def parameters_to_json(self):
dict_setting = parameter_to_dict.get_dict_data_ms(self.mass_spectrum)
dict_setting['MassSpecAttrs'] = self.get_mass_spec_attrs(mass_spectrum)
dict_setting['analyzer'] = self.mass_spectrum.analyzer
dict_setting['instrument_label'] = self.mass_spectrum.instrument_label
dict_setting['sample_name'] = self.mass_spectrum.sample_name
return json.dumps(dict_setting)
def parameters_to_json(self):
dict_setting = parameter_to_dict.get_dict_data_ms(self.mass_spectrum)
dict_setting['MassSpecAttrs'] = self.get_mass_spec_attrs(
self.mass_spectrum)
dict_setting['analyzer'] = self.mass_spectrum.analyzer
dict_setting['instrument_label'] = self.mass_spectrum.instrument_label
dict_setting['sample_name'] = self.mass_spectrum.sample_name
import re
# pretty print
output = json.dumps(dict_setting)
# output = json.dumps(dict_setting, sort_keys=False, indent=4, separators=(',', ': '))
# output = re.sub(r'",\s+', '", ', output)
return output
def write_settings(self, output_path, mass_spectrum):
import json
dict_setting = parameter_to_dict.get_dict_data_ms(mass_spectrum)
dict_setting['MassSpecAttrs'] = self.get_mass_spec_attrs(mass_spectrum)
dict_setting['analyzer'] = mass_spectrum.analyzer
dict_setting['instrument_label'] = mass_spectrum.instrument_label
dict_setting['sample_name'] = mass_spectrum.sample_name
with open(
output_path.with_suffix('.json'),
'w',
encoding='utf8',
) as outfile:
output = json.dumps(dict_setting,
sort_keys=True,
indent=4,
separators=(',', ': '))
outfile.write(output)
def to_hdf(self):
import h5py
import json
from datetime import datetime, timezone
with h5py.File(self.output_file.with_suffix('.hdf5'),
'a') as hdf_handle:
list_results = self.list_dict_to_list(self.mass_spectrum,
is_hdf5=True)
dict_ms_attrs = self.get_mass_spec_attrs(self.mass_spectrum)
setting_dicts = parameter_to_dict.get_dict_data_ms(
self.mass_spectrum)
columns_labels = json.dumps(
self.columns_label +
self.get_all_used_atoms_in_order(self.mass_spectrum),
sort_keys=False,
indent=4,
separators=(',', ': '))
if not hdf_handle.attrs.get('date_utc'):
timenow = str(
datetime.now(
timezone.utc).strftime("%d/%m/%Y %H:%M:%S %Z"))
hdf_handle.attrs['date_utc'] = timenow
hdf_handle.attrs[
'file_name'] = self.mass_spectrum.filename.name
hdf_handle.attrs['data_structure'] = 'mass_spectrum'
hdf_handle.attrs['analyzer'] = self.mass_spectrum.analyzer
hdf_handle.attrs[
'instrument_label'] = self.mass_spectrum.instrument_label
hdf_handle.attrs[
'sample_name'] = self.mass_spectrum.sample_name
group_key = str(self.mass_spectrum.scan_number)
if group_key not in hdf_handle.keys():
scan_group = hdf_handle.create_group(
str(self.mass_spectrum.scan_number))
if list(self.mass_spectrum.abundance_profile):
mz_abun_array = empty(
shape=(2, len(self.mass_spectrum.abundance_profile)))
mz_abun_array[0] = self.mass_spectrum.abundance_profile
mz_abun_array[1] = self.mass_spectrum.mz_exp_profile
raw_ms_dataset = scan_group.create_dataset(
'raw_ms', data=mz_abun_array, dtype="f8")
else:
# create empy dataset for missing raw data
raw_ms_dataset = scan_group.create_dataset('raw_ms',
dtype="f8")
raw_ms_dataset.attrs['MassSpecAttrs'] = json.dumps(
dict_ms_attrs)
if isinstance(self.mass_spectrum, MassSpecfromFreq):
raw_ms_dataset.attrs['TransientSetting'] = json.dumps(
setting_dicts.get('TransientSetting'),
sort_keys=False,
indent=4,
separators=(',', ': '))
else:
scan_group = hdf_handle.get(group_key)
# if there is not processed data len = 0, otherwise len() will return next index
index_processed_data = str(len(scan_group.keys()))
print('index_processed_data', index_processed_data)
timenow = str(
datetime.now(timezone.utc).strftime("%d/%m/%Y %H:%M:%S %Z"))
processed_dset = scan_group.create_dataset(index_processed_data,
data=list_results)
processed_dset.attrs['date_utc'] = timenow
processed_dset.attrs['ColumnsLabels'] = columns_labels
processed_dset.attrs['MoleculaSearchSetting'] = json.dumps(
setting_dicts.get('MoleculaSearch'),
sort_keys=False,
indent=4,
separators=(',', ': '))
processed_dset.attrs['MassSpecPeakSetting'] = json.dumps(
setting_dicts.get('MassSpecPeak'),
sort_keys=False,
indent=4,
separators=(',', ': '))
processed_dset.attrs['MassSpectrumSetting'] = json.dumps(
setting_dicts.get('MassSpectrum'),
sort_keys=False,
indent=4,
separators=(',', ': '))
