def test_ChainSeparator( self ):
"""ChainSeparator test"""
self.sep = ChainSeparator( self.fname, self.outPath, 1)
self.chain = self.sep.next()
i=1
all_chains = []
while self.chain <> None:
if self.local:
print 'Chain %i:'%i, ''.join(singleAA(self.chain.sequence() ) )
all_chains += self.chain.sequence()
self.chain = self.sep.next()
i += 1
if self.local:
print 'ChainSeparator log file written to: %s'%self.sep.log.fname
r = ''.join( singleAA( all_chains ) )
self.assertEqual(r, self.EXPECTED)
def test_ChainSeparator(self):
"""ChainSeparator test"""
self.sep = ChainSeparator(self.fname, self.outPath, 1)
self.chain = self.sep.next()
i = 1
all_chains = []
while self.chain <> None:
if self.local:
print 'Chain %i:' % i, ''.join(singleAA(self.chain.sequence()))
all_chains += self.chain.sequence()
self.chain = self.sep.next()
i += 1
if self.local:
print 'ChainSeparator log file written to: %s' % self.sep.log.fname
r = ''.join(singleAA(all_chains))
self.assertEqual(r, self.EXPECTED)
def _removeDuplicateChains(self, chainMask=None):
"""
Get rid of identical chains by comparing all chains with Blast2seq.
@param chainMask: chain mask for overriding the
chain identity checking (default: None)
@type chainMask: [int]
@return: number of chains removed
@rtype: int
"""
chainCount = len(self.chains)
matrix = 1.0 * N.zeros((chainCount,chainCount))
chain_ids = []
## create identity matrix for all chains against all chains
for i in range(0, chainCount):
chain_ids = chain_ids + [self.chains[i].chain_id] # collect for log file
for j in range(i, len(self.chains)):
# convert 3-letter-code res list into 1-letter-code String
seq1 = singleAA( self.chains[i].sequence() )
seq2 = singleAA( self.chains[j].sequence() )
## if len(seq1) > len(seq2): # take shorter sequence
## # aln len at least half the len of the shortest sequence
## alnCutoff = len(seq2) * 0.5
## else:
## alnCutoff = len(seq1) * 0.5
## if id['aln_len'] > alnCutoff:
## matrix[i,j] = id['aln_id']
## else: # aln length too short, ignore
## matrix[i,j] = 0
matrix[i,j] = self._compareSequences( seq1, seq2 )
## report activity
self.log.add("\n Chain ID's of compared chains: "+str(chain_ids))
self.log.add(" Cross-Identity between chains:\n"+str(matrix))
self.log.add(" Identity threshold used: "+str(self.threshold))
## override the automatic chain deletion by supplying a
## chain mask to this function
if chainMask:
if len(chainMask) == chainCount:
self.chains = N.compress(chainMask, self.chains)
self.log.add("NOTE: chain mask %s used for removing chains.\n"%chainMask)
else:
self.log.add("########## ERROR ###############")
self.log.add("# Chain mask is only %i chains long"%len(chainMask))
self.log.add("# when a mask of length %i is needed"%chainCount)
self.log.add("# No cleaning will be performed.\n")
if not chainMask:
## look at diagonals in "identity matrix"
## (each chain against each)
duplicate = len(self.chains)
for offset in range(1,chainCount):
diag = N.diagonal(matrix, offset ,0,1)
# diagonal of 1's mark begin of duplicate
avg = 1.0 * N.sum(diag)/len(diag)
if (avg >= self.threshold):
duplicate = offset
break
self.chains = self.chains[:duplicate]
self.log.add("NOTE: Identity matrix will be used for removing identical chains.")
## report activit
self.log.add(str(chainCount - len(self.chains))+\
" chains have been removed.\n")
# how many chains have been removed?
return (chainCount - len(self.chains))
def _removeDuplicateChains(self, chainMask=None):
"""
Get rid of identical chains by comparing all chains with Blast2seq.
@param chainMask: chain mask for overriding the
chain identity checking (default: None)
@type chainMask: [int]
@return: number of chains removed
@rtype: int
"""
chainCount = len(self.chains)
matrix = 1.0 * N.zeros((chainCount, chainCount))
chain_ids = []
## create identity matrix for all chains against all chains
for i in range(0, chainCount):
chain_ids = chain_ids + [self.chains[i].chain_id
] # collect for log file
for j in range(i, len(self.chains)):
# convert 3-letter-code res list into 1-letter-code String
seq1 = singleAA(self.chains[i].sequence())
seq2 = singleAA(self.chains[j].sequence())
## if len(seq1) > len(seq2): # take shorter sequence
## # aln len at least half the len of the shortest sequence
## alnCutoff = len(seq2) * 0.5
## else:
## alnCutoff = len(seq1) * 0.5
## if id['aln_len'] > alnCutoff:
## matrix[i,j] = id['aln_id']
## else: # aln length too short, ignore
## matrix[i,j] = 0
matrix[i, j] = self._compareSequences(seq1, seq2)
## report activity
self.log.add("\n Chain ID's of compared chains: " + str(chain_ids))
self.log.add(" Cross-Identity between chains:\n" + str(matrix))
self.log.add(" Identity threshold used: " + str(self.threshold))
## override the automatic chain deletion by supplying a
## chain mask to this function
if chainMask:
if len(chainMask) == chainCount:
self.chains = N.compress(chainMask, self.chains)
self.log.add(
"NOTE: chain mask %s used for removing chains.\n" %
chainMask)
else:
self.log.add("########## ERROR ###############")
self.log.add("# Chain mask is only %i chains long" %
len(chainMask))
self.log.add("# when a mask of length %i is needed" %
chainCount)
self.log.add("# No cleaning will be performed.\n")
if not chainMask:
## look at diagonals in "identity matrix"
## (each chain against each)
duplicate = len(self.chains)
for offset in range(1, chainCount):
diag = N.diagonal(matrix, offset, 0, 1)
# diagonal of 1's mark begin of duplicate
avg = 1.0 * N.sum(diag) / len(diag)
if (avg >= self.threshold):
duplicate = offset
break
self.chains = self.chains[:duplicate]
self.log.add(
"NOTE: Identity matrix will be used for removing identical chains."
)
## report activit
self.log.add(str(chainCount - len(self.chains))+\
" chains have been removed.\n")
# how many chains have been removed?
return (chainCount - len(self.chains))