def _make_deconvoluted_peak_solution(self, fit, composition, charge_carrier):
eid = fit.experimental
tid = fit.theoretical
charge = fit.charge
rep_eid = drop_placeholders(eid)
total_abundance = sum(
p.intensity for p in eid if p.intensity > 1)
monoisotopic_mass = neutral_mass(
tid.monoisotopic_mz, charge, charge_carrier)
monoisotopic_mz = tid.monoisotopic_mz
reference_peak = first_peak(eid)
peak = DeconvolutedPeakSolution(
composition, fit,
monoisotopic_mass, total_abundance, charge,
signal_to_noise=mean(p.signal_to_noise for p in rep_eid),
index=reference_peak.index,
full_width_at_half_max=mean(
p.full_width_at_half_max for p in rep_eid),
a_to_a2_ratio=a_to_a2_ratio(tid),
most_abundant_mass=neutral_mass(
most_abundant_mz(eid), charge),
average_mass=neutral_mass(average_mz(eid), charge),
score=fit.score,
envelope=[(p.mz, p.intensity) for p in rep_eid],
mz=monoisotopic_mz, area=sum(e.area for e in eid))
return peak
def _make_deconvoluted_peak_solution(self, fit, composition, charge_carrier):
eid = fit.experimental
tid = fit.theoretical
charge = fit.charge
rep_eid = drop_placeholders(eid)
total_abundance = sum(
p.intensity for p in eid if p.intensity > 1)
monoisotopic_mass = neutral_mass(
tid.monoisotopic_mz, charge, charge_carrier)
monoisotopic_mz = tid.monoisotopic_mz
reference_peak = first_peak(eid)
peak = DeconvolutedPeakSolution(
composition, fit,
monoisotopic_mass, total_abundance, charge,
signal_to_noise=mean(p.signal_to_noise for p in rep_eid),
index=reference_peak.index,
full_width_at_half_max=mean(
p.full_width_at_half_max for p in rep_eid),
a_to_a2_ratio=a_to_a2_ratio(tid),
most_abundant_mass=neutral_mass(
most_abundant_mz(eid), charge),
average_mass=neutral_mass(average_mz(eid), charge),
score=fit.score,
envelope=[(p.mz, p.intensity) for p in rep_eid],
mz=monoisotopic_mz, area=sum(e.area for e in eid))
return peak
def _make_deconvoluted_peak(self, fit, charge_carrier):
score, charge, eid, tid = fit
rep_eid = drop_placeholders(eid)
total_abundance = sum(p.intensity for p in rep_eid)
monoisotopic_mass = neutral_mass(tid.monoisotopic_mz, charge,
charge_carrier)
reference_peak = first_peak(eid)
dpeak = DeconvolutedPeak(
neutral_mass=monoisotopic_mass,
intensity=total_abundance,
charge=charge,
signal_to_noise=mean(p.signal_to_noise for p in rep_eid),
index=reference_peak.index,
full_width_at_half_max=mean(p.full_width_at_half_max
for p in rep_eid),
a_to_a2_ratio=a_to_a2_ratio(tid),
most_abundant_mass=neutral_mass(most_abundant_mz(eid), charge),
average_mass=neutral_mass(average_mz(eid), charge),
score=score,
envelope=[(p.mz, p.intensity) for p in eid],
mz=tid.monoisotopic_mz,
fit=fit,
area=sum(e.area for e in eid))
return dpeak
def _make_deconvoluted_peak(self, fit, charge_carrier):
score, charge, eid, tid = fit
rep_eid = drop_placeholders(eid)
total_abundance = sum(p.intensity for p in rep_eid)
monoisotopic_mass = neutral_mass(
tid.monoisotopic_mz, charge, charge_carrier)
reference_peak = first_peak(eid)
dpeak = DeconvolutedPeak(
neutral_mass=monoisotopic_mass, intensity=total_abundance, charge=charge,
signal_to_noise=mean(p.signal_to_noise for p in rep_eid),
index=reference_peak.index,
full_width_at_half_max=mean(
p.full_width_at_half_max for p in rep_eid),
a_to_a2_ratio=a_to_a2_ratio(tid),
most_abundant_mass=neutral_mass(
most_abundant_mz(eid), charge),
average_mass=neutral_mass(average_mz(eid), charge),
score=score,
envelope=[(p.mz, p.intensity) for p in eid],
mz=tid.monoisotopic_mz, fit=fit,
area=sum(e.area for e in eid))
return dpeak
def finalize_fit(self,
feature_fit,
charge_carrier=PROTON,
subtract=True,
detection_threshold=0.1,
max_missed_peaks=1):
nodes = []
start_time, end_time, _segments = find_bounds(feature_fit,
detection_threshold)
feat_iter = FeatureSetIterator(feature_fit.features, start_time,
end_time)
base_tid = feature_fit.theoretical
charge = feature_fit.charge
abs_charge = abs(charge)
for eid in feat_iter:
cleaned_eid, tid, n_missing = conform_envelopes(
eid, base_tid.peaklist)
rep_eid = drop_placeholders(cleaned_eid)
n_real_peaks = len(rep_eid)
if n_real_peaks == 0 or (n_real_peaks == 1 and abs_charge > 1) or \
n_missing > max_missed_peaks:
continue
score = self.scorer.evaluate(None, cleaned_eid, tid)
is_valid = True
if np.isnan(score) or score < 0:
is_valid = False
envelope = [(e.mz, min(e.intensity, t.intensity))
for e, t in zip(cleaned_eid, tid)]
if is_valid:
total_abundance = sum(p[1] for p in envelope)
monoisotopic_mass = neutral_mass(base_tid.monoisotopic_mz,
charge,
charge_carrier=charge_carrier)
reference_peak = first_peak(cleaned_eid)
dpeak = DeconvolutedPeak(
neutral_mass=monoisotopic_mass,
intensity=total_abundance,
charge=charge,
signal_to_noise=mean(p.signal_to_noise for p in rep_eid),
index=reference_peak.index,
full_width_at_half_max=mean(p.full_width_at_half_max
for p in rep_eid),
a_to_a2_ratio=a_to_a2_ratio(tid),
most_abundant_mass=neutral_mass(
most_abundant_mz(cleaned_eid),
charge,
charge_carrier=charge_carrier),
average_mass=neutral_mass(average_mz(cleaned_eid),
charge,
charge_carrier=charge_carrier),
score=score,
envelope=envelope,
mz=base_tid.monoisotopic_mz,
area=sum(e.area for e in cleaned_eid))
time = feat_iter.current_time
precursor_info_set = []
for peak in rep_eid:
pinfo = self.precursor_map.precursor_for_peak(
(time, peak.index))
if pinfo is not None:
precursor_info_set.append(pinfo)
node = DeconvolutedLCMSFeatureTreeNode(time, [dpeak],
precursor_info_set)
nodes.append(node)
if subtract:
for fpeak, tpeak in zip(cleaned_eid, envelope):
# If a theoretical peak uses up more than 70%
# of the abundance of a single peak, this peak
# should not contribute meaninfully to any other
# fits from now on. Set it's abundance to 1.0 as
# if it were fully used up.
ruin = (fpeak.intensity * 0.7) < tpeak[1]
if ruin:
fpeak.intensity = 1.0
else:
fpeak.intensity -= tpeak[1]
if fpeak.intensity < 0:
fpeak.intensity = 1.0
for feature in feature_fit.features:
if feature is None or isinstance(feature, EmptyFeature):
continue
feature.invalidate()
if len(nodes) < self.minimum_size:
return None
result_feature = DeconvolutedLCMSFeature(
nodes,
feature_fit.charge,
score=feature_fit.score,
n_features=len(feature_fit),
supporters=feature_fit.supporters)
return result_feature
def finalize_fit(self, feature_fit, charge_carrier=PROTON, subtract=True,
detection_threshold=0.1, max_missed_peaks=1):
nodes = []
start_time, end_time = find_bounds(feature_fit, detection_threshold)
feat_iter = FeatureSetIterator(
feature_fit.features, start_time, end_time)
base_tid = feature_fit.theoretical
charge = feature_fit.charge
abs_charge = abs(charge)
for eid in feat_iter:
cleaned_eid, tid, n_missing = conform_envelopes(eid, base_tid.truncated_tid)
rep_eid = drop_placeholders(cleaned_eid)
n_real_peaks = len(rep_eid)
if n_real_peaks == 0 or (n_real_peaks == 1 and abs_charge > 1) or \
n_missing > max_missed_peaks:
continue
score = self.scorer.evaluate(None, cleaned_eid, tid)
is_valid = True
if np.isnan(score) or score < 0:
is_valid = False
envelope = [(e.mz, min(e.intensity, t.intensity)) for e, t in zip(cleaned_eid, tid)]
if is_valid:
total_abundance = sum(p[1] for p in envelope)
monoisotopic_mass = neutral_mass(
base_tid.monoisotopic_mz, charge, charge_carrier=charge_carrier)
reference_peak = first_peak(cleaned_eid)
dpeak = DeconvolutedPeak(
neutral_mass=monoisotopic_mass, intensity=total_abundance,
charge=charge,
signal_to_noise=mean(p.signal_to_noise for p in rep_eid),
index=reference_peak.index,
full_width_at_half_max=mean(p.full_width_at_half_max for p in rep_eid),
a_to_a2_ratio=a_to_a2_ratio(tid),
most_abundant_mass=neutral_mass(
most_abundant_mz(cleaned_eid), charge, charge_carrier=charge_carrier),
average_mass=neutral_mass(
average_mz(cleaned_eid), charge, charge_carrier=charge_carrier),
score=score,
envelope=envelope,
mz=base_tid.monoisotopic_mz,
area=sum(e.area for e in cleaned_eid))
time = feat_iter.current_time
precursor_info_set = []
for peak in rep_eid:
pinfo = self.precursor_map.precursor_for_peak((time, peak.index))
if pinfo is not None:
precursor_info_set.append(pinfo)
node = DeconvolutedLCMSFeatureTreeNode(time, [dpeak], precursor_info_set)
nodes.append(node)
if subtract:
for fpeak, tpeak in zip(cleaned_eid, envelope):
# If a theoretical peak uses up more than 70%
# of the abundance of a single peak, this peak
# should not contribute meaninfully to any other
# fits from now on. Set it's abundance to 1.0 as
# if it were fully used up.
ruin = (fpeak.intensity * 0.7) < tpeak[1]
if ruin:
fpeak.intensity = 1.0
else:
fpeak.intensity -= tpeak[1]
if fpeak.intensity < 0:
fpeak.intensity = 1.0
for feature in feature_fit.features:
if feature is None or isinstance(feature, EmptyFeature):
continue
feature.invalidate()
if len(nodes) < self.minimum_size:
return None
result_feature = DeconvolutedLCMSFeature(
nodes, feature_fit.charge,
score=feature_fit.score, n_features=len(feature_fit),
supporters=feature_fit.supporters)
return result_feature