def preprocess_short_square_sweeps(data_set,
sweep_numbers,
extra_dur=0.2,
spike_window=0.05):
if len(sweep_numbers) == 0:
raise er.FeatureError(
"No short square sweeps available for feature extraction")
good_sweep_numbers, ssq_start, ssq_end = validate_sweeps(
data_set, sweep_numbers, extra_dur=extra_dur)
if len(good_sweep_numbers) == 0:
raise er.FeatureError(
"No short square sweeps were long enough or did not end early")
ssq_sweeps = data_set.sweep_set(good_sweep_numbers)
ssq_spx, ssq_spfx = dsf.extractors_for_sweeps(
ssq_sweeps,
est_window=[ssq_start, ssq_start + 0.001],
start=ssq_start,
end=ssq_end + spike_window,
reject_at_stim_start_interval=0.0002,
**dsf.detection_parameters(data_set.SHORT_SQUARE))
ssq_an = spa.ShortSquareAnalysis(ssq_spx, ssq_spfx)
ssq_features = ssq_an.analyze(ssq_sweeps)
return ssq_sweeps, ssq_features
def preprocess_long_square_sweeps(data_set,
sweep_numbers,
extra_dur=0.2,
subthresh_min_amp=-100.):
if len(sweep_numbers) == 0:
raise er.FeatureError(
"No long square sweeps available for feature extraction")
good_sweep_numbers, lsq_start, lsq_end = validate_sweeps(
data_set, sweep_numbers, extra_dur=extra_dur)
if len(good_sweep_numbers) == 0:
raise er.FeatureError(
"No long square sweeps were long enough or did not end early")
lsq_sweeps = data_set.sweep_set(good_sweep_numbers)
lsq_spx, lsq_spfx = dsf.extractors_for_sweeps(lsq_sweeps,
start=lsq_start,
end=lsq_end,
min_peak=-25,
**dsf.detection_parameters(
data_set.LONG_SQUARE))
lsq_an = spa.LongSquareAnalysis(lsq_spx,
lsq_spfx,
subthresh_min_amp=subthresh_min_amp)
lsq_features = lsq_an.analyze(lsq_sweeps)
return lsq_sweeps, lsq_features, lsq_start, lsq_end, lsq_spx
def run_feature_extraction(input_nwb_file, stimulus_ontology_file,
output_nwb_file, qc_fig_dir, sweep_info, cell_info):
lu.log_pretty_header("Extract ephys features", level=1)
sp.drop_failed_sweeps(sweep_info)
if len(sweep_info) == 0:
raise er.FeatureError(
"There are no QC-passed sweeps available to analyze")
if not stimulus_ontology_file:
stimulus_ontology_file = StimulusOntology.DEFAULT_STIMULUS_ONTOLOGY_FILE
logging.info(
F"Ontology is not provided, using default {StimulusOntology.DEFAULT_STIMULUS_ONTOLOGY_FILE}"
)
ont = StimulusOntology(ju.read(stimulus_ontology_file))
data_set = create_data_set(sweep_info=sweep_info,
nwb_file=input_nwb_file,
ontology=ont,
api_sweeps=False)
try:
cell_features, sweep_features, cell_record, sweep_records = dsft.extract_data_set_features(
data_set)
if cell_info: cell_record.update(cell_info)
cell_state = {"failed_fx": False, "fail_fx_message": None}
feature_data = {
'cell_features': cell_features,
'sweep_features': sweep_features,
'cell_record': cell_record,
'sweep_records': sweep_records,
'cell_state': cell_state
}
except (er.FeatureError, IndexError) as e:
cell_state = {"failed_fx": True, "fail_fx_message": str(e)}
logging.warning(e)
feature_data = {'cell_state': cell_state}
if not cell_state["failed_fx"]:
sweep_spike_times = collect_spike_times(sweep_features)
embed_spike_times(input_nwb_file, output_nwb_file, sweep_spike_times)
if qc_fig_dir is None:
logging.info("qc_fig_dir is not provided, will not save figures")
else:
plotqc.display_features(qc_fig_dir, data_set, feature_data)
# On Windows int64 keys of sweep numbers cannot be converted to str by json.dump when serializing.
# Thus, we are converting them here:
feature_data["sweep_features"] = {
str(k): v
for k, v in feature_data["sweep_features"].items()
}
return feature_data
def preprocess_ramp_sweeps(data_set, sweep_numbers):
if len(sweep_numbers) == 0:
raise er.FeatureError("No ramp sweeps available for feature extraction")
ramp_sweeps = data_set.sweep_set(sweep_numbers)
ramp_sweeps.select_epoch("recording")
ramp_start, ramp_dur, _, _, _ = stf.get_stim_characteristics(ramp_sweeps.sweeps[0].i, ramp_sweeps.sweeps[0].t)
ramp_spx, ramp_spfx = dsf.extractors_for_sweeps(ramp_sweeps,
start = ramp_start,
**dsf.detection_parameters(data_set.RAMP))
ramp_an = spa.RampAnalysis(ramp_spx, ramp_spfx)
ramp_features = ramp_an.analyze(ramp_sweeps)
return ramp_sweeps, ramp_features, ramp_an
def run_feature_extraction(input_nwb_file,
stimulus_ontology_file,
output_nwb_file,
qc_fig_dir,
sweep_info,
cell_info,
write_spikes=True):
lu.log_pretty_header("Extract ephys features", level=1)
sp.drop_failed_sweeps(sweep_info)
if len(sweep_info) == 0:
raise er.FeatureError(
"There are no QC-passed sweeps available to analyze")
if not stimulus_ontology_file:
stimulus_ontology_file = StimulusOntology.DEFAULT_STIMULUS_ONTOLOGY_FILE
logging.info(
F"Ontology is not provided, using default {StimulusOntology.DEFAULT_STIMULUS_ONTOLOGY_FILE}"
)
ont = StimulusOntology(ju.read(stimulus_ontology_file))
data_set = create_ephys_data_set(sweep_info=sweep_info,
nwb_file=input_nwb_file,
ontology=ont)
(cell_features, sweep_features, cell_record, sweep_records, cell_state,
feature_states) = dsft.extract_data_set_features(data_set)
if cell_state['failed_fx']:
feature_data = {'cell_state': cell_state}
else:
if cell_info:
cell_record.update(cell_info)
feature_data = {
'cell_features': cell_features,
'sweep_features': sweep_features,
'cell_record': cell_record,
'sweep_records': sweep_records,
'cell_state': cell_state,
'feature_states': feature_states
}
if write_spikes:
if not feature_states['sweep_features_state']['failed_fx']:
sweep_spike_times = collect_spike_times(sweep_features)
append_spike_times(input_nwb_file,
sweep_spike_times,
output_nwb_path=output_nwb_file)
else:
logging.warn("extract_sweep_features failed, "
"unable to write spikes")
if qc_fig_dir is None:
logging.info("qc_fig_dir is not provided, will not save figures")
else:
plotqc.display_features(qc_fig_dir, data_set, feature_data)
# On Windows int64 keys of sweep numbers cannot be converted to str by json.dump when serializing.
# Thus, we are converting them here:
feature_data["sweep_features"] = {
str(k): v
for k, v in feature_data["sweep_features"].items()
}
return feature_data
