def _simplify_peak_set(peaks, bin_width=5.0):
bin_edges = np.arange(0, peaks[-1].mz + bin_width, bin_width)
bins = []
for i, bin_edge in enumerate(bin_edges, 1):
if i == len(bin_edges):
next_edge = bin_edges[-1] + bin_width
else:
next_edge = bin_edges[i]
subset = peaks.between(bin_edge, next_edge)
bins.append(subset)
thresholds = []
reduced_subsets = {}
k = 0
for b in bins:
if len(b) > 0:
bin_intensities = np.array([p.intensity for p in b])
thresholds.append(np.max(bin_intensities) / 3.)
for p in b:
if p.intensity > thresholds[-1]:
reduced_subsets[p.peak_count] = p
k += (bin_intensities > thresholds[-1]).sum()
else:
thresholds.append(0.0)
subset_peaks = PeakSet(sorted(reduced_subsets.values(),
key=lambda x: x.mz)).clone()
subset_peaks.reindex()
return PeakIndex(np.array([]), np.array([]), subset_peaks)
def convert_map_to_scan_peak_list(feature_map,
peak_loader,
time_precision=4,
deconvoluted=True):
metadata_map = {}
scan_accumulator = defaultdict(list)
for scan_id, metadata in peak_loader.extended_index.ms1_ids.items():
metadata_map[round(metadata["scan_time"], time_precision)] = metadata
for feature in feature_map:
for node in feature:
scan_accumulator[round(node.time,
time_precision)].extend(node.members)
packed = []
for key, peaks in sorted(scan_accumulator.items(), key=lambda x: x[0]):
template = peak_loader.get_scan_by_time(key)
if deconvoluted:
peak_set = PeakSet([])
deconvoluted_peak_set = DeconvolutedPeakSet(peaks)
else:
peak_set = PeakSet(peaks)
deconvoluted_peak_set = DeconvolutedPeakSet([])
peak_set.reindex()
deconvoluted_peak_set.reindex()
scan = ProcessedScan(template.id, template.title, None,
template.ms_level, template.scan_time,
template.index, peak_set, deconvoluted_peak_set,
template.polarity, None)
packed.append(scan)
return packed
def convert_map_to_scan_peak_list(feature_map, peak_loader, time_precision=4, deconvoluted=True):
metadata_map = {}
scan_accumulator = defaultdict(list)
for scan_id, metadata in peak_loader.extended_index.ms1_ids.items():
metadata_map[round(metadata["scan_time"], time_precision)] = metadata
for feature in feature_map:
for node in feature:
scan_accumulator[round(node.time, time_precision)].extend(node.members)
packed = []
for key, peaks in sorted(scan_accumulator.items(), key=lambda x: x[0]):
template = peak_loader.get_scan_by_time(key)
if deconvoluted:
peak_set = PeakSet([])
deconvoluted_peak_set = DeconvolutedPeakSet(peaks)
else:
peak_set = PeakSet(peaks)
deconvoluted_peak_set = DeconvolutedPeakSet([])
peak_set.reindex()
deconvoluted_peak_set.reindex()
scan = ProcessedScan(
template.id, template.title, None, template.ms_level, template.scan_time,
template.index, peak_set, deconvoluted_peak_set, template.polarity,
None)
packed.append(scan)
return packed
def _pick_peaks_vendor(self, scan, *args, **kwargs):
scan_info = Business.Scan.FromFile(self._source, scan.scan_number + 1)
if scan_info.HasCentroidStream:
stream = self._source.GetCentroidStream(scan.scan_number + 1, 0)
mzs = stream.Masses
intens = stream.Intensities
peaks = PeakSet([simple_peak(mzs[i], intens[i], 0.001) for i in range(len(mzs))])
peaks.reindex()
arrays = self._scan_arrays(scan)
return PeakIndex(arrays[0], arrays[1], peaks)
else:
raise NotImplementedError()
def deserialize_peak_set(scan_dict):
mz_array = scan_dict['m/z array']
intensity_array = scan_dict['intensity array']
n = len(scan_dict['m/z array'])
peaks = []
for i in range(n):
peak = FittedPeak(
mz_array[i], intensity_array[i], 1, i, i,
0, intensity_array[i], 0, 0)
peaks.append(peak)
peak_set = PeakSet(peaks)
peak_set.reindex()
return PeakIndex(np.array([]), np.array([]), peak_set)
def envelopes_to_peak_set(self):
"""Convert a set of deconvoluted peaks with fitted isotopic envelopes into a
set of centroids representing those envelope peaks.
Returns
-------
:class:`ms_peak_picker.PeakSet`
"""
peaks = []
for peak in self:
for point in peak.envelope:
peaks.append(
simple_peak(point.mz, point.intensity, peak.full_width_at_half_max))
new_peak_set = FittedPeakSet(peaks)
new_peak_set.reindex()
return new_peak_set
def prepare_peaklist(peaks):
'''Ensure ``peaks`` is a :class:`~.PeakSet` object,
converting from other compatible types as needed. Additionally, make a deep
copy of the peaks as signal subtraction methods will modify peaks in place.
This function ensures that any of the following common input types are coerced
to the appropriate type:
1. :class:`ms_peak_picker.PeakSet` will be copied and indexed
2. :class:`ms_peak_picker.PeakIndex` will have its peaks extracted and copied
3. Any other *sequence* of :class:`PeakLike` objects (objects having an mz and
intensity attribute) will be converted into a :class:`ms_peak_picker.PeakSet`
4. Any *sequence* of :class:`tuple` or :class:`list` having at least two entries
will be converted into a :class:`ms_peak_picker.PeakSet` with the m/z value
of each peak being the the `p[0]` of each entry and the intensity `p[1]`. Any
other entries will be ignored.
Parameters
----------
peaks: Sequence
Any sequence of :class:`~.FittedPeak` objects, objects
with ``mz`` and ``intensity`` attributes, or :class:`list` / :class:`tuple`
objects containing paired values for ``mz`` and ``intensity``
Returns
-------
:class:`~.PeakSet`
'''
if isinstance(peaks, PeakIndex):
peaks = PeakSet(peaks.peaks).clone()
else:
peaks = tuple(peaks)
if len(peaks) == 0:
return PeakSet([])
if not isinstance(peaks[0], FittedPeak):
if is_peak(peaks[0]):
peaks = [simple_peak(p.mz, p.intensity, 0.01) for p in peaks]
elif isinstance(peaks[0], (list, tuple)):
peaks = [simple_peak(p[0], p[1], 0.01) for p in peaks]
else:
raise TypeError("Cannot convert peaks into a PeakSet")
peaks = PeakSet(peaks).clone()
peaks.reindex()
return peaks