def test_initial_guess_wt_average(self):
result = fit_rates_weighted_average(self.reduced_hdxm)
output = result.output
assert output.size == 100
check_rates = csv_to_protein(output_dir / 'ecSecB_reduced_guess.csv')
pd.testing.assert_series_equal(check_rates['rate'], output['rate'])
test_data_dir = directory / 'test_data'
guess = False # guess true requires dask cluster at config defined ip/port
control = ('Full deuteration control', 0.167)
data = read_dynamx(test_data_dir / 'ecSecB_apo.csv', test_data_dir / 'ecSecB_dimer.csv')
pmt = PeptideMasterTable(data, drop_first=1, ignore_prolines=True, remove_nan=False)
pmt.set_control(control)
temperature, pH = 273.15 + 30, 8.
hdxm = HDXMeasurement(pmt.get_state('SecB WT apo'), sequence=sequence, temperature=temperature, pH=pH)
if guess:
client = default_client()
wt_avg_result = fit_rates_weighted_average(hdxm, bounds=(1e-2, 800))
output = wt_avg_result.output
output.to_file(directory / 'test_data' / 'ecSecB_guess.txt')
else:
output = csv_to_protein(directory / 'test_data' / 'ecSecB_guess.txt')
gibbs_guess = hdxm.guess_deltaG(output['rate'])
fr_torch = fit_gibbs_global(hdxm, gibbs_guess, epochs=epochs, r1=2)
fr_torch.output.to_file(directory / 'test_data' / 'ecSecB_torch_fit.txt')
hdxm_dimer = HDXMeasurement(pmt.get_state('SecB his dimer apo'), sequence=sequence_dimer,
temperature=temperature, pH=pH)
hdx_set = HDXMeasurementSet([hdxm_dimer, hdxm])
gibbs_guess = hdx_set.guess_deltaG([output['rate'], output['rate']])
from pyhdx.batch_processing import load_from_yaml
from pathlib import Path
from pyhdx.fitting import fit_rates_weighted_average, fit_rates_half_time_interpolate
import yaml
from pyhdx.local_cluster import default_client
current_dir = Path(__file__).parent
data_dir = current_dir.parent / 'tests' / 'test_data'
yaml_stream = Path(current_dir / 'yaml_files' / 'SecB.yaml').read_text()
data_dict = yaml.safe_load(yaml_stream)
# Requires local_cluster.py to be running (or other Dask client on default address in config)
client = default_client()
for name, dic in data_dict.items():
print(name)
dic = data_dict[name]
hdxm = load_from_yaml(dic, data_dir=data_dir)
#Uncomment/adjust path to save sequence info + intrinsic rates
#hdxm.coverage.protein.to_file(f'{name}_sequence_info.txt', fmt='pprint')
fr = fit_rates_weighted_average(hdxm, client=client)
fr.output.to_file(current_dir / 'guesses' / f'{name}_rates_guess.txt')
drop_first=1,
ignore_prolines=True,
remove_nan=False)
pmt.set_control(control)
temperature, pH = 273.15 + 30, 8.
hdxm = HDXMeasurement(pmt.get_state('SecB WT apo'),
sequence=sequence,
temperature=temperature,
pH=pH)
data = pmt.get_state('SecB WT apo')
reduced_data = data[data['end'] < 40]
hdxm_reduced = HDXMeasurement(reduced_data, temperature=temperature, pH=pH)
result = fit_rates_weighted_average(hdxm_reduced)
reduced_guess = result.output
dataframe_to_file(output_dir / 'ecSecB_reduced_guess.csv', reduced_guess)
dataframe_to_file(output_dir / 'ecSecB_reduced_guess.txt',
reduced_guess,
fmt='pprint')
gibbs_guess = hdxm_reduced.guess_deltaG(reduced_guess['rate'])
fr_torch = fit_gibbs_global(hdxm_reduced, gibbs_guess, epochs=epochs, r1=2)
save_fitresult(output_dir / 'ecsecb_reduced', fr_torch)
if guess:
wt_avg_result = fit_rates_weighted_average(hdxm,
bounds=(1e-2 / 60., 800 / 60.))
guess_output = wt_avg_result.output
dataframe_to_file(output_dir / 'ecSecB_guess.csv', guess_output)
def test_initial_guess(self):
result = fit_rates_weighted_average(self.reduced_series)
output = result.output
assert output.size == 100
#%%
# Load the data of two Dynamx files, and combine the result to one table
data = read_dynamx(input_dir / 'ecSecB_apo.csv', input_dir / 'ecSecB_dimer.csv')
pmt = PeptideMasterTable(data, drop_first=1, ignore_prolines=True, remove_nan=False)
pmt.set_control(('Full deuteration control', 0.167*60))
temperature, pH = 273.15 + 30, 8.
hdxm = HDXMeasurement(pmt.get_state('SecB WT apo'), temperature=temperature, pH=pH)
#%%
if guess:
client = default_client()
wt_avg_result = fit_rates_weighted_average(hdxm, client=client)
init_guess = wt_avg_result.output
else:
init_guess = csv_to_dataframe(test_data_dir / 'output' / 'ecSecB_guess.csv')
gibbs_guess = hdxm.guess_deltaG(init_guess['rate'])
#%%
fr_torch = fit_gibbs_global(hdxm, gibbs_guess, **fit_kwargs)
#Human readable output
fr_torch.to_file(output_dir / 'SecB_fit_result.txt', fmt='pprint')
#Machine readable output
fr_torch.to_file(output_dir / 'SecB_fit_result.csv', fmt='csv')
guess = False
epochs = 1000
root_dir = Path().resolve().parent
test_data_dir = root_dir / 'tests' / 'test_data'
input_file_path = test_data_dir / 'ecSecB_apo.csv'
# Load the data of two Dynamx files, and combine the result to one table
data = read_dynamx(test_data_dir / 'ecSecB_apo.csv',
test_data_dir / 'ecSecB_dimer.csv')
pmt = PeptideMasterTable(data,
drop_first=1,
ignore_prolines=True,
remove_nan=False)
pmt.set_control(('Full deuteration control', 0.167))
temperature, pH = 273.15 + 30, 8.
series = HDXMeasurement(pmt.get_state('SecB WT apo'),
temperature=temperature,
pH=pH)
if guess:
client = default_client()
wt_avg_result = fit_rates_weighted_average(series, client=client)
init_guess = wt_avg_result.output
else:
init_guess = csv_to_protein(test_data_dir / 'ecSecB_guess.txt')
gibbs_guess = series.guess_deltaG(init_guess['rate'])
fr_torch = fit_gibbs_global(series, gibbs_guess, epochs=epochs)
print(fr_torch.metadata['total_loss'])
