def run(nstates, nsamples):
# Load force data.
from netCDF4 import Dataset
ncfile = Dataset('rnase-h-d10a-trace47.nc', 'r')
tau = 0.001 # 1 kHz
obs_label = 'force / pN'
time_units = 's' # seconds
o_t = ncfile.variables['force'] # load trace
# copy data
o_t = o_t[:]
O = [o_t] # form list of traces
# Initialize MLHMM.
print "Initializing MLHMM with " + str(nstates) + " states."
estimator = bhmm.MLHMM(O, nstates)
# Plot initial guess.
plots.plot_state_assignments(
estimator.hmm,
None,
O[0],
time_units=time_units,
obs_label=obs_label,
tau=tau,
pdf_filename='RNAseH_trace47-guess-stateassignments-nstates' +
str(nstates) + '.pdf')
# Fit HMM.
mle = estimator.fit()
# Plot.
plots.plot_state_assignments(
mle,
mle.hidden_state_trajectories[0],
o_t,
time_units=time_units,
obs_label=obs_label,
tau=tau,
pdf_filename='RNAseH_trace47-mlhmm-stateassignments-nstates' +
str(nstates) + '.pdf')
# Initialize BHMM, using MLHMM model as initial model.
print "Initializing BHMM and running with " + str(nsamples) + " samples."
sampler = bhmm.BHMM(O, nstates, initial_model=mle)
# Sample models.
bhmm_models = sampler.sample(nsamples=nsamples,
save_hidden_state_trajectory=False)
# Generate a sample saving a hidden state trajectory.
final_models = sampler.sample(nsamples=1,
save_hidden_state_trajectory=True)
# Plot.
model = final_models[0]
s_t = model.hidden_state_trajectories[0]
o_t = O[0]
plots.plot_state_assignments(
model,
s_t,
o_t,
time_units=time_units,
obs_label=obs_label,
tau=tau,
pdf_filename='RNAseH_trace47-bhmm-stateassignments-nstates' +
str(nstates) + '.pdf')
# write latex table with sample statistics
conf = 0.95
sampled_hmm = bhmm.SampledGaussianHMM(mle, bhmm_models)
generate_latex_table(
sampled_hmm,
conf=conf,
dt=tau,
time_unit='s',
caption='Bayesian HMM parameter estimates for RNAse-H data.',
outfile='rnase-h-bhmm-statistics-table.tex')
return table
if __name__ == "__main__":
# Set verbosity.
bhmm.config.verbose = True
# Make figures directory.
directory = 'figures'
if not os.path.exists(directory):
os.makedirs(directory)
# Generate data.
nobservations = 100000
[true_hmm, O, S] = generate_synthetic_data(nobservations)
# Analyze data.
nstates = 3
[mle1, bhmm_models1] = analyze_data(O, nstates, nobservations=1000)
[mle2, bhmm_models2] = analyze_data(O, nstates, nobservations=10000)
[mle3, bhmm_models3] = analyze_data(O, nstates, nobservations=100000)
# Write latex table with true and inferred sample statistics.
conf = 0.95 # confidence interval
sampled_hmm_models = [ bhmm.SampledGaussianHMM(mle1, bhmm_models1), bhmm.SampledGaussianHMM(mle2, bhmm_models2), bhmm.SampledGaussianHMM(mle3, bhmm_models3)]
generate_latex_table(true_hmm, sampled_hmm_models, conf=conf, dt=1, time_unit='ms',
outfile='synthetic-three-state-model-bhmm-statistics.tex')
def run(nstates, nsamples):
# Create model.
true_model = testsystems.force_spectroscopy_model()
nstates = true_model.nstates
tau = 0.001 # time interval per observation
# Generate synthetic data.
print "Generating synthetic data..."
[O, S] = true_model.generate_synthetic_observation_trajectories(
ntrajectories=1, length=50000)
# DEBUG
print "synthetic observation trajectories:"
print O
print "Total state visits, min_state, max_state:"
print testsystems.total_state_visits(nstates, S)
# Generate MLHMM.
print "Generating MLHMM..."
estimator = bhmm.MLHMM(O, nstates)
print "Initial guess:"
print str(estimator.hmm.output_model)
print estimator.hmm.transition_matrix
print estimator.hmm.stationary_distribution
# Plot initial guess.
s_t = None
o_t = O[0]
plots.plot_state_assignments(
estimator.hmm,
s_t,
o_t,
time_units='s',
obs_label='force / pN',
tau=tau,
pdf_filename='synthetic-three-state-model-guess-nstates' +
str(nstates) + '.pdf')
print "Fitting HMM..."
mle = estimator.fit()
# Plot.
s_t = mle.hidden_state_trajectories[0]
import numpy as np
o_t = O[0]
plots.plot_state_assignments(
mle,
s_t,
o_t,
time_units='s',
obs_label='force / pN',
tau=tau,
pdf_filename='synthetic-three-state-model-mlhmm-nstates' +
str(nstates) + '.pdf')
# Initialize BHMM with MLHMM model.
print "Sampling models from BHMM..."
sampler = bhmm.BHMM(O, nstates, initial_model=mle)
bhmm_models = sampler.sample(nsamples=nsamples,
save_hidden_state_trajectory=False)
# Generate a sample saving a hidden state trajectory.
final_models = sampler.sample(nsamples=1,
save_hidden_state_trajectory=True)
# Plot final BHMM sample.
model = final_models[0]
s_t = model.hidden_state_trajectories[0]
o_t = O[0]
plots.plot_state_assignments(
model,
s_t,
o_t,
time_units='s',
obs_label='force / pN',
tau=tau,
pdf_filename='synthetic-three-state-model-bhmm-nstates' +
str(nstates) + '.pdf')
# write latex table with sample statistics
conf = 0.95
sampled_hmm = bhmm.SampledGaussianHMM(mle, bhmm_models)
generate_latex_table(
sampled_hmm,
conf=conf,
dt=1,
time_unit='step',
caption=
'Bayesian HMM parameter estimates for synthetic three-state model.',
outfile='synthetic-three-state-model-bhmm-statistics.tex')
def run(nstates, nsamples):
# Load force data.
from netCDF4 import Dataset
ncfile = Dataset('fiber3-trace011.nc', 'r')
tau = 0.001 # 1 kHz
obs_label = 'force / pN'
time_units = 's' # seconds
o_t = ncfile.variables['force'] # load trace
# force to make a copy because netCDF appears to cause problems
nsubsample = 50 # subsampling rate
o_t = o_t[::nsubsample]
tau *= nsubsample
# -------------------
O = [o_t] # form list of traces
# Initialize MLHMM.
print "Initializing MLHMM with " + str(nstates) + " states."
estimator = bhmm.MLHMM(O, nstates)
# Plot initial guess.
plots.plot_state_assignments(
estimator.hmm,
None,
O[0],
time_units=time_units,
obs_label=obs_label,
tau=tau,
pdf_filename='fiber3-trace11-guess-stateassignments-nstate' +
str(nstates) + '.pdf')
# Fit MLHMM
mle = estimator.fit()
# Plot.
plots.plot_state_assignments(
mle,
mle.hidden_state_trajectories[0],
o_t,
time_units=time_units,
obs_label=obs_label,
tau=tau,
pdf_filename='fiber3-trace11-mlhmm-stateassignments-nstate' +
str(nstates) + '.pdf')
# Initialize BHMM, using MLHMM model as initial model.
print "Initializing BHMM and running with " + str(nsamples) + " samples."
sampler = bhmm.BHMM(O, nstates, initial_model=mle)
# Sample models.
bhmm_models = sampler.sample(nsamples=nsamples,
save_hidden_state_trajectory=False)
# Generate a sample saving a hidden state trajectory.
final_models = sampler.sample(nsamples=1,
save_hidden_state_trajectory=True)
# Plot.
model = final_models[0]
s_t = model.hidden_state_trajectories[0]
o_t = O[0]
plots.plot_state_assignments(
model,
s_t,
o_t,
time_units=time_units,
obs_label=obs_label,
tau=tau,
pdf_filename='fiber3-trace11-bhmm-stateassignments-nstate' +
str(nstates) + '.pdf')
# write latex table with sample statistics
conf = 0.95
sampled_hmm = bhmm.SampledGaussianHMM(mle, bhmm_models)
generate_latex_table(sampled_hmm,
conf=conf,
dt=tau,
time_unit='s',
caption='BHMM model estimates for RNA hairpin data.',
outfile='p5ab-bhmm-statistics-table' + str(nstates) +
'.tex')