def test_load_save_fitresult(self, tmp_path):
#todo missing read batch result test
fpath = Path(tmp_path) / 'fit_result_single.csv'
self.fit_result.to_file(fpath)
df = csv_to_dataframe(fpath)
assert df.attrs['metadata'] == self.fit_result.metadata
fit_result_dir = Path(tmp_path) / 'fit_result'
save_fitresult(fit_result_dir, self.fit_result, log_lines=['test123'])
log_lines = Path(fit_result_dir / 'log.txt').read_text().split('\n')
assert log_lines[-1] == 'test123'
fit_result_loaded = load_fitresult(fit_result_dir)
assert isinstance(fit_result_loaded.losses, pd.DataFrame)
assert isinstance(fit_result_loaded.hdxm_set, HDXMeasurementSet)
timepoints = np.linspace(0, 30*60, num=100)
d_calc = fit_result_loaded(timepoints)
assert d_calc.shape == (1, self.hdxm.Np, len(timepoints))
losses = csv_to_dataframe(fit_result_dir / 'losses.csv')
fr_load_with_hdxm_and_losses = load_fitresult(fit_result_dir)
assert len(fr_load_with_hdxm_and_losses.losses) == 100
assert fr_load_with_hdxm_and_losses.metadata['total_loss'] == losses.iloc[-1].sum()
df = checkpoint.to_dataframe(hdx_set.names)
dataframe_to_file(output_dir / 'model_history.csv', df)
dataframe_to_file(output_dir / 'model_history.txt', df, fmt='pprint')
# Checkpoint history scatter plot
# Note that these are raw dG values including interpolated values in regions of no coverage
history = checkpoint.model_history
num = len(history)
cmap = mpl.cm.get_cmap('winter')
norm = mpl.colors.Normalize(vmin=1, vmax=num*checkpoint.epoch_step)
colors = iter(cmap(np.linspace(0, 1, num=num)))
fig, ax = plt.subplots()
for key, val in history.items():
n = len(val['dG'].numpy().squeeze())
ax.scatter(hdx_set.coverage.index, val['dG'].numpy().squeeze()[0], color=next(colors))
fig.colorbar(mpl.cm.ScalarMappable(cmap=cmap, norm=norm), label='Epochs')
plt.show()
#Human readable output
result.to_file(output_dir / 'Batch_fit_result.txt', fmt='pprint')
#Machine readable output
result.to_file(output_dir / 'Batch_fit_result.csv', fmt='csv')
#Save full fitresult
save_fitresult(output_dir / 'SecB_tetramer_dimer_batch', result)
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)
dataframe_to_file(output_dir / 'ecSecB_guess.txt',
guess_output,
fmt='pprint')
else:
guess_output = csv_to_dataframe(output_dir / 'ecSecB_guess.csv')
# Export protein sequence and intrinsic rate of exchange
hdxm.coverage.protein.to_file(output_dir / 'ecSecB_info.csv')
hdxm.coverage.protein.to_file(output_dir / 'ecSecB_info.txt', fmt='pprint')
# 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')
save_fitresult(output_dir / 'SecB_fit', fr_torch)
"""Obtain ΔG for ecSecB tetramer and dimer""" from pathlib import Path from pyhdx.batch_processing import yaml_to_hdxmset from pyhdx.fileIO import csv_to_dataframe, save_fitresult from pyhdx.fitting import fit_gibbs_global_batch import yaml cwd = Path(__file__).parent data_dir = cwd / 'test_data' / 'input' output_dir = cwd / 'test_data' / 'output' yaml_dict = yaml.safe_load(Path(data_dir / 'data_states.yaml').read_text()) hdx_set = yaml_to_hdxmset(yaml_dict, data_dir=data_dir) initial_guess_rates = csv_to_dataframe(output_dir / 'ecSecB_guess.csv') guesses = hdx_set[0].guess_deltaG(initial_guess_rates['rate']) fit_kwargs = yaml.safe_load(Path(data_dir / 'fit_settings.yaml').read_text()) fr = fit_gibbs_global_batch(hdx_set, guesses, **fit_kwargs) save_fitresult(output_dir / 'ecsecb_tetramer_dimer', fr)