def classify(self,db,fastain):
proIDs,features,labels = [],[],[]
prevFeatureset = ''
prevText = ''
for seq_record in SeqIO.parse(fastain, "fasta"):
title = seq_record.id
toks = title.split("|")
proteinID = toks[5]
query_rows = genbank.proteinQuery(proteinID,db)
ids,text = zip(*query_rows)
text = ''.join(map(str,text))
if text=='':
label = ['na']
else:
text = word_reg.findall(text)
featureset = self.gene_features(text)
assert text!=prevText
assert featureset!=prevFeatureset
prevFeatureset = featureset
prevText = text
label = self.classifier.batch_classify([featureset])
proIDs.append(proteinID)
labels+=label
return zip(proIDs,labels)
