class Tree(object):
def _loadNames(self, dmpDir):
self.names = MultiDict()
self.sciNames = dict()
sciName = "scientific name"
fh = dmpFileParser(dmpDir + "/names.dmp")
for row in fh:
name = Name(row)
self.names[name.taxId] = name
if name.nameClass == sciName:
self.sciNames[name.nameTxt] = name.taxId
def _loadNodes(self, dmpDir):
self.nodes = dict()
self.parentNodeRefs = MultiDict()
fh = dmpFileParser(dmpDir + "/nodes.dmp")
for row in fh:
node = Node(row)
self.nodes[node.taxId] = node
self.parentNodeRefs.add(node.parentTaxId, node)
def __init__(self, dmpDir):
"parse *.dmp files in dmpDir"
self._loadNames(dmpDir)
self._loadNodes(dmpDir)
class Tree(object):
def _loadNames(self, dmpDir):
self.names = MultiDict()
self.sciNames = dict()
sciName = "scientific name"
fh = dmpFileParser(dmpDir + "/names.dmp")
for row in fh:
name = Name(row)
self.names[name.taxId] = name
if name.nameClass == sciName:
self.sciNames[name.nameTxt] = name.taxId
def _loadNodes(self, dmpDir):
self.nodes = dict()
self.parentNodeRefs = MultiDict()
fh = dmpFileParser(dmpDir + "/nodes.dmp")
for row in fh:
node = Node(row)
self.nodes[node.taxId] = node
self.parentNodeRefs.add(node.parentTaxId, node)
def __init__(self, dmpDir):
"parse *.dmp files in dmpDir"
self._loadNames(dmpDir)
self._loadNodes(dmpDir)
class GenePredTbl(list):
"""Table of GenePred objects loaded from a tab-file"""
def __init__(self, fileName, buildIdx=False, buildUniqIdx=False, buildRangeIdx=False):
if buildIdx and buildUniqIdx:
raise Exception("can't specify both buildIdx and buildUniqIdx")
for row in GenePredReader(fileName):
self.append(row)
self.names = None
self.rangeMap = None
if buildUniqIdx:
self.__buildUniqIdx()
if buildIdx:
self.__buildIdx()
if buildRangeIdx:
self.__buildRangeIdx()
def __buildUniqIdx(self):
self.names = dict()
for row in self:
if row.name in self.names:
raise Exception("gene with this name already in index: " + row.name)
self.names[row.name] = row
def __buildIdx(self):
from pycbio.sys.MultiDict import MultiDict
self.names = MultiDict()
for row in self:
self.names.add(row.name, row)
def __buildRangeIdx(self):
from pycbio.hgdata.RangeFinder import RangeFinder
self.rangeMap = RangeFinder()
for gene in self:
self.rangeMap.add(gene.chrom, gene.txStart, gene.txEnd, gene, gene.strand)
def _loadNodes(self, dmpDir):
self.nodes = dict()
self.parentNodeRefs = MultiDict()
fh = dmpFileParser(dmpDir + "/nodes.dmp")
for row in fh:
node = Node(row)
self.nodes[node.taxId] = node
self.parentNodeRefs.add(node.parentTaxId, node)
class PslTbl(list):
"""Table of PSL objects loaded from a tab-file
"""
def __mkQNameIdx(self):
self.qNameMap = MultiDict()
for psl in self:
self.qNameMap.add(psl.qName, psl)
def __mkTNameIdx(self):
self.tNameMap = MultiDict()
for psl in self:
self.tNameMap.add(psl.tName, psl)
def __init__(self, fileName, qNameIdx=False, tNameIdx=False):
for psl in PslReader(fileName):
self.append(psl)
self.qNameMap = self.tNameMap = None
if qNameIdx:
self.__mkQNameIdx()
if tNameIdx:
self.__mkTNameIdx()
def getQNameIter(self):
return self.qNameMap.iterkeys()
def haveQName(self, qName):
return (self.qNameMap.get(qName) != None)
def getByQName(self, qName):
"""generator to get all PSL with a give qName"""
ent = self.qNameMap.get(qName)
if ent != None:
if isinstance(ent, list):
for psl in ent:
yield psl
else:
yield ent
def getTNameIter(self):
return self.tNameMap.iterkeys()
def haveTName(self, tName):
return (self.tNameMap.get(qName) != None)
def getByTName(self, tName):
"""generator to get all PSL with a give tName"""
ent = self.tNameMap.get(tName)
if ent != None:
if isinstance(ent, list):
for psl in ent:
yield psl
else:
yield ent
class PslTbl(list):
"""Table of PSL objects loaded from a tab-file
"""
def __mkQNameIdx(self):
self.qNameMap = MultiDict()
for psl in self:
self.qNameMap.add(psl.qName, psl)
def __mkTNameIdx(self):
self.tNameMap = MultiDict()
for psl in self:
self.tNameMap.add(psl.tName, psl)
def __init__(self, fileName, qNameIdx=False, tNameIdx=False):
for psl in PslReader(fileName):
self.append(psl)
self.qNameMap = self.tNameMap = None
if qNameIdx:
self.__mkQNameIdx()
if tNameIdx:
self.__mkTNameIdx()
def getQNameIter(self):
return self.qNameMap.iterkeys()
def haveQName(self, qName):
return (self.qNameMap.get(qName) != None)
def getByQName(self, qName):
"""generator to get all PSL with a give qName"""
ent = self.qNameMap.get(qName)
if ent != None:
if isinstance(ent, list):
for psl in ent:
yield psl
else:
yield ent
def getTNameIter(self):
return self.tNameMap.iterkeys()
def haveTName(self, tName):
return (self.tNameMap.get(qName) != None)
def getByTName(self, tName):
"""generator to get all PSL with a give tName"""
ent = self.tNameMap.get(tName)
if ent != None:
if isinstance(ent, list):
for psl in ent:
yield psl
else:
yield ent
class BedTbl(TabFile):
"""Table of BED objects loaded from a tab-file
"""
def _mkNameIdx(self):
self.nameMap = MultiDict()
for bed in self:
self.nameMap.add(bed.name, bed)
def __init__(self, fileName, nameIdx=False):
TabFile.__init__(self, fileName, rowClass=Bed, hashAreComments=True)
self.nameMap = None
if nameIdx:
self._nameIdx()
class BedTbl(TabFile):
"""Table of BED objects loaded from a tab-file
"""
def _mkNameIdx(self):
self.nameMap = MultiDict()
for bed in self:
self.nameMap.add(bed.name, bed)
def __init__(self, fileName, nameIdx=False):
TabFile.__init__(self, fileName, rowClass=Bed, hashAreComments=True)
self.nameMap = None
if nameIdx:
self._nameIdx()
def __init__(self, clusterGenesOut):
self.genes = MultiDict()
tsv = TSVReader(clusterGenesOut, typeMap=typeMap)
self.columns = tsv.columns
self.tableSet = set()
for gene in tsv:
self.__addGene(gene)
def _loadNodes(self, dmpDir):
self.nodes = dict()
self.parentNodeRefs = MultiDict()
fh = dmpFileParser(dmpDir + "/nodes.dmp")
for row in fh:
node = Node(row)
self.nodes[node.taxId] = node
self.parentNodeRefs.add(node.parentTaxId, node)
class ClusterGenes(list):
"""Object to access output of ClusterGenes. List of Cluster objects,
indexed by clusterId. Note that clusterId is one based, entry 0 is
None, however generator doesn't return it or other Null clusters.
"""
def __init__(self, clusterGenesOut):
self.genes = MultiDict()
tsv = TSVReader(clusterGenesOut, typeMap=typeMap)
self.columns = tsv.columns
self.tableSet = set()
for gene in tsv:
self.__addGene(gene)
def haveCluster(self, clusterId):
" determine if the specified cluster exists"
if clusterId >= len(self):
return False
return self[clusterId] != None
def __getCluster(self, clusterId):
while len(self) <= clusterId:
self.append(None)
if self[clusterId] == None:
self[clusterId] = Cluster(clusterId)
return self[clusterId]
def __addGene(self, row):
cluster = self.__getCluster(row.cluster)
cluster.add(row)
self.genes.add(row.gene, row)
self.tableSet.add(row.table)
def __iter__(self):
"get generator over non-null clusters"
return self.generator()
def generator(self):
"generator over non-null clusters"
for cl in list.__iter__(self):
if cl != None:
yield cl
def _loadNames(self, dmpDir):
self.names = MultiDict()
self.sciNames = dict()
sciName = "scientific name"
fh = dmpFileParser(dmpDir + "/names.dmp")
for row in fh:
name = Name(row)
self.names[name.taxId] = name
if name.nameClass == sciName:
self.sciNames[name.nameTxt] = name.taxId
class GenePredTbl(list):
"""Table of GenePred objects loaded from a tab-file"""
def __init__(self,
fileName,
buildIdx=False,
buildUniqIdx=False,
buildRangeIdx=False):
if buildIdx and buildUniqIdx:
raise Exception("can't specify both buildIdx and buildUniqIdx")
for row in GenePredReader(fileName):
self.append(row)
self.names = None
self.rangeMap = None
if buildUniqIdx:
self.__buildUniqIdx()
if buildIdx:
self.__buildIdx()
if buildRangeIdx:
self.__buildRangeIdx()
def __buildUniqIdx(self):
self.names = dict()
for row in self:
if row.name in self.names:
raise Exception("gene with this name already in index: " +
row.name)
self.names[row.name] = row
def __buildIdx(self):
from pycbio.sys.MultiDict import MultiDict
self.names = MultiDict()
for row in self:
self.names.add(row.name, row)
def __buildRangeIdx(self):
from pycbio.hgdata.RangeFinder import RangeFinder
self.rangeMap = RangeFinder()
for gene in self:
self.rangeMap.add(gene.chrom, gene.txStart, gene.txEnd, gene,
gene.strand)
def _mkNameIdx(self):
self.nameMap = MultiDict()
for bed in self:
self.nameMap.add(bed.name, bed)
def __buildIdx(self):
from pycbio.sys.MultiDict import MultiDict
self.names = MultiDict()
for row in self:
self.names.add(row.name, row)
def __mkTNameIdx(self):
self.tNameMap = MultiDict()
for psl in self:
self.tNameMap.add(psl.tName, psl)
def __mkTNameIdx(self):
self.tNameMap = MultiDict()
for psl in self:
self.tNameMap.add(psl.tName, psl)
def __buildIdx(self):
from pycbio.sys.MultiDict import MultiDict
self.names = MultiDict()
for row in self:
self.names.add(row.name, row)
def _mkNameIdx(self):
self.nameMap = MultiDict()
for bed in self:
self.nameMap.add(bed.name, bed)
