8 tool_dependencies.xml --- a/tool_dependencies.xml Wed Nov 11 12:49:24 2015 -0500 +++ b/tool_dependencies.xml Thu Feb 11 12:11:59 2016 -0500 |
| b |
| @@ -4,6 +4,6 @@ <repository changeset_revision="2d0c08728bca" name="package_bx_python_0_7" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> <package name="galaxy-ops" version="1.0.0"> - <repository changeset_revision="9cbb20b85c01" name="package_galaxy_ops_1_0_0" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + <repository changeset_revision="eef263ff9b95" name="package_galaxy_ops_1_0_0" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> </tool_dependency> |
| b |
| diff -r ecb36112b056 -r 7a2a604ae9c8 utils/gff_util.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/utils/gff_util.py Thu Feb 11 12:11:59 2016 -0500 |
| [ |
| b'@@ -0,0 +1,430 @@\n+"""\n+Provides utilities for working with GFF files.\n+"""\n+\n+import copy\n+from bx.intervals.io import GenomicInterval, GenomicIntervalReader, MissingFieldError, NiceReaderWrapper\n+from bx.tabular.io import Header, Comment, ParseError\n+from utils.odict import odict\n+\n+\n+class GFFInterval( GenomicInterval ):\n+ """\n+ A GFF interval, including attributes. If file is strictly a GFF file,\n+ only attribute is \'group.\'\n+ """\n+ def __init__( self, reader, fields, chrom_col=0, feature_col=2, start_col=3, end_col=4,\n+ strand_col=6, score_col=5, default_strand=\'.\', fix_strand=False ):\n+ # HACK: GFF format allows \'.\' for strand but GenomicInterval does not. To get around this,\n+ # temporarily set strand and then unset after initing GenomicInterval.\n+ unknown_strand = False\n+ if not fix_strand and fields[ strand_col ] == \'.\':\n+ unknown_strand = True\n+ fields[ strand_col ] = \'+\'\n+ GenomicInterval.__init__( self, reader, fields, chrom_col, start_col, end_col, strand_col,\n+ default_strand, fix_strand=fix_strand )\n+ if unknown_strand:\n+ self.strand = \'.\'\n+ self.fields[ strand_col ] = \'.\'\n+\n+ # Handle feature, score column.\n+ self.feature_col = feature_col\n+ if self.feature_col >= self.nfields:\n+ raise MissingFieldError( "No field for feature_col (%d)" % feature_col )\n+ self.feature = self.fields[ self.feature_col ]\n+ self.score_col = score_col\n+ if self.score_col >= self.nfields:\n+ raise MissingFieldError( "No field for score_col (%d)" % score_col )\n+ self.score = self.fields[ self.score_col ]\n+\n+ # GFF attributes.\n+ self.attributes = parse_gff_attributes( fields[8] )\n+\n+ def copy( self ):\n+ return GFFInterval(self.reader, list( self.fields ), self.chrom_col, self.feature_col, self.start_col,\n+ self.end_col, self.strand_col, self.score_col, self.strand)\n+\n+\n+class GFFFeature( GFFInterval ):\n+ """\n+ A GFF feature, which can include multiple intervals.\n+ """\n+ def __init__( self, reader, chrom_col=0, feature_col=2, start_col=3, end_col=4,\n+ strand_col=6, score_col=5, default_strand=\'.\', fix_strand=False, intervals=[],\n+ raw_size=0 ):\n+ # Use copy so that first interval and feature do not share fields.\n+ GFFInterval.__init__( self, reader, copy.deepcopy( intervals[0].fields ), chrom_col, feature_col,\n+ start_col, end_col, strand_col, score_col, default_strand,\n+ fix_strand=fix_strand )\n+ self.intervals = intervals\n+ self.raw_size = raw_size\n+ # Use intervals to set feature attributes.\n+ for interval in self.intervals:\n+ # Error checking. NOTE: intervals need not share the same strand.\n+ if interval.chrom != self.chrom:\n+ raise ValueError( "interval chrom does not match self chrom: %s != %s" %\n+ ( interval.chrom, self.chrom ) )\n+ # Set start, end of interval.\n+ if interval.start < self.start:\n+ self.start = interval.start\n+ if interval.end > self.end:\n+ self.end = interval.end\n+\n+ def name( self ):\n+ """ Returns feature\'s name. """\n+ name = None\n+ # Preference for name: GTF, GFF3, GFF.\n+ for attr_name in [\'gene_id\', \'transcript_id\', # GTF\n+ \'ID\', \'id\', # GFF3\n+ \'group\' ]: # GFF (TODO)\n+ name = self.attributes.get( attr_name, None )\n+ if name is not None:\n+ break\n+ return name\n+\n+ def copy( self ):\n+ intervals_copy = []\n+ for interval in self.intervals:\n+ intervals_copy.append( interval.copy() )\n+ return GFFFeature(self.reader, se'..b'f pair == \'\':\n+ continue\n+ name = pair[0].strip()\n+ if name == \'\':\n+ continue\n+ # Need to strip double quote from values\n+ value = pair[1].strip(" \\"")\n+ attributes[ name ] = value\n+\n+ if len( attributes ) == 0:\n+ # Could not split attributes string, so entire string must be\n+ # \'group\' attribute. This is the case for strictly GFF files.\n+ attributes[\'group\'] = attr_str\n+ return attributes\n+\n+\n+def gff_attributes_to_str( attrs, gff_format ):\n+ """\n+ Convert GFF attributes to string. Supported formats are GFF3, GTF.\n+ """\n+ if gff_format == \'GTF\':\n+ format_string = \'%s "%s"\'\n+ # Convert group (GFF) and ID, parent (GFF3) attributes to transcript_id, gene_id\n+ id_attr = None\n+ if \'group\' in attrs:\n+ id_attr = \'group\'\n+ elif \'ID\' in attrs:\n+ id_attr = \'ID\'\n+ elif \'Parent\' in attrs:\n+ id_attr = \'Parent\'\n+ if id_attr:\n+ attrs[\'transcript_id\'] = attrs[\'gene_id\'] = attrs[id_attr]\n+ elif gff_format == \'GFF3\':\n+ format_string = \'%s=%s\'\n+ attrs_strs = []\n+ for name, value in attrs.items():\n+ attrs_strs.append( format_string % ( name, value ) )\n+ return " ; ".join( attrs_strs )\n+\n+\n+def read_unordered_gtf( iterator, strict=False ):\n+ """\n+ Returns GTF features found in an iterator. GTF lines need not be ordered\n+ or clustered for reader to work. Reader returns GFFFeature objects sorted\n+ by transcript_id, chrom, and start position.\n+ """\n+\n+ # -- Get function that generates line/feature key. --\n+\n+ get_transcript_id = lambda fields: parse_gff_attributes( fields[8] )[ \'transcript_id\' ]\n+ if strict:\n+ # Strict GTF parsing uses transcript_id only to group lines into feature.\n+ key_fn = get_transcript_id\n+ else:\n+ # Use lenient parsing where chromosome + transcript_id is the key. This allows\n+ # transcripts with same ID on different chromosomes; this occurs in some popular\n+ # datasources, such as RefGenes in UCSC.\n+ key_fn = lambda fields: fields[0] + \'_\' + get_transcript_id( fields )\n+\n+ # Aggregate intervals by transcript_id and collect comments.\n+ feature_intervals = odict()\n+ comments = []\n+ for count, line in enumerate( iterator ):\n+ if line.startswith( \'#\' ):\n+ comments.append( Comment( line ) )\n+ continue\n+\n+ line_key = key_fn( line.split(\'\\t\') )\n+ if line_key in feature_intervals:\n+ feature = feature_intervals[ line_key ]\n+ else:\n+ feature = []\n+ feature_intervals[ line_key ] = feature\n+ feature.append( GFFInterval( None, line.split( \'\\t\' ) ) )\n+\n+ # Create features.\n+ chroms_features = {}\n+ for count, intervals in enumerate( feature_intervals.values() ):\n+ # Sort intervals by start position.\n+ intervals.sort( lambda a, b: cmp( a.start, b.start ) )\n+ feature = GFFFeature( None, intervals=intervals )\n+ if feature.chrom not in chroms_features:\n+ chroms_features[ feature.chrom ] = []\n+ chroms_features[ feature.chrom ].append( feature )\n+\n+ # Sort features by chrom, start position.\n+ chroms_features_sorted = []\n+ for chrom_features in chroms_features.values():\n+ chroms_features_sorted.append( chrom_features )\n+ chroms_features_sorted.sort( lambda a, b: cmp( a[0].chrom, b[0].chrom ) )\n+ for features in chroms_features_sorted:\n+ features.sort( lambda a, b: cmp( a.start, b.start ) )\n+\n+ # Yield comments first, then features.\n+ # FIXME: comments can appear anywhere in file, not just the beginning.\n+ # Ideally, then comments would be associated with features and output\n+ # just before feature/line.\n+ for comment in comments:\n+ yield comment\n+\n+ for chrom_features in chroms_features_sorted:\n+ for feature in chrom_features:\n+ yield feature\n' |
| b |
| diff -r ecb36112b056 -r 7a2a604ae9c8 utils/odict.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/utils/odict.py Thu Feb 11 12:11:59 2016 -0500 |
| [ |
| @@ -0,0 +1,86 @@ +""" +Ordered dictionary implementation. +""" + +from UserDict import UserDict + + +class odict(UserDict): + """ + http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/107747 + + This dictionary class extends UserDict to record the order in which items are + added. Calling keys(), values(), items(), etc. will return results in this + order. + """ + def __init__( self, dict=None ): + self._keys = [] + UserDict.__init__( self, dict ) + + def __delitem__( self, key ): + UserDict.__delitem__( self, key ) + self._keys.remove( key ) + + def __setitem__( self, key, item ): + UserDict.__setitem__( self, key, item ) + if key not in self._keys: + self._keys.append( key ) + + def clear( self ): + UserDict.clear( self ) + self._keys = [] + + def copy(self): + new = odict() + new.update( self ) + return new + + def items( self ): + return zip( self._keys, self.values() ) + + def keys( self ): + return self._keys[:] + + def popitem( self ): + try: + key = self._keys[-1] + except IndexError: + raise KeyError( 'dictionary is empty' ) + val = self[ key ] + del self[ key ] + return ( key, val ) + + def setdefault( self, key, failobj=None ): + if key not in self._keys: + self._keys.append( key ) + return UserDict.setdefault( self, key, failobj ) + + def update( self, dict ): + for ( key, val ) in dict.items(): + self.__setitem__( key, val ) + + def values( self ): + return map( self.get, self._keys ) + + def iterkeys( self ): + return iter( self._keys ) + + def itervalues( self ): + for key in self._keys: + yield self.get( key ) + + def iteritems( self ): + for key in self._keys: + yield key, self.get( key ) + + def __iter__( self ): + for key in self._keys: + yield key + + def reverse( self ): + self._keys.reverse() + + def insert( self, index, key, item ): + if key not in self._keys: + self._keys.insert( index, key ) + UserDict.__setitem__( self, key, item ) |