def centerFrames(self):
"""
Get indices for frame nearest to each cluster center.
@return: list of cluster center indecies
@rtype: [int]
"""
return N0.argmax(self.memberships(), 1)
def argmax(self, key):
"""
@param key: item attribute
@type key: any
@return: index of item with highest item[key] value
@rtype: int
"""
vLst = self.valuesOf(key)
return N0.argmax(vLst)
def argmax( self, infoKey ):
"""
Get index of complex c with highest c.infos[infokey] value
@param infoKey: key for info dict
@type infoKey: str
@return: index of complex c with highest c.infos[infokey] value
@rtype: int
"""
vLst = self.valuesOf( infoKey )
return N0.argmax( vLst )
def memberFrames(self, threshold=0.):
"""
Get indices of all frames belonging to each cluster. Each frame
is guaranteed to belong, at least, to the cluster for which it has
its maximum membership. If threshold > 0, it can additionally pop
up in other clusters.
@param threshold: minimal cluster membership or 0 to consider
only max membership (default: 0)
@type threshold: float
@return: n_cluster, lst of lst of int, frame indices
@rtype: [[int]]
"""
## best cluster for each frame
msm = self.memberships()
maxMemb = N0.argmax(msm, 0)
r = [
N0.nonzero(N0.equal(maxMemb, i))
for i in range(0, self.n_clusters)
]
r = [x.tolist() for x in r]
## same thing but now taking all above threshold
## -> same frame can end up in several clusters
if threshold > 0.:
r2 = [N0.nonzero(N0.greater(l, threshold)) for l in msm]
## add only additional frames
for i in range(0, len(r)):
try:
frames = r[i].tolist()
except:
frames = r[i]
r[i] = frames + [fr for fr in r2[i] if fr not in r[i]]
## sort frames within each cluster by their membership
r = [self.membershipSort(r[i], i) for i in range(0, len(r))]
return r
def max(self):
"""
Max height of distribution.
"""
index = N0.argmax(self.p)
return self.x[index]
def parse_result(self):
"""
Extract some information about the profile as well as the
match state emmission scores. Keys of the returned dictionary::
'AA', 'name', 'NrSeq', 'emmScore', 'accession',
'maxAllScale', 'seqNr', 'profLength', 'ent', 'absSum'
@return: dictionary with warious information about the profile
@rtype: dict
"""
## check that the outfut file is there and seems valid
if not os.path.exists(self.f_out):
raise HmmerError,\
'Hmmerfetch result file %s does not exist.'%self.f_out
if T.fileLength(self.f_out) < 10:
raise HmmerError,\
'Hmmerfetch result file %s seems incomplete.'%self.f_out
profileDic = {}
## read result
hmm = open(self.f_out, 'r')
out = hmm.read()
hmm.close()
## collect some data about the hmm profile
profileDic['name'] = self.hmmName
profileDic['profLength'] = \
int( string.split(re.findall('LENG\s+[0-9]+', out)[0])[1] )
profileDic['accession'] = \
string.split(re.findall('ACC\s+PF[0-9]+', out)[0])[1]
profileDic['NrSeq'] = \
int( string.split(re.findall('NSEQ\s+[0-9]+', out)[0])[1] )
profileDic['AA'] = \
string.split(re.findall('HMM[ ]+' + '[A-Y][ ]+'*20, out)[0] )[1:]
## collect null emmission scores
pattern = 'NULE[ ]+' + '[-0-9]+[ ]+' * 20
nullEmm = [
float(j) for j in string.split(re.findall(pattern, out)[0])[1:]
]
## get emmision scores
prob = []
for i in range(1, profileDic['profLength'] + 1):
pattern = "[ ]+%i" % i + "[ ]+[-0-9]+" * 20
e = [float(j) for j in string.split(re.findall(pattern, out)[0])]
prob += [e]
profileDic['seqNr'] = N0.transpose(N0.take(prob, (0, ), 1))
profileDic['emmScore'] = N0.array(prob)[:, 1:]
## calculate emission probablitities
emmProb, nullProb = self.hmmEmm2Prob(nullEmm, profileDic['emmScore'])
ent = [
N0.resize(self.entropy(e, nullProb), (1, 20))[0] for e in emmProb
]
profileDic['ent'] = N0.array(ent)
###### TEST #####
proba = N0.array(prob)[:, 1:]
## # test set all to max score
## p = proba
## p1 = []
## for i in range( len(p) ):
## p1 += [ N0.resize( p[i][N0.argmax( N0.array( p[i] ) )] , N0.shape( p[i] ) ) ]
## profileDic['maxAll'] = p1
# test set all to N0.sum( abs( probabilities ) )
p = proba
p2 = []
for i in range(len(p)):
p2 += [N0.resize(N0.sum(N0.absolute(p[i])), N0.shape(p[i]))]
profileDic['absSum'] = p2
# set all to normalized max score
p = proba
p4 = []
for i in range(len(p)):
p_scale = (p[i] - N0.average(p[i])) / math.SD(p[i])
p4 += [
N0.resize(p_scale[N0.argmax(N0.array(p_scale))],
N0.shape(p[i]))
]
profileDic['maxAllScale'] = p4
return profileDic
def parse_result( self ):
"""
Extract some information about the profile as well as the
match state emmission scores. Keys of the returned dictionary::
'AA', 'name', 'NrSeq', 'emmScore', 'accession',
'maxAllScale', 'seqNr', 'profLength', 'ent', 'absSum'
@return: dictionary with warious information about the profile
@rtype: dict
"""
## check that the outfut file is there and seems valid
if not os.path.exists( self.f_out ):
raise HmmerError,\
'Hmmerfetch result file %s does not exist.'%self.f_out
if T.fileLength( self.f_out ) < 10:
raise HmmerError,\
'Hmmerfetch result file %s seems incomplete.'%self.f_out
profileDic = {}
## read result
hmm = open( self.f_out, 'r')
out = hmm.read()
hmm.close()
## collect some data about the hmm profile
profileDic['name'] = self.hmmName
profileDic['profLength'] = \
int( string.split(re.findall('LENG\s+[0-9]+', out)[0])[1] )
profileDic['accession'] = \
string.split(re.findall('ACC\s+PF[0-9]+', out)[0])[1]
profileDic['NrSeq'] = \
int( string.split(re.findall('NSEQ\s+[0-9]+', out)[0])[1] )
profileDic['AA'] = \
string.split(re.findall('HMM[ ]+' + '[A-Y][ ]+'*20, out)[0] )[1:]
## collect null emmission scores
pattern = 'NULE[ ]+' + '[-0-9]+[ ]+'*20
nullEmm = [ float(j) for j in string.split(re.findall(pattern, out)[0])[1:] ]
## get emmision scores
prob=[]
for i in range(1, profileDic['profLength']+1):
pattern = "[ ]+%i"%i + "[ ]+[-0-9]+"*20
e = [ float(j) for j in string.split(re.findall(pattern, out)[0]) ]
prob += [ e ]
profileDic['seqNr'] = N0.transpose( N0.take( prob, (0,),1 ) )
profileDic['emmScore'] = N0.array(prob)[:,1:]
## calculate emission probablitities
emmProb, nullProb = self.hmmEmm2Prob( nullEmm, profileDic['emmScore'])
ent = [ N0.resize( self.entropy(e, nullProb), (1,20) )[0] for e in emmProb ]
profileDic['ent'] = N0.array(ent)
###### TEST #####
proba = N0.array(prob)[:,1:]
## # test set all to max score
## p = proba
## p1 = []
## for i in range( len(p) ):
## p1 += [ N0.resize( p[i][N0.argmax( N0.array( p[i] ) )] , N0.shape( p[i] ) ) ]
## profileDic['maxAll'] = p1
# test set all to N0.sum( abs( probabilities ) )
p = proba
p2 = []
for i in range( len(p) ) :
p2 += [ N0.resize( N0.sum( N0.absolute( p[i] )), N0.shape( p[i] ) ) ]
profileDic['absSum'] = p2
# set all to normalized max score
p = proba
p4 = []
for i in range( len(p) ) :
p_scale = (p[i] - N0.average(p[i]) )/ math.SD(p[i])
p4 += [ N0.resize( p_scale[N0.argmax( N0.array(p_scale) )] ,
N0.shape( p[i] ) ) ]
profileDic['maxAllScale'] = p4
return profileDic