def in_minutes(x):
'''Convert a time quantity to minutes
Parameters
----------
x: unitfloat
A float representing a quantity of time annotated with a time unit
Returns
-------
unitfloat:
The time after conversion to minutes
'''
try:
unit = x.unit_info
except AttributeError:
return x
if unit == 'minute':
return x
elif unit == 'second':
y = unitfloat(x / 60., 'minute')
return y
elif unit == 'hour':
y = unitfloat(x * 60, 'minute')
return y
else:
warnings.warn("Time unit %r not recognized" % unit)
return x
def _acquisition_information(self, scan):
scan_info = {}
scan_list_struct = scan['scanList']
combination = "unknown"
if "no combination" in scan_list_struct:
combination = "no combination"
elif "sum of spectra" in scan_list_struct:
combination = "sum of spectra"
elif "median of spectra" in scan_list_struct:
combination = "median of spectra"
elif "mean of spectra" in scan_list_struct:
combination = "mean of spectra"
scan_info['combination'] = combination
scan_info_scan_list = []
misplaced_FAIMS_value = scan.get(FAIMS_compensation_voltage.name, None)
for i, scan_ in enumerate(scan_list_struct.get("scan", [])):
scan_ = scan_.copy()
if misplaced_FAIMS_value is not None and i == 0:
scan[FAIMS_compensation_voltage.name] = misplaced_FAIMS_value
struct = {}
struct['start_time'] = scan_.pop('scan start time', unitfloat(0, 'minute'))
struct['injection_time'] = scan_.pop("ion injection time", unitfloat(0, 'millisecond'))
windows = []
for window in scan_.pop("scanWindowList", {}).get("scanWindow", []):
windows.append(ScanWindow(
window['scan window lower limit'],
window['scan window upper limit']))
struct['window_list'] = windows
scan_.pop("instrumentConfigurationRef", None)
struct['traits'] = scan_
scan_info_scan_list.append(ScanEventInformation(**struct))
scan_info['scan_list'] = scan_info_scan_list
return ScanAcquisitionInformation(**scan_info)
def in_minutes(x):
'''Convert a time quantity to minutes
Parameters
----------
x: unitfloat
A float representing a quantity of time annotated with a time unit
Returns
-------
unitfloat:
The time after conversion to minutes
'''
try:
unit = x.unit_info
except AttributeError:
return x
if unit == 'minute':
return x
elif unit == 'second':
y = unitfloat(x / 60., 'minute')
return y
elif unit == 'hour':
y = unitfloat(x * 60, 'minute')
return y
else:
warnings.warn("Time unit %r not recognized" % unit)
return x
def in_minutes(x):
try:
unit = x.unit_info
except AttributeError:
return x
if unit == 'minute':
return x
elif unit == 'second':
y = unitfloat(x / 60., 'minute')
return y
elif unit == 'hour':
y = unitfloat(x * 60, 'minute')
return y
else:
warnings.warn("Time unit %r not recognized" % unit)
return x
def to_mzml(reader,
outstream,
pick_peaks=False,
ms1_filters=None,
msn_filters=None,
default_activation=None):
if ms1_filters is None:
ms1_filters = []
if msn_filters is None:
msn_filters = []
reader.make_iterator(grouped=True)
writer = MzMLSerializer(outstream, deconvoluted=False)
writer.copy_metadata_from(reader)
method = data_transformation.ProcessingMethod(software_id='ms_deisotope_1')
if pick_peaks:
method.add('MS:1000035')
method.add('MS:1000544')
writer.add_data_processing(method)
if default_activation is not None:
if isinstance(default_activation, basestring):
default_activation = activation_module.ActivationInformation(
default_activation, unitfloat(0, 'electronvolt'))
elif isinstance(default_activation, dict):
default_activation = activation_module.ActivationInformation(
**default_activation)
else:
click.secho("Could not convert %r into ActivationInformation" %
(default_activation, ),
err=1,
fg='yellow')
default_activation = None
if pick_peaks:
try:
writer.remove_file_contents("profile spectrum")
except KeyError:
pass
writer.add_file_contents("centroid spectrum")
for bunch in reader:
if bunch.precursor is not None:
if ms1_filters:
bunch = bunch._replace(
precursor=bunch.precursor.transform(ms1_filters))
if (pick_peaks or not bunch.precursor.is_profile):
bunch.precursor.pick_peaks()
for i, product in enumerate(bunch.products):
if msn_filters:
product = bunch.products[i] = product.transform(msn_filters)
if pick_peaks or not product.is_profile:
product.pick_peaks()
if product.activation is None and default_activation is not None:
product.activation = default_activation
writer.save_scan_bunch(bunch)
writer.complete()
writer.format()
def _acquisition_information(self, scan):
fline = self._filter_string(scan)
event = self._get_scan_event(scan)
trailer_extras = self._trailer_values(scan)
traits = {
'preset scan configuration': event,
'filter string': fline,
}
cv = fline.get("compensation_voltage")
if cv is not None:
traits[FAIMS_compensation_voltage] = cv
event = ScanEventInformation(self._scan_time(scan),
injection_time=unitfloat(
trailer_extras.get(
'Ion Injection Time (ms)', 0.0),
'millisecond'),
window_list=[
ScanWindow(
fline.get("scan_window")[0],
fline.get("scan_window")[1])
],
traits=traits)
return ScanAcquisitionInformation("no combination", [event])
def _handle_param(self, element, **kwargs):
"""Unpacks cvParam and userParam tags into key-value pairs"""
types = {'int': unitint, 'float': unitfloat, 'string': unitstr}
attribs = element.attrib
unit_info = None
unit_accesssion = None
if 'unitCvRef' in attribs or 'unitName' in attribs:
unit_accesssion = attribs.get('unitAccession')
unit_name = attribs.get("unitName", unit_accesssion)
unit_info = unit_name
accession = attribs.get("accession")
# value = attribs.get("value", "")
if 'value' in attribs and attribs['value'] != '':
try:
if attribs.get('type') in types:
value = types[attribs['type']](attribs['value'], unit_info)
else:
value = unitfloat(attribs['value'], unit_info)
except ValueError:
value = unitstr(attribs['value'], unit_info)
return {cvstr(attribs['name'], accession, unit_accesssion): value}
else:
return {'name': cvstr(attribs['name'], accession, unit_accesssion)}
def to_mzml(reader,
outstream,
pick_peaks=False,
reprofile=False,
ms1_filters=None,
msn_filters=None,
default_activation=None,
correct_precursor_mz=False,
write_index=True,
update_metadata=True):
"""Translate the spectra from `reader` into mzML format written to `outstream`.
Wraps the process of iterating over `reader`, performing a set of simple data transformations if desired,
and then converts each :class:`~.Scan` into mzML format. Any data transformations are described in the
appropriate metadata section. All other metadata from `reader` is copied to into `outstream`.
Parameters
----------
reader : :class:`~.ScanIterator`
The source of spectra to iterate over
outstream : file-like
The output stream to write mzML to.
pick_peaks : bool, optional
Whether to centroid profile spectra (the default is False)
reprofile: bool, optional
Whether to reprofile spectra from their centroids (the default is False)
ms1_filters : list, optional
An optional list of strings or :class:`~.ScanFilterBase` instances which will be
used to transform the m/z and intensity arrays of MS1 spectra before they are further
processed (the default is None, which results in no transformations)
msn_filters : list, optional
An optional list of strings or :class:`~.ScanFilterBase` instances which will be
used to transform the m/z and intennsity arrays of MSn spectra before they are futher
procssed. (the default is None, which results in no transformations)
default_activation : :class:`str` or :class:`dict`, optional
A default activation type to use when `reader` does not contain that information (the default is None)
correct_precursor_mz : bool, optional
Whether or not to assign the precursor m/z of each product scan to the nearest peak
m/z in the precursor's peak list. (the default is False, which results in no correction)
"""
if ms1_filters is None:
ms1_filters = []
if msn_filters is None:
msn_filters = []
reader.make_iterator(grouped=True)
writer = MzMLSerializer(outstream,
len(reader),
deconvoluted=False,
build_extra_index=write_index,
include_software_entry=update_metadata)
writer.copy_metadata_from(reader)
if update_metadata:
method = data_transformation.ProcessingMethod(
software_id='ms_deisotope_1')
if pick_peaks:
method.add('MS:1000035')
if correct_precursor_mz:
method.add('MS:1000780')
if reprofile:
method.add('MS:1000784')
method.add('MS:1000544')
writer.add_data_processing(method)
if default_activation is not None:
if isinstance(default_activation, basestring):
default_activation = activation_module.ActivationInformation(
default_activation, unitfloat(0, 'electronvolt'))
elif isinstance(default_activation, dict):
default_activation = activation_module.ActivationInformation(
**default_activation)
else:
click.secho("Could not convert %r into ActivationInformation" %
(default_activation, ),
err=1,
fg='yellow')
default_activation = None
if pick_peaks:
try:
writer.remove_file_contents("profile spectrum")
except KeyError:
pass
writer.add_file_contents("centroid spectrum")
n_spectra = len(reader)
progbar = progress(
label="Processed Spectra",
length=n_spectra,
item_show_func=lambda x: str(x.precursor.id
if x.precursor else x.products[0].id)
if x else '')
with progbar:
for bunch in reader:
progbar.current_item = bunch
progbar.update((bunch.precursor is not None) + len(bunch.products))
discard_peaks = False
if bunch.precursor is not None:
if (reprofile):
bunch = bunch._replace(
precursor=bunch.precursor.reprofile())
if ms1_filters:
bunch = bunch._replace(
precursor=bunch.precursor.transform(ms1_filters))
if (pick_peaks or not bunch.precursor.is_profile):
bunch.precursor.pick_peaks()
if correct_precursor_mz:
if not pick_peaks:
bunch.precursor.pick_peaks()
if bunch.precursor.is_profile:
discard_peaks = True
for i, product in enumerate(bunch.products):
# if reprofile:
# product = bunch.products[i] = product.reprofile()
if msn_filters:
product = bunch.products[i] = product.transform(
msn_filters)
if pick_peaks or not product.is_profile:
product.pick_peaks()
if product.activation is None and default_activation is not None:
product.activation = default_activation
if correct_precursor_mz:
product.precursor_information.correct_mz()
if discard_peaks:
bunch.precursor.peak_set = None
writer.save_scan_bunch(bunch)
writer.complete()
writer.format()
def to_mzml(reader, outstream, pick_peaks=False, ms1_filters=None, msn_filters=None, default_activation=None,
correct_precursor_mz=False):
"""Translate the spectra from `reader` into mzML format written to `outstream`.
Wraps the process of iterating over `reader`, performing a set of simple data transformations if desired,
and then converts each :class:`~.Scan` into mzML format. Any data transformations are described in the
appropriate metadata section. All other metadata from `reader` is copied to into `outstream`.
Parameters
----------
reader : :class:`~.ScanIterator`
The source of spectra to iterate over
outstream : file-like
The output stream to write mzML to.
pick_peaks : bool, optional
Whether to centroid profile spectra (the default is False)
ms1_filters : list, optional
An optional list of strings or :class:`~.ScanFilterBase` instances which will be
used to transform the m/z and intensity arrays of MS1 spectra before they are further
processed (the default is None, which results in no transformations)
msn_filters : list, optional
An optional list of strings or :class:`~.ScanFilterBase` instances which will be
used to transform the m/z and intennsity arrays of MSn spectra before they are futher
procssed. (the default is None, which results in no transformations)
default_activation : :class:`str` or :class:`dict`, optional
A default activation type to use when `reader` does not contain that information (the default is None)
correct_precursor_mz : bool, optional
Whether or not to assign the precursor m/z of each product scan to the nearest peak
m/z in the precursor's peak list. (the default is False, which results in no correction)
"""
if ms1_filters is None:
ms1_filters = []
if msn_filters is None:
msn_filters = []
reader.make_iterator(grouped=True)
writer = MzMLSerializer(outstream, len(reader), deconvoluted=False)
writer.copy_metadata_from(reader)
method = data_transformation.ProcessingMethod(software_id='ms_deisotope_1')
if pick_peaks:
method.add('MS:1000035')
if correct_precursor_mz:
method.add('MS:1000780')
method.add('MS:1000544')
writer.add_data_processing(method)
if default_activation is not None:
if isinstance(default_activation, basestring):
default_activation = activation_module.ActivationInformation(
default_activation, unitfloat(0, 'electronvolt'))
elif isinstance(default_activation, dict):
default_activation = activation_module.ActivationInformation(**default_activation)
else:
click.secho("Could not convert %r into ActivationInformation" % (default_activation, ), err=1,
fg='yellow')
default_activation = None
if pick_peaks:
try:
writer.remove_file_contents("profile spectrum")
except KeyError:
pass
writer.add_file_contents("centroid spectrum")
for bunch in reader:
discard_peaks = False
if bunch.precursor is not None:
if ms1_filters:
bunch = bunch._replace(precursor=bunch.precursor.transform(ms1_filters))
if (pick_peaks or not bunch.precursor.is_profile):
bunch.precursor.pick_peaks()
if correct_precursor_mz:
if not pick_peaks:
bunch.precursor.pick_peaks()
if bunch.precursor.is_profile:
discard_peaks = True
for i, product in enumerate(bunch.products):
if msn_filters:
product = bunch.products[i] = product.transform(msn_filters)
if pick_peaks or not product.is_profile:
product.pick_peaks()
if product.activation is None and default_activation is not None:
product.activation = default_activation
if correct_precursor_mz:
product.precursor_information.correct_mz()
if discard_peaks:
bunch.precursor.peak_set = None
writer.save_scan_bunch(bunch)
writer.complete()
writer.format()