def get_predictions(self, sequence, positions):
seqlen = self.window_right + self.window_left + 2
num = len(positions)
testdat = []
for j in xrange(num):
i = positions[j] - self.offset
s = sequence[i - self.window_left:i + self.window_right + 2]
testdat.append(s)
t = StringCharFeatures(DNA)
t.set_string_features(testdat)
self.wd_kernel.init(self.traindat, t)
l = self.svm.classify().get_labels()
sys.stderr.write("\n...done...\n")
return l
def get_predictions(self, sequence, positions):
seqlen=self.window_right+self.window_left+2
num=len(positions)
testdat = []
for j in xrange(num):
i=positions[j] - self.offset ;
s=sequence[i-self.window_left:i+self.window_right+2]
testdat.append(s)
t=StringCharFeatures(DNA)
t.set_string_features(testdat)
self.wd_kernel.init(self.traindat, t)
l=self.svm.classify().get_labels()
sys.stderr.write("\n...done...\n")
return l
def get_predictions_from_seqdict(self, seqdic, site):
""" we need to generate a huge test features object
containing all locations found in each seqdict-sequence
and each location (this is necessary to efficiently
(==fast,low memory) compute the splice outputs
"""
seqlen=self.window_right+self.window_left+2
num=0
for s in seqdic:
num+= len(s.preds[site].positions)
testdat = []
for s in seqdic:
sequence=s.seq
positions=s.preds[site].positions
for j in xrange(len(positions)):
i=positions[j] - self.offset
s=sequence[i-self.window_left:i+self.window_right+2]
testdat.append(s)
t=StringCharFeatures(DNA)
t.set_string_features(testdat)
self.wd_kernel.init(self.traindat, t)
l=self.svm.classify().get_labels()
sys.stderr.write("\n...done...\n")
k=0
for s in seqdic:
num=len(s.preds[site].positions)
scores= num * [0]
for j in xrange(num):
scores[j]=l[k]
k+=1
s.preds[site].set_scores(scores)