def load(self, dictionary):
State.load(self, dictionary)
if 'backgroundprob' not in dictionary:
raise ParseException("Backround probability was not found in state")
self.backgroundProbability = [tuple(x)
for x in dictionary['backgroundprob']]
if 'time' not in dictionary:
raise ParseException('Time was not found in state')
self.time = dictionary['time']
if 'transitionmatrix' not in dictionary:
raise ParseException('Transition matrix not found in state')
self.transitionMatrix = dictionary['transitionmatrix']
if 'consensusdistribution' in dictionary:
self.consensusDistribution = default_dist(normalize_dict(
dictionary['consensusdistribution'],
mathType=self.mathType
))
else:
self.consensusDistribution = defaultdict(lambda *x: self.mathType(1.0))
if 'repeatlengthdistribution' in dictionary:
tp = type(dictionary['repeatlengthdistribution'])
if tp in [dict, defaultdict]:
self.repeatLengthDistribution = \
default_dist(normalize_dict(
dictionary['repeatlengthdistribution'],
mathType=self.mathType
))
else:
self.repeatLengthDistribution = \
dictionary['repeatlengthdistribution']
self.repProb = self.repeatLengthDistribution.p
if 'trackemissions' in dictionary:
self.trackEmissions = dictionary['trackemissions']
if 'version' in dictionary:
self.version = dictionary['version']
else:
self.version = 'v1'
if 'repprob' in dictionary:
self.repProb = self.mathType(dictionary['repprob'])
if self.version == 'v2':
self.trackEmissions = defaultdict(lambda *_: self.mathType(1.0))
self.trackEmissions['MM'] = self.mathType(1.0)
self.repeatLengthDistribution = defaultdict(lambda *_:
self.mathType(1.0))
self.repeatLengthDistribution[10] = self.mathType(1.0)
self.factory = RepeatProfileFactory(self.mathType, self.version,
self.repProb)
self.factory.backgroudProbability = self.backgroundProbability
self.factory.time = self.time
self.factory.transitionMatrix = self.transitionMatrix
def improveModel(self, transitions, emissions):
self.clearCache()
back = list(normalize_dict(emissions['I'], self.mathType).iteritems())
self.backgroundProbability = back
self.factory.backgroudProbability = back
eqprob = emissions['M'][1] / sum(emissions['M'].values())
time = -3.0/4.0 * (math.log((self.mathType(4.0) * eqprob - 1.0)/3.0))
self.time = time
self.factory.time = time
totals = defaultdict(self.mathType)
for k, v in transitions.iteritems():
totals[k[:-1]] += v
for state in transitions:
transitions[state] /= totals[state[:-1]]
self.transitionMatrix = transitions
self.factory.transitionMatrix = transitions
def main(model_file, additional_parameters,
emmisions_file, transitions_file, repeat_consensus_file,
repeat_length_file, trf_cover_file, output_file, simple_model):
loader = HMMLoader()
with Open(trf_cover_file, 'r') as f:
trf_cover = json.load(f)
if not simple_model:
repeat_probability = (float(trf_cover['R_segment_count']) /
(trf_cover['R_segment_count'] +
trf_cover['M_count']))
repeat_count = sum([trf_cover[x] for x in ['RR', 'RM', 'MR']])
repeat_repeat_probability = float(trf_cover['RR']) / repeat_count
nothing_repeat_probability = float(trf_cover['MR']) / repeat_count
repeat_nothing_probability = float(trf_cover['RM']) / repeat_count
loader.addDictionary('trackemi', {"value": {
'RR': 0.0,#repeat_repeat_probability,
'RM': repeat_nothing_probability,
'MR': nothing_repeat_probability,
}})
for k, v in additional_parameters.iteritems():
loader.addDictionary(k, v)
# Parse emissions
with Open(emmisions_file, 'r') as f:
emm = normalize_dict(json.load(f))
emm = [(ast.literal_eval(k), v) for k, v in emm.iteritems()]
loader.addDictionary('MatchStateEmissions', {'value': emm})
background_prob = defaultdict(int)
for ((r1, r2), v) in emm:
background_prob[r1] += v
background_prob[r2] += v
background_prob = \
{'value': list(normalize_dict(background_prob).iteritems())}
loader.addDictionary('background-probability', background_prob)
# Parse transitions
with Open(transitions_file, 'r') as f:
__trans = json.load(f)
trans = dict()
for k, v in __trans.iteritems():
trans[''.join(ast.literal_eval(k))] = v
trans = normalize_tuple_dict(trans)
if not simple_model:
for k in trans:
trans[k] *= (1 - repeat_probability)
trans['MR'] = repeat_probability
trans['XR'] = repeat_probability
trans['YR'] = repeat_probability
trans['RR'] = repeat_probability
trans['RX'] = (1 - repeat_probability) / 3
trans['RY'] = (1 - repeat_probability) / 3
trans['RM'] = (1 - repeat_probability) / 3
loader.addDictionary('trans', trans)
# Parse emissions from trf
if not simple_model:
loader.addFile('consensus.js',
os.path.relpath(os.path.abspath(repeat_consensus_file),
os.path.dirname(model_file)))
loader.addFile('repeatlength.js', os.path.abspath(repeat_length_file))
model = loader.load(model_file)
json_prep = {'model': model['model'].toJSON()}
with Open(output_file, 'w') as f:
json.dump(json_prep, f, indent=4)
return output_file
def main(model_file, additional_parameters,
emmisions_file, transitions_file, repeat_consensus_file,
repeat_length_file, trf_cover_file, output_file, simple_model):
loader = HMMLoader()
with Open(trf_cover_file, 'r') as f:
trf_cover = json.load(f)
if not simple_model:
repeat_probability = (float(trf_cover['R_segment_count']) /
(trf_cover['R_segment_count'] +
trf_cover['M_count']))
repeat_count = sum([trf_cover[x] for x in ['RR', 'RM', 'MR']])
repeat_repeat_probability = float(trf_cover['RR']) / repeat_count
nothing_repeat_probability = float(trf_cover['MR']) / repeat_count
repeat_nothing_probability = float(trf_cover['RM']) / repeat_count
loader.addDictionary('trackemi', {"value": {
'RR': repeat_repeat_probability,
'RM': repeat_nothing_probability,
'MR': nothing_repeat_probability,
}})
for k, v in additional_parameters.iteritems():
loader.addDictionary(k, v)
# Parse emissions
with Open(emmisions_file, 'r') as f:
emm = normalize_dict(json.load(f))
emm = [(ast.literal_eval(k), v) for k, v in emm.iteritems()]
loader.addDictionary('MatchStateEmissions', {'value': emm})
background_prob = defaultdict(int)
for ((r1, r2), v) in emm:
background_prob[r1] += v
background_prob[r2] += v
background_prob = \
{'value': list(normalize_dict(background_prob).iteritems())}
loader.addDictionary('background-probability', background_prob)
# Parse transitions
with Open(transitions_file, 'r') as f:
__trans = json.load(f)
trans = dict()
for k, v in __trans.iteritems():
trans[''.join(ast.literal_eval(k))] = v
trans = normalize_tuple_dict(trans)
if not simple_model:
for k in trans:
trans[k] *= (1 - repeat_probability)
trans['MR'] = repeat_probability
trans['XR'] = repeat_probability
trans['YR'] = repeat_probability
trans['RR'] = repeat_probability
trans['RX'] = (1 - repeat_probability) / 3
trans['RY'] = (1 - repeat_probability) / 3
trans['RM'] = (1 - repeat_probability) / 3
loader.addDictionary('trans', trans)
# Parse emissions from trf
if not simple_model:
loader.addFile('consensus.js',
os.path.relpath(os.path.abspath(repeat_consensus_file),
os.path.dirname(model_file)))
loader.addFile('repeatlength.js', os.path.abspath(repeat_length_file))
model = loader.load(model_file)
json_prep = {'model': model['model'].toJSON()}
with Open(output_file, 'w') as f:
json.dump(json_prep, f, indent=4)
return output_file
