def main(args):
filenames = (args.out_forward, args.out_scaling, args.out_backward)
# aggregate and validate the model parameters
model = DGRP.Model()
model.from_fieldstorage(args)
# see how the states interact with the observations
states = (model.get_recent_state(), model.get_ancient_state(),
model.get_misaligned_state(args.misalignment_effect),
model.get_garbage_state())
# define the transition object
nstates = len(states)
prandom = min(1.0, (nstates / (nstates - 1.0)) / args.region_size)
T = TransitionMatrix.UniformTransitionObject(prandom, nstates)
# make the hmm
hmm = ExternalHMM.ExternalModel(T, states, filenames)
converter = lineario.IntTupleConverter()
o_stream = lineario.SequentialDiskIO(converter, args.obsfile)
hmm.init_dp(o_stream)
o_stream.open_read()
for p, obs in itertools.izip(hmm.posterior(), o_stream.read_forward()):
p_recent, p_ancient, p_misaligned, p_garbage = p
maxpost = get_maxpost(p_recent, p_ancient, p_misaligned, p_garbage)
# show the annotation for this position
annotation = list(obs) + list(p) + [maxpost]
print '\t'.join(str(x) for x in annotation)
o_stream.close()
def get_response_content(fs):
"""
@param fs: a FieldStorage object containing the cgi arguments
@return: a (response_headers, response_text) pair
"""
out = StringIO()
lines = Util.get_stripped_lines(StringIO(fs.param_field))
model = DGRP.Model()
model.from_lines(lines)
# see how the states interact with the observations
states = (model.get_recent_state(), model.get_ancient_state(),
model.get_misaligned_state(fs.misalignment_effect),
model.get_garbage_state())
# define the transition object
nstates = len(states)
prandom = min(1.0, (nstates / (nstates - 1.0)) / fs.region_size)
T = TransitionMatrix.UniformTransitionObject(prandom, nstates)
# use StringIO objects for storage
hmm = ExternalHMM.ExternalModel(T, states, (None, None, None))
converter = lineario.IntTupleConverter()
o_stream = lineario.SequentialStringIO(converter, fs.data_field)
hmm.init_dp(o_stream)
o_stream.open_read()
for p, obs in itertools.izip(hmm.posterior(), o_stream.read_forward()):
p_recent, p_ancient, p_misaligned, p_garbage = p
# get the prior probability of polymorphism conditional on state
p_recent_AA = states[0].get_posterior_distribution(obs)[2]
p_ancient_AA = states[1].get_posterior_distribution(obs)[2]
# compute the posterior probability of a polymorphism
posterior_polymorphism = 0
posterior_polymorphism += p_recent * p_recent_AA
posterior_polymorphism += p_ancient * p_ancient_AA
# Given that a polymorphism occurred,
# get the probability distribution over the
# three non-reference nucleotides.
r = model.seqerr
log_Pr = math.log(r / 4.0)
log_PA = math.log(1 - 3 * r / 4.0)
logs = [
obs[1] * log_PA + obs[2] * log_Pr + obs[3] * log_Pr,
obs[1] * log_Pr + obs[2] * log_PA + obs[3] * log_Pr,
obs[1] * log_Pr + obs[2] * log_Pr + obs[3] * log_PA
]
condmaxpost = math.exp(max(logs) - scipy.misc.logsumexp(logs))
# get the posterior probability distribution
maxpost = posterior_polymorphism * condmaxpost
# show the inference for this position
print >> out, obs, p, maxpost
o_stream.close()
return out.getvalue()
def main(args):
filenames = (args.out_forward, args.out_scaling, args.out_backward)
# aggregate and validate the model parameters
model = DGRP.Model()
model.from_fieldstorage(args)
# see how the states interact with the observations
states = (model.get_recent_state(), model.get_ancient_state(),
model.get_misaligned_state(args.misalignment_effect),
model.get_garbage_state())
# define the transition object
nstates = len(states)
prandom = min(1.0, (nstates / (nstates - 1.0)) / args.region_size)
T = TransitionMatrix.UniformTransitionObject(prandom, nstates)
# make the hmm
hmm = ExternalHMM.ExternalModel(T, states, filenames)
converter = lineario.IntTupleConverter()
o_stream = lineario.SequentialDiskIO(converter, args.obsfile)
hmm.init_dp(o_stream)
o_stream.open_read()
for p, obs in itertools.izip(hmm.posterior(), o_stream.read_forward()):
p_recent, p_ancient, p_misaligned, p_garbage = p
# get the prior probability of polymorphism conditional on state
p_recent_AA = states[0].get_posterior_distribution(obs)[2]
p_ancient_AA = states[1].get_posterior_distribution(obs)[2]
# compute the posterior probability of a polymorphism
posterior_polymorphism = 0
posterior_polymorphism += p_recent * p_recent_AA
posterior_polymorphism += p_ancient * p_ancient_AA
# Given that a polymorphism occurred,
# get the probability distribution over the
# three non-reference nucleotides.
r = model.seqerr
log_Pr = math.log(r / 4.0)
log_PA = math.log(1 - 3 * r / 4.0)
logs = [
obs[1] * log_PA + obs[2] * log_Pr + obs[3] * log_Pr,
obs[1] * log_Pr + obs[2] * log_PA + obs[3] * log_Pr,
obs[1] * log_Pr + obs[2] * log_Pr + obs[3] * log_PA
]
condmaxpost = math.exp(max(logs) - scipy.misc.logsumexp(logs))
# get the posterior probability distribution
maxpost = posterior_polymorphism * condmaxpost
# show the annotation for this position
annotation = list(obs) + list(p) + [maxpost]
print '\t'.join(str(x) for x in annotation)
o_stream.close()
