def __init__(self, pslStatsFile):
tsvRdr = TsvReader(pslStatsFile, typeMap=typeMap)
self.columns = tsvRdr.columns
self.type = self._determineType(tsvRdr)
self.idx = self._createIdx(self.type)
for row in tsvRdr:
self._add(row)
def __init__(self, clusterGenesOut):
self.genes = defaultdict(list)
self.tableSet = set()
tsvRdr = TsvReader(clusterGenesOut, typeMap=typeMap)
self.columns = tsvRdr.columns
for gene in tsvRdr:
self._addGene(gene)
def loadTsv(self, attrsFile):
"""load a GENCODE attributes file, adding bin"""
typeMap = {
"ccdsId": noneIfEmpty,
"proteinId": noneIfEmpty,
"level": int
}
rows = [
self._loadTsvRow(row)
for row in TsvReader(attrsFile, typeMap=typeMap)
]
self.loads(rows)
def loadInfoFromFile(self, gencodeInfo, onlyExisting=True):
"""load file produced by the gencodeGtfToAttrs script. If onlyExisting
is true, only entries for transcripts already loaded from genePreds
area included.
"""
infoTypeMap = {
"geneType": BioType,
"transcriptType": BioType,
"level": int,
"tags": BioTags,
"havanaGene": _noneIfEmpty,
"havanaTranscript": _noneIfEmpty,
"ccdsId": _noneIfEmpty
}
for info in TsvReader(gencodeInfo, typeMap=infoTypeMap):
self.__loadInfoRow(info, onlyExisting)
def __init__(self, fileName):
TsvReader.__init__(self, fileName, typeMap=typeMap)
def loadTsv(self, sourceFile):
"""load a GENCODE attributes file, adding bin"""
rows = [self._loadTsvRow(row) for row in TsvReader(sourceFile)]
self.loads(rows)
def GeneCheckReader(fspec):
for gc in TsvReader(fspec, typeMap=typeMap):
yield gc
def __init__(self, fileName, isRdb=False):
TsvReader.__init__(self, fileName, typeMap=typeMap, isRdb=isRdb)
