def core_model_test(base_dir, mapping_table, taxa_level, output_dir):
""" Tests the core model
Inputs:
base_dir: base common directory of all mapping files
mapping_table: dictionary with the mapping table information
output_dir: output directory
"""
profiles = get_profiles_list(base_dir, mapping_table, taxa_level)
# Bootstrap profiles to get the results
profile, mean, stdev, ci = bootstrap_profiles(normalize_profiles(profiles))
# Write the bootstrapped profile
profile_fp = join(output_dir, 'core_model_profile.txt')
write_profile(profile, profile_fp)
# Write the test result
output_fp = join(output_dir, 'core_model_result.txt')
outf = open(output_fp, 'w')
outf.write("Results for the core model test:\n")
outf.write("Microbiome model: ")
if profile['not_shared'] < 0.5:
outf.write("Substantial core.\n")
elif profile['not_shared'] < 1.0:
outf.write("Minimal core.\n")
else:
outf.write('No core\n')
outf.write("\nStatistical results (amount shared):\n")
outf.write("Mean: %f %%\n" % (mean * 100))
outf.write("Standard deviation: %f %%\n" % (stdev * 100))
outf.write("Confidence interval for the mean: [%f %%, %f %%]\n"
% ((ci[0] * 100), (ci[1] * 100)))
def core_model_test(base_dir, mapping_table, taxa_level, output_dir):
""" Tests the core model
Inputs:
base_dir: base common directory of all mapping files
mapping_table: dictionary with the mapping table information
output_dir: output directory
"""
profiles = get_profiles_list(base_dir, mapping_table, taxa_level)
# Bootstrap profiles to get the results
profile, mean, stdev, ci = bootstrap_profiles(normalize_profiles(profiles))
# Write the bootstrapped profile
profile_fp = join(output_dir, 'core_model_profile.txt')
write_profile(profile, profile_fp)
# Write the test result
output_fp = join(output_dir, 'core_model_result.txt')
outf = open(output_fp, 'w')
outf.write("Results for the core model test:\n")
outf.write("Microbiome model: ")
if profile['not_shared'] < 0.5:
outf.write("Substantial core.\n")
elif profile['not_shared'] < 1.0:
outf.write("Minimal core.\n")
else:
outf.write('No core\n')
outf.write("\nStatistical results (amount shared):\n")
outf.write("Mean: %f %%\n" % (mean * 100))
outf.write("Standard deviation: %f %%\n" % (stdev * 100))
outf.write("Confidence interval for the mean: [%f %%, %f %%]\n" %
((ci[0] * 100), (ci[1] * 100)))
def test_normalize_profiles_neq_len(self):
'''Normalizing two profiles with many diferent taxa'''
self.assertEquals(normalize_profiles(self.uneven_profiles),
[{'taxa1': 0.20, 'taxa2': 0.00, 'taxa3': 0.30,
'taxa4': 0.00, 'taxa5': 0.15, 'taxa6': 0.35,
'taxa7': 0.00, 'not_shared': 0.00},
{'taxa1': 0.10, 'taxa2': 0.50, 'taxa3': 0.00,
'taxa4': 0.15, 'taxa5': 0.05, 'taxa6': 0.00,
'taxa7': 0.20, 'not_shared': 0.00}])
def test_normalize_profiles_eq_len(self):
'''Normalizing two profiles of equal length'''
self.assertEquals(normalize_profiles(self.many_profiles),
[{'taxa1': 0.20, 'taxa2': 0.30, 'taxa3': 0.15,
'taxa4': 0.35, 'not_shared': 0.00},
{'taxa1': 0.10, 'taxa2': 0.50, 'taxa3': 0.15,
'taxa4': 0.25, 'not_shared': 0.00},
{'taxa1': 0.15, 'taxa2': 0.22, 'taxa3': 0.15,
'taxa4': 0.48, 'not_shared': 0.00}])
def bootstrap_profiles(profiles,
alpha=0.05,
repetitions=1000,
randfunc=randint):
"""Performs bootstrapping over the sample 'profiles'
Inputs:
profiles: list of profiles
alpha: defines the confidence interval as 1 - alpha
repetitions: number of bootstrap iterations
randfunc: random function for generate the bootstrap samples
Returns:
profile: the bootstrapped profile of the profiles list
sample_mean: the bootstrap mean of the amount shared
sample_stdev: the bootstrap standard deviation of the amount shared
ci: the confidence interval for the bootstrap mean
"""
length = len(profiles)
normalize_profiles(profiles)
boot_shared = []
boot_profiles = []
for i in range(repetitions):
# Construct the bootstrap sample
resample = [profiles[randfunc(0, length)] for j in range(length)]
profile = compare_profiles(resample)
# Store the amount shared
boot_shared.append(1.0 - profile['not_shared'])
# Store the result profile
boot_profiles.append(profile)
# Convert data to a numpy array
boot_shared = array(boot_shared)
# Get the mean and the standard deviation of the shared data
sample_mean = mean(boot_shared)
sample_stdev = std(boot_shared)
# Compute the confidence interval for the bootstrapped data
# using bootstrap percentile interval
ci = quantile(boot_shared, [alpha / 2, 1 - (alpha / 2)])
# Compute the bootstrapped profile of the profiles list
profile = compare_profiles(profiles)
return profile, 1.0 - profile['not_shared'], sample_stdev, ci
def bootstrap_profiles(profiles, alpha=0.05, repetitions=1000,
randfunc=randint):
"""Performs bootstrapping over the sample 'profiles'
Inputs:
profiles: list of profiles
alpha: defines the confidence interval as 1 - alpha
repetitions: number of bootstrap iterations
randfunc: random function for generate the bootstrap samples
Returns:
profile: the bootstrapped profile of the profiles list
sample_mean: the bootstrap mean of the amount shared
sample_stdev: the bootstrap standard deviation of the amount shared
ci: the confidence interval for the bootstrap mean
"""
length = len(profiles)
normalize_profiles(profiles)
boot_shared = []
boot_profiles = []
for i in range(repetitions):
# Construct the bootstrap sample
resample = [profiles[randfunc(0, length)] for j in range(length)]
profile = compare_profiles(resample)
# Store the amount shared
boot_shared.append(1.0 - profile['not_shared'])
# Store the result profile
boot_profiles.append(profile)
# Convert data to a numpy array
boot_shared = array(boot_shared)
# Get the mean and the standard deviation of the shared data
sample_mean = mean(boot_shared)
sample_stdev = std(boot_shared)
# Compute the confidence interval for the bootstrapped data
# using bootstrap percentile interval
ci = quantile(boot_shared, [alpha/2, 1-(alpha/2)])
# Compute the bootstrapped profile of the profiles list
profile = compare_profiles(profiles)
return profile, 1.0-profile['not_shared'], sample_stdev, ci
def test_normalize_profiles_neq_len(self):
'''Normalizing two profiles with many diferent taxa'''
self.assertEquals(normalize_profiles(self.uneven_profiles),
[{
'taxa1': 0.20,
'taxa2': 0.00,
'taxa3': 0.30,
'taxa4': 0.00,
'taxa5': 0.15,
'taxa6': 0.35,
'taxa7': 0.00,
'not_shared': 0.00
}, {
'taxa1': 0.10,
'taxa2': 0.50,
'taxa3': 0.00,
'taxa4': 0.15,
'taxa5': 0.05,
'taxa6': 0.00,
'taxa7': 0.20,
'not_shared': 0.00
}])
def test_normalize_profiles_eq_len(self):
'''Normalizing two profiles of equal length'''
self.assertEquals(normalize_profiles(self.many_profiles),
[{
'taxa1': 0.20,
'taxa2': 0.30,
'taxa3': 0.15,
'taxa4': 0.35,
'not_shared': 0.00
}, {
'taxa1': 0.10,
'taxa2': 0.50,
'taxa3': 0.15,
'taxa4': 0.25,
'not_shared': 0.00
}, {
'taxa1': 0.15,
'taxa2': 0.22,
'taxa3': 0.15,
'taxa4': 0.48,
'not_shared': 0.00
}])
