def run( self, args ):
self.reader = ConanCountsReader( args.cncnt_file_name )
self.writer = ConanSnvMixWriter( args.cnsm_file_name )
ModelRunner.run( self, args )
class ConanModelRunner( ModelRunner ):
def __init__( self ):
ModelRunner.__init__( self )
self.data_class = JointData
self.parameters = {}
self.priors = {}
def run( self, args ):
self.reader = ConanCountsReader( args.cncnt_file_name )
self.writer = ConanSnvMixWriter( args.cnsm_file_name )
ModelRunner.run( self, args )
def _classify( self, args ):
cn_states = self.reader.get_cn_states()
for cn_state in sorted( cn_states ):
self._classify_cn_state( cn_state )
def _classify_cn_state( self, cn_state ):
chr_list = self.reader.get_chr_list( cn_state )
for chr_name in sorted( chr_list ):
self._classify_chromosome( cn_state, chr_name )
def _train( self, args ):
cn_states = self.reader.get_cn_states()
for cn_state in sorted( cn_states ):
self._train_cn_state( cn_state, args )
self._write_priors()
def _train_cn_state( self, cn_state, args ):
if args.subsample_size > 0:
counts = self._subsample( cn_state, args.subsample_size )
else:
counts = self.reader.get_counts()
nclass = {}
nclass['normal'] = 3
nclass['tumour'] = constants.cn_state_map[cn_state]
priors = self._get_priors( nclass )
model = self.model_class( nclass )
data = self.data_class( counts )
self.parameters[cn_state] = model.train(
data, priors,
args.max_iters,
args.convergence_threshold
)
self.priors[cn_state] = priors
def _classify_chromosome( self, cn_state, chr_name ):
nclass = {}
nclass['normal'] = 3
nclass['tumour'] = constants.cn_state_map[cn_state]
model = self.model_class( nclass )
counts = self.reader.get_counts( cn_state, chr_name )
jcnt_rows = self.reader.get_rows( cn_state, chr_name )
end = self.reader.get_chr_size( cn_state, chr_name )
n = int( 1e5 )
start = 0
stop = min( n, end )
while start < end:
sub_counts = counts[start:stop]
sub_rows = jcnt_rows[start:stop]
data = self.data_class( sub_counts )
resp = model.classify( data, self.parameters[cn_state] )
self.writer.write_data( cn_state, chr_name, sub_rows, resp )
start = stop
stop = min( stop + n, end )
def _subsample( self, cn_state, sample_size ):
chr_list = self.reader.get_chr_list( cn_state )
sample = []
nrows = self.reader.get_data_set_size( cn_state )
for chr_name in chr_list:
chr_size = self.reader.get_chr_size( cn_state, chr_name )
chr_sample_size = math.floor( float( chr_size ) / nrows * sample_size )
chr_sample_size = int( chr_sample_size )
chr_sample_size = min( chr_size, chr_sample_size )
chr_sample_indices = random.sample( xrange( chr_size ), chr_sample_size )
chr_counts = self.reader.get_counts( cn_state, chr_name )
chr_sample = chr_counts[chr_sample_indices]
sample.append( chr_sample )
sample = np.vstack( sample )
return sample