def main():
global options
D1 = options.disease1
D2 = options.disease2
# Import EMR data into database
database = EMRDatabase()
database.import_data(options.emr_data_file,
options.diseases_file,
options.code2disease_file)
# Instantiate the OptimizeLogLikelihood class
opt_log_likelihood = OptimizeLogLikelihood(options.verbose)
opt_log_likelihood.set_opt_method(options.opt_method)
opt_log_likelihood.set_use_random_seed(options.use_random_seed)
opt_log_likelihood.setup_log_likelihood_func(database,
D1, D2,
options.tau1,
options.tau2,
options.overlap_type,
options.threshold_type,
options.prevalence_file,
options.norm_prval_method)
# Get optimized parameters
_, optimized_param, _ = opt_log_likelihood.run()
# Compute optimization paths
optimization_paths = []
for n in range(options.num_paths):
_, _, path = opt_log_likelihood.run(save_path=True)
optimization_paths.append(path)
log_likelihood_func = opt_log_likelihood.get_log_likelihood_func()
plot = __plot_contour(log_likelihood_func,
optimized_param,
optimization_paths,
options.tau1,
options.tau2,
options.overlap_type,
options.threshold_type,
options.norm_prval_method,
options.verbose)
plt.show()
def main():
global options
database = EMRDatabase()
database.import_data(options.emr_data_file,
options.diseases_file,
options.code2disease_file)
diseases = database.get_diseases()
diseases.sort()
# Create plot for specified disease pair or for all disease pairs with
# non-zero patient counts.
if options.disease1 != None and options.disease2 != None:
funcs = __get_funcs(database,
options.disease1,
options.disease2,
options.verbose)
plt = __plot_figure(funcs,
options.disease1,
options.disease2,
options.verbose)
plt.show()
else:
filtered_diseases = __filter_diseases(diseases, database)
for D1 in filtered_diseases:
for D2 in filtered_diseases:
if D1 == D2: continue
funcs = __get_funcs(database,
D1, D2,
options.verbose)
plt = __plot_figure(funcs,
D1, D2,
options.verbose)
plt.close() # close current figure
def main():
global options
D1 = options.disease1
D2 = options.disease2
# Import EMR data into database
database = EMRDatabase()
database.import_data(options.emr_data_file, options.diseases_file,
options.code2disease_file)
# Instantiate the OptimizeLogLikelihood class
opt_log_likelihood = OptimizeLogLikelihood(options.verbose)
opt_log_likelihood.set_opt_method(options.opt_method)
opt_log_likelihood.set_use_random_seed(options.use_random_seed)
opt_log_likelihood.setup_log_likelihood_func(database, D1, D2,
options.tau1, options.tau2,
options.overlap_type,
options.threshold_type,
options.prevalence_file,
options.norm_prval_method)
# Get optimized parameters
_, optimized_param, _ = opt_log_likelihood.run()
# Compute optimization paths
optimization_paths = []
for n in range(options.num_paths):
_, _, path = opt_log_likelihood.run(save_path=True)
optimization_paths.append(path)
log_likelihood_func = opt_log_likelihood.get_log_likelihood_func()
plot = __plot_contour(log_likelihood_func, optimized_param,
optimization_paths, options.tau1, options.tau2,
options.overlap_type, options.threshold_type,
options.norm_prval_method, options.verbose)
plt.show()
def main():
global options
database = EMRDatabase()
database.import_data(options.emr_data_file,
options.diseases_file,
options.code2disease_file)
diseases = database.get_diseases()
diseases.sort()
# Create plot for the specified disease or all diseases with non-zero
# patient counts.
if options.disease != None:
M_func, F_func, M_count, F_count = __get_funcs(database,
options.disease)
plt = __plot_figure(M_func, F_func, M_count, F_count,
options.disease, options.verbose)
plt.show()
else:
filtered_diseases = __filter_diseases(diseases, database)
for D in filtered_diseases:
M_func, F_func, M_count, F_count = __get_funcs(database, D)
plt = __plot_figure(M_func, F_func, M_count, F_count,
D, options.verbose)
plt.close()
def main():
global options
database = EMRDatabase()
database.import_data(options.emr_data_file, options.diseases_file,
options.code2disease_file)
diseases = database.get_diseases()
diseases.sort()
# Create plot for the specified disease or all diseases with non-zero
# patient counts.
if options.disease != None:
M_func, F_func, M_count, F_count = __get_funcs(database,
options.disease)
plt = __plot_figure(M_func, F_func, M_count, F_count, options.disease,
options.verbose)
plt.show()
else:
filtered_diseases = __filter_diseases(diseases, database)
for D in filtered_diseases:
M_func, F_func, M_count, F_count = __get_funcs(database, D)
plt = __plot_figure(M_func, F_func, M_count, F_count, D,
options.verbose)
plt.close()
def main():
global options
# Import EMR data into database
database = EMRDatabase()
database.import_data(options.emr_data_file, options.diseases_file, options.code2disease_file)
# Instantiate the OptimizeLogLikelihood class
opt_log_likelihood = OptimizeLogLikelihood(options.verbose)
opt_log_likelihood.set_use_random_seed(options.use_random_seed)
f = open("p_value.txt", "w")
f.write("# emr_data_file = %s\n" % options.emr_data_file)
f.write("# norm_prval_method = %s\n" % options.norm_prval_method)
f.write("# threshold_type = %s\n" % options.threshold_type)
f.write("\n")
f.write("# D1, D2, overlap_type, ")
f.write("overlap_LL, indepedent_LL, ")
f.write("LLR, p_value\n")
# Compute p-value for specified disease pair or for all disease pairs with
# non-zero patient counts.
if options.disease1 != None and options.disease2 != None:
D1_list = [options.disease1]
D2_list = [options.disease2]
else:
diseases = database.get_diseases()
diseases.sort()
filtered_diseases = __filter_diseases(diseases, database)
D1_list = filtered_diseases
D2_list = filtered_diseases
for D1 in D1_list:
for D2 in D2_list:
if options.disease1 == None or options.disease2 == None:
if D1 >= D2:
continue
print "-" * 80
print "D1= %s, D2= %s," % (D1, D2),
print "overlap_type= %s" % options.overlap_type
# Independent (no genetic overlap) model
indep_log_likelihood = __compute_log_likelihood_wrapper(
opt_log_likelihood,
database,
D1,
D2,
options.tau1,
options.tau2,
"independent",
options.threshold_type,
options.prevalence_file,
options.norm_prval_method,
)
min_log_likelihood = indep_log_likelihood - 1.0
# Allow genetic overlap model
overlap_log_likelihood = __compute_log_likelihood_wrapper(
opt_log_likelihood,
database,
D1,
D2,
options.tau1,
options.tau2,
options.overlap_type,
options.threshold_type,
options.prevalence_file,
options.norm_prval_method,
min_log_likelihood,
)
log_likelihood_ratio = 2.0 * (overlap_log_likelihood - indep_log_likelihood)
# Degree of freedoms of the chi-square distribution.
dof = 1
# p-value is the area at the right tail of the chi-square
# distribution
p_value = 1.0 - chi2.cdf(log_likelihood_ratio, dof)
text = "%s, %s, %s, " % (D1, D2, options.overlap_type)
text += "%.3E, " % overlap_log_likelihood
text += "%.3E, " % indep_log_likelihood
text += "%.3E, %.3E" % (log_likelihood_ratio, p_value)
print "overlap_LL= %.2E," % overlap_log_likelihood,
print "indep_LL= %.2E," % indep_log_likelihood,
print "LLR= %.2E," % log_likelihood_ratio,
print "p_value= %.2E" % p_value
print "-" * 80
print
f.write(text + "\n")
f.close()
def main():
global options
database = EMRDatabase(options.verbose)
database.import_data(options.emr_data_file, options.diseases_file,
options.code2disease_file)
diseases = [
"Alzheimer's disease", "Attention deficit", "Autism",
"Breast cancer (female)", "Epilepsy", "Schizophrenia"
]
D1 = "Autism"
D2 = "Epilepsy"
D3 = "Breast cancer (female)"
# Query for patients that have D1
D1_patients = database.query_emr_data(D1)
# Query for patients that have D2
D2_patients = database.query_emr_data(D2)
# Query for patients that have both D1 and D2
D1andD2_patients = database.query_emr_data([D1, D2])
# Query for patients that have either D1 or D2
D1orD2_patients = database.query_emr_data([D1, D2], OR_match=True)
# Query for patients that have D1 and not D2
D1notD2_patients = database.query_emr_data([D1, "not " + D2])
# Query for patients that have D2 and not D1
D2notD1_patients = database.query_emr_data(["not " + D1, D2])
# Query for patients that have neither D2 nor D1
noD1D2_patients = database.query_emr_data(["not " + D1, "not " + D2])
# Query for male patients with female Breast cancer
D3_male_patients = database.query_emr_data(D3, gender_filters="M")
# Query for female patients with female Breast cancer
D3_female_patients = database.query_emr_data(D3, gender_filters="F")
print "Test EMR_database queries:"
print "%-6d patients with %s" % (len(D1_patients), D1)
print "%-6d patients with %s" % (len(D2_patients), D2)
print "%-6d patients with %s and %s" % (len(D1andD2_patients), D1, D2)
print "%-6d patients with %s or %s" % (len(D1orD2_patients), D1, D2)
print "%-6d patients with %s and no %s" % (len(D1notD2_patients), D1, D2)
print "%-6d patients with %s and no %s" % (len(D2notD1_patients), D2, D1)
print "%-6d patients with no %s and no %s" % (len(noD1D2_patients), D1, D2)
print "%-6d male patients with %s" % (len(D3_male_patients), D3)
print "%-6d female patients with %s" % (len(D3_female_patients), D3)
if options.verbose:
print "Patients with %s:" % D1
for patient in D1_patients:
print "patient %s --> %s" % (patient, D1_patients[patient])
print
print "Patients with %s:" % D2
for patient in D2_patients:
print "patient %s --> %s" % (patient, D2_patients[patient])
print
print "Patients with %s and %s:" % (D1, D2)
for patient in D1andD2_patients:
print "patient %s --> %s" % (patient, D1andD2_patients[patient])
print
print "Patients with %s or %s:" % (D1, D2)
for patient in D1orD2_patients:
print "patient %s --> %s" % (patient, D1orD2_patients[patient])
print
print "Patients with %s and no %s:" % (D2, D1)
for patient in D2notD1_patients:
print "patient %s --> %s" % (patient, D2notD1_patients[patient])
print
print "Patients with %s and no %s:" % (D1, D2)
for patient in D1notD2_patients:
print "patient %s --> %s" % (patient, D1notD2_patients[patient])
print
print "Patients with no %s and no %s:" % (D1, D2)
for patient in noD1D2_patients:
print "patient %s --> %s" % (patient, noD1D2_patients[patient])
print
print "Male patients with %s:" % (D3)
for patient in D3_male_patients:
print "patient %s --> %s" % (patient, D3_male_patients[patient])
print
print "Female patients with %s:" % (D3)
for patient in D3_female_patients:
print "patient %s --> %s" % (patient, D3_female_patients[patient])
print
# Find occurrences of 6 diseases.
print
print "Occurrences of the 6 diseases:"
for n1, D1 in enumerate(diseases):
D1_patients = database.query_emr_data(D1)
print "%-6d patients with %s" % (len(D1_patients), D1)
if options.verbose:
print "Patients with %s:" % D1
for patient in D1_patients:
print "patient %s --> %s" % (patient, D1_patients[patient])
print
# Find comorbidities between the 6 diseases.
print
print "Comorbidities between the 6 diseases:"
for n1, D1 in enumerate(diseases):
for n2, D2 in enumerate(diseases):
if n1 >= n2: continue
D1andD2_patients = database.query_emr_data([D1, D2])
print("%-6d patients with %s and %s" %
(len(D1andD2_patients), D1, D2))
if options.verbose:
print "Patients with both %s and %s:" % (D1, D2)
for patient in D1andD2_patients:
print("patient %s --> %s" %
(patient, D1andD2_patients[patient]))
print
def main():
global options
database = EMRDatabase(options.verbose)
database.import_data(options.emr_data_file,
options.diseases_file,
options.code2disease_file)
diseases = ["Alzheimer's disease", "Attention deficit", "Autism",
"Breast cancer (female)", "Epilepsy", "Schizophrenia"]
D1 = "Autism"
D2 = "Epilepsy"
D3 = "Breast cancer (female)"
# Query for patients that have D1
D1_patients = database.query_emr_data(D1)
# Query for patients that have D2
D2_patients = database.query_emr_data(D2)
# Query for patients that have both D1 and D2
D1andD2_patients = database.query_emr_data([D1, D2])
# Query for patients that have either D1 or D2
D1orD2_patients = database.query_emr_data([D1, D2], OR_match = True)
# Query for patients that have D1 and not D2
D1notD2_patients = database.query_emr_data([D1, "not " + D2])
# Query for patients that have D2 and not D1
D2notD1_patients = database.query_emr_data(["not " + D1, D2])
# Query for patients that have neither D2 nor D1
noD1D2_patients = database.query_emr_data(["not " + D1, "not " + D2])
# Query for male patients with female Breast cancer
D3_male_patients = database.query_emr_data(D3 , gender_filters = "M")
# Query for female patients with female Breast cancer
D3_female_patients = database.query_emr_data(D3, gender_filters = "F")
print "Test EMR_database queries:"
print "%-6d patients with %s" %(len(D1_patients), D1)
print "%-6d patients with %s" %(len(D2_patients), D2)
print "%-6d patients with %s and %s" %(len(D1andD2_patients), D1, D2)
print "%-6d patients with %s or %s" %(len(D1orD2_patients), D1, D2)
print "%-6d patients with %s and no %s" %(len(D1notD2_patients), D1, D2)
print "%-6d patients with %s and no %s" %(len(D2notD1_patients), D2, D1)
print "%-6d patients with no %s and no %s" %(len(noD1D2_patients), D1, D2)
print "%-6d male patients with %s" %(len(D3_male_patients), D3)
print "%-6d female patients with %s" %(len(D3_female_patients), D3)
if options.verbose:
print "Patients with %s:" % D1
for patient in D1_patients:
print "patient %s --> %s" % (patient, D1_patients[patient])
print
print "Patients with %s:" % D2
for patient in D2_patients:
print "patient %s --> %s" % (patient, D2_patients[patient])
print
print "Patients with %s and %s:" % (D1, D2)
for patient in D1andD2_patients:
print "patient %s --> %s" % (patient, D1andD2_patients[patient])
print
print "Patients with %s or %s:" % (D1, D2)
for patient in D1orD2_patients:
print "patient %s --> %s" % (patient, D1orD2_patients[patient])
print
print "Patients with %s and no %s:" % (D2, D1)
for patient in D2notD1_patients:
print "patient %s --> %s" % (patient, D2notD1_patients[patient])
print
print "Patients with %s and no %s:" % (D1, D2)
for patient in D1notD2_patients:
print "patient %s --> %s" % (patient, D1notD2_patients[patient])
print
print "Patients with no %s and no %s:" % (D1, D2)
for patient in noD1D2_patients:
print "patient %s --> %s" % (patient, noD1D2_patients[patient])
print
print "Male patients with %s:" % (D3)
for patient in D3_male_patients:
print "patient %s --> %s" % (patient, D3_male_patients[patient])
print
print "Female patients with %s:" % (D3)
for patient in D3_female_patients:
print "patient %s --> %s" % (patient, D3_female_patients[patient])
print
# Find occurrences of 6 diseases.
print
print "Occurrences of the 6 diseases:"
for n1, D1 in enumerate(diseases):
D1_patients = database.query_emr_data(D1)
print "%-6d patients with %s" %(len(D1_patients), D1)
if options.verbose:
print "Patients with %s:" % D1
for patient in D1_patients:
print "patient %s --> %s" % (patient, D1_patients[patient])
print
# Find comorbidities between the 6 diseases.
print
print "Comorbidities between the 6 diseases:"
for n1, D1 in enumerate(diseases):
for n2, D2 in enumerate(diseases):
if n1 >= n2: continue
D1andD2_patients = database.query_emr_data([D1, D2])
print ("%-6d patients with %s and %s"
%(len(D1andD2_patients), D1, D2))
if options.verbose:
print "Patients with both %s and %s:" % (D1, D2)
for patient in D1andD2_patients:
print ("patient %s --> %s" % (patient,
D1andD2_patients[patient]))
print
def main():
global options
# Import EMR data into database
database = EMRDatabase()
database.import_data(options.emr_data_file, options.diseases_file,
options.code2disease_file)
# Instantiate the OptimizeLogLikelihood class
opt_log_likelihood = OptimizeLogLikelihood(options.verbose)
opt_log_likelihood.set_use_random_seed(options.use_random_seed)
f = open("p_value.txt", 'w')
f.write("# emr_data_file = %s\n" % options.emr_data_file)
f.write("# norm_prval_method = %s\n" % options.norm_prval_method)
f.write("# threshold_type = %s\n" % options.threshold_type)
f.write("\n")
f.write("# D1, D2, overlap_type, ")
f.write("overlap_LL, indepedent_LL, ")
f.write("LLR, p_value\n")
# Compute p-value for specified disease pair or for all disease pairs with
# non-zero patient counts.
if options.disease1 != None and options.disease2 != None:
D1_list = [options.disease1]
D2_list = [options.disease2]
else:
diseases = database.get_diseases()
diseases.sort()
filtered_diseases = __filter_diseases(diseases, database)
D1_list = filtered_diseases
D2_list = filtered_diseases
for D1 in D1_list:
for D2 in D2_list:
if options.disease1 == None or options.disease2 == None:
if D1 >= D2: continue
print "-" * 80
print "D1= %s, D2= %s," % (D1, D2),
print "overlap_type= %s" % options.overlap_type
# Independent (no genetic overlap) model
indep_log_likelihood = (__compute_log_likelihood_wrapper(
opt_log_likelihood, database, D1, D2, options.tau1,
options.tau2, "independent", options.threshold_type,
options.prevalence_file, options.norm_prval_method))
min_log_likelihood = indep_log_likelihood - 1.0
# Allow genetic overlap model
overlap_log_likelihood = (__compute_log_likelihood_wrapper(
opt_log_likelihood, database, D1, D2, options.tau1,
options.tau2, options.overlap_type, options.threshold_type,
options.prevalence_file, options.norm_prval_method,
min_log_likelihood))
log_likelihood_ratio = 2.0 * (overlap_log_likelihood -
indep_log_likelihood)
# Degree of freedoms of the chi-square distribution.
dof = 1
# p-value is the area at the right tail of the chi-square
# distribution
p_value = 1.0 - chi2.cdf(log_likelihood_ratio, dof)
text = "%s, %s, %s, " % (D1, D2, options.overlap_type)
text += "%.3E, " % overlap_log_likelihood
text += "%.3E, " % indep_log_likelihood
text += "%.3E, %.3E" % (log_likelihood_ratio, p_value)
print "overlap_LL= %.2E," % overlap_log_likelihood,
print "indep_LL= %.2E," % indep_log_likelihood,
print "LLR= %.2E," % log_likelihood_ratio,
print "p_value= %.2E" % p_value
print "-" * 80
print
f.write(text + '\n')
f.close()