def processUPGMA(self):
self.log.debug("Computing the associated matrix")
# Serialize the symbols
(serialSymbols, formatSymbols) = TypeConvertor.serializeSymbols(self.symbols, self.unitSize, self.scores)
self.log.debug("Clustering input format " + formatSymbols)
# Execute the Clustering part in C
debug = False
logging.debug("Execute the clustering part in C ...")
(i_max, j_max, maxScore, scores) = _libNeedleman.getHighestEquivalentGroup(self.doInternalSlick, len(self.symbols), formatSymbols, serialSymbols, self.cb_executionStatus, debug)
listScores = TypeConvertor.deserializeScores(self.symbols, scores)
# Retrieve the scores for each association of symbols
self.scores = {}
for (iuid, juid, score) in listScores:
if iuid not in self.scores.keys():
self.scores[iuid] = {}
if juid not in self.scores.keys():
self.scores[juid] = {}
self.scores[iuid][juid] = score
if iuid not in self.scores[juid].keys():
self.scores[juid][iuid] = score
# Reduce the UPGMA matrix (merge symbols by similarity)
self.computePhylogenicTree()
return (i_max, j_max, maxScore)
def deserializeGroups(self, symbols):
# First we serialize the messages
(serialSymbols, format) = TypeConvertor.serializeSymbols(symbols, self.unitSize, self.scores)
debug = False
return _libNeedleman.deserializeGroups(len(symbols), format, serialSymbols, debug)
