def get_dataset_metadata(self):
"""
Get dict of additional metadata associated with the current dataset
NOTE: In the case that multiple regions and/or datasets are supported,
this function should return the metadata of the currently selected
dataset only. If no particular dataset is selected, then all should
be returned.
:return: Instance of omsi.shared.metadata_data.metadata_dict
"""
return metadata_dict()
def get_metadata(self, key=None):
"""
Get dict with the full description of the metadata for the given key or all
metadata if no key is given.
:param key: The name of the metadata object to be retrieved. Default is None in
which case all metadata will be retrieved.
:returns: `omsi.shared.metadata_data.metadata_value` object if a key is given
or a `omsi.shared.metadata_data.metadata_dict` with all metadata
if key is set to None.
:raises: KeyError is raised in case that the specified key does not exist
"""
descr_attr = omsi_format_metadata_collection.description_value_attribute
unit_attr = omsi_format_metadata_collection.unit_value_attribute
ontology_attr = omsi_format_metadata_collection.ontology_value_attribute
isjson_attr = omsi_format_metadata_collection.is_json_dict_attribute
if key is None:
output_meta_dict = metadata_dict()
for metadata_name, metadata_dataset in self.managed_group.iteritems():
unit = None if unit_attr not in metadata_dataset.attrs else metadata_dataset.attrs[unit_attr]
description = None if descr_attr not in metadata_dataset.attrs else metadata_dataset.attrs[descr_attr]
ontology = None if ontology_attr not in metadata_dataset.attrs else \
json.loads(metadata_dataset.attrs[ontology_attr])
md_value = metadata_dataset[:] if len(metadata_dataset.shape) > 0 else metadata_dataset[()]
if isjson_attr in metadata_dataset.attrs:
try:
md_value = json.loads(md_value)
except:
log_helper.error(__name__, "Parsing of json metadata object failed for " + str(metadata_name))
output_meta_dict[metadata_name] = metadata_value(
name=metadata_name,
value=md_value,
description=description,
unit=unit,
ontology=ontology)
return output_meta_dict
else:
metadata_dataset = self.managed_group[key]
unit = None if unit_attr not in metadata_dataset.attrs else metadata_dataset.attrs[unit_attr]
description = None if descr_attr not in metadata_dataset.attrs else metadata_dataset.attrs[descr_attr]
ontology = None if ontology_attr not in metadata_dataset.attrs else \
json.loads(metadata_dataset.attrs[ontology_attr])
return metadata_value(
name=key,
value=metadata_dataset[:],
description=description,
unit=unit,
ontology=ontology)
def __create__(cls,
parent_group,
instrument_name=None,
mzdata=None,
flush_io=True):
"""
Create an instrument group and populate it with the given data.
:param parent_group: The parent h5py group where the instrument group should be created in.
:type parent_group. h5py.Group
:param instrument_name: The name of the instrument
:type instrument_name: string, None
:param mzdata: Numpy array of the mz data values of the instrument
:type mzdata: numpy array or None
:param flush_io: Call flush on the HDF5 file to ensure all HDF5 bufferes are flushed so that all
data has been written to file
:returns: The function returns the h5py HDF5 handler to the instrument info group created for the experiment.
"""
if instrument_name is not None or mzdata is not None:
all_meta = metadata_dict()
if instrument_name is not None:
all_meta[omsi_format_instrument.instrument_name] = \
metadata_value(value=instrument_name,
name=omsi_format_instrument.instrument_name,
description='Name of the instrument')
if mzdata is not None:
all_meta[omsi_format_instrument.instrument_name] = \
metadata_value(value=mzdata,
name=omsi_format_instrument.instrument_mz_name,
description='The global m/z axis for the recordings')
else:
all_meta = None
# Initialize the group and populate the data using the create method of the parent class
metadata_obj = omsi_file_metadata_collection.___create___(
parent_group=parent_group,
group_name=omsi_format_instrument.instrument_groupname,
metadata=all_meta,
type_attr_value="omsi_file_instrument",
version_attr_value=omsi_format_instrument.current_version,
flush_io=flush_io)
if flush_io:
parent_group.file.flush()
return omsi_file_instrument.__create_instrument_info___(instrument_group=metadata_obj.managed_group)
def __parse_scan_parameters(self):
"""
Internal helper function used to parse out scan parameters from the scan filter string
"""
# precursor m/z
# example scan filter: MS2: ITMS + p MALDI Z ms2 [email protected] [500.00-700.00]
## example scan filter: MS1: FTMS + p MALDI Full ms [850.00-1000.00]
scan_params = []
for scan_idx, scantype in enumerate(self.scan_types):
#MSnValueOfN
n = filter(None, re.findall('(?<=ms)\d*', scantype))
if n:
MSnValueOfN = int(n[0])
else:
MSnValueOfN = 1
#precursor
ms2pre = filter(None, re.findall('[\d.]+(?=@)', scantype))
if ms2pre:
ms2_precursor = float(ms2pre[0])
else:
ms2_precursor = None
#dissociation type
dissot = filter(None, re.findall('(?<=\d@)[A-z]*', scantype))
if dissot:
dissociationtype = dissot[0]
else:
dissociationtype = 'None'
#dissociation energy
dissoe = filter(None, re.findall('(?<='+dissociationtype+')'+'[\d.]+', scantype))
if dissoe:
dissociationenergy = float(dissoe[0])
else:
dissociationenergy = None
#polarity
pol = filter(None, re.findall('([+][ ]p)', scantype))
if pol:
polarity = 'pos'
else:
pol = filter(None, re.findall('([-][ ]p)', scantype))
if pol:
polarity = 'neg'
else:
polarity = 'unk'
#put all params in dictionary
paramdict = metadata_dict()
msn_von_ontology = METADATA_ONTOLOGIES['msn_value_of_n']
paramdict['msn_value_of_n'] = metadata_value(name='msn_value_of_n',
value=MSnValueOfN,
unit=msn_von_ontology['unit'],
description=msn_von_ontology['description'],
ontology=msn_von_ontology)
if dissociationenergy:
paramdict['dissociation_energy'] = metadata_value(name='dissociation_energy',
value=dissociationenergy,
unit='V',
description='Dissociation energy')
if ms2_precursor is not None:
paramdict['msn_precursor_mz'] = metadata_value(name='msn_precursor_mz',
value=ms2_precursor,
unit='m/z',
description='The precursor m/z value')
paramdict['dissociation_type'] = metadata_value(name='dissociation_type',
value=dissociationtype,
unit=None,
description='Dissociation type')
polarity_ontology = METADATA_ONTOLOGIES['polarity']
paramdict['polarity'] = metadata_value(name='polarity',
value=polarity,
unit=polarity_ontology['unit'],
description=polarity_ontology['description'],
ontology=polarity_ontology)
scan_params.append(paramdict)
return scan_params
def __parse_scan_parameters(self):
"""
Internal helper function used to parse out scan parameters from the scan filter string
"""
# precursor m/z
# example scan filter: MS2: ITMS + p MALDI Z ms2 [email protected] [500.00-700.00]
## example scan filter: MS1: FTMS + p MALDI Full ms [850.00-1000.00]
scan_params = []
for scan_idx, scantype in enumerate(self.scan_types):
#MSnValueOfN
n = filter(None, re.findall('(?<=ms)\d*', scantype))
if n:
MSnValueOfN = int(n[0])
else:
MSnValueOfN = 1
#precursor
ms2pre = filter(None, re.findall('[\d.]+(?=@)', scantype))
if ms2pre:
ms2_precursor = float(ms2pre[0])
else:
ms2_precursor = None
#dissociation type
dissot = filter(None, re.findall('(?<=\d@)[A-z]*', scantype))
if dissot:
dissociationtype = dissot[0]
else:
dissociationtype = 'None'
#dissociation energy
dissoe = filter(
None,
re.findall('(?<=' + dissociationtype + ')' + '[\d.]+',
scantype))
if dissoe:
dissociationenergy = float(dissoe[0])
else:
dissociationenergy = None
#polarity
pol = filter(None, re.findall('([+][ ]p)', scantype))
if pol:
polarity = 'pos'
else:
pol = filter(None, re.findall('([-][ ]p)', scantype))
if pol:
polarity = 'neg'
else:
polarity = 'unk'
#put all params in dictionary
paramdict = metadata_dict()
msn_von_ontology = METADATA_ONTOLOGIES['msn_value_of_n']
paramdict['msn_value_of_n'] = metadata_value(
name='msn_value_of_n',
value=MSnValueOfN,
unit=msn_von_ontology['unit'],
description=msn_von_ontology['description'],
ontology=msn_von_ontology)
if dissociationenergy:
paramdict['dissociation_energy'] = metadata_value(
name='dissociation_energy',
value=dissociationenergy,
unit='V',
description='Dissociation energy')
if ms2_precursor is not None:
paramdict['msn_precursor_mz'] = metadata_value(
name='msn_precursor_mz',
value=ms2_precursor,
unit='m/z',
description='The precursor m/z value')
paramdict['dissociation_type'] = metadata_value(
name='dissociation_type',
value=dissociationtype,
unit=None,
description='Dissociation type')
polarity_ontology = METADATA_ONTOLOGIES['polarity']
paramdict['polarity'] = metadata_value(
name='polarity',
value=polarity,
unit=polarity_ontology['unit'],
description=polarity_ontology['description'],
ontology=polarity_ontology)
scan_params.append(paramdict)
return scan_params
def __compute_file_info(cls, filename, resolution):
## TODO completely refactor this to make it smartly handle profile or centroid datasets
## TODO: centroid datasets should take in a user parameter "Resolution" and resample data at that resolution
## TODO: profile datasets should work as is
## TODO: checks for profile data vs. centroid data on the variation in length of ['m/z array']
"""
Internal helper function used to compute the mz axis, data type for the intensities, format type
:return: Numpy array with mz axis
:return: string with data type
:return: imzml file type
:return:
"""
reader = ImzMLParser(filename)
# Read the first spectrum
mz_axes, intens = reader.getspectrum(0) # NOTE: mz_axes is a tuple
# Read the coordinates
coordinates = np.asarray(reader.coordinates)
# Determine the data type for the internsity values
dtype = np.asarray(intens).dtype.str
# Compute the mz axis and file type
file_type = cls.available_imzml_types['continuous']
min_mz, max_mz = np.amin(mz_axes), np.amax(mz_axes)
for ind in range(coordinates.shape[0]
): #for ind, loc in enumerate(reader.coordinates):
mz, intens = reader.getspectrum(ind)
if mz == mz_axes:
pass
else:
file_type = cls.available_imzml_types['processed']
if min_mz > np.amin(mz):
min_mz = np.amin(mz)
if max_mz < np.amax(mz):
max_mz = np.amax(mz)
# Reinterpolate the mz-axis if we have a processed mode imzml file
if file_type == cls.available_imzml_types['processed']:
f = np.ceil(1e6 * np.log(max_mz / min_mz) / resolution)
mz_axes = np.logspace(np.log10(min_mz), np.log10(max_mz), f)
log_helper.info(
__name__, "Reinterpolated m/z axis for processed imzML file")
# Construct the imzml metadata information
dataset_metadata = metadata_dict()
instrument_metadata = metadata_dict()
method_metadata = metadata_dict()
for k, v in reader.imzmldict.iteritems():
dataset_metadata[k] = metadata_value(name=k,
value=v,
unit=None,
description=k,
ontology=None)
# Delete the parser and read the metadata
del reader
# Parse the metadata for the file. We try to parse only the header and ignore the
# <run > group in the XML file to avoid going throught the whole file again
# while extracting the majority of the relevant metadata
try:
with open(filename, 'r') as ins:
metdata_header = ''
for line in ins:
if '<run' in line:
break
else:
metdata_header += line
metdata_header += '</mzML>'
metdata_header_dict = xmltodict.parse(metdata_header)['mzML']
for k, v in metdata_header_dict.iteritems():
store_value = metadata_value(
name=k,
value=v,
unit=None,
description=str(k) +
" extracted from imzML XML header.",
ontology=None)
if k == 'instrumentConfigurationList':
instrument_metadata[k] = store_value
elif k == 'dataProcessingList':
method_metadata[k] = store_value
elif k == 'scanSettingsList':
dataset_metadata[k] = store_value
elif k == 'softwareList':
method_metadata[k] = store_value
elif k == 'sampleList':
method_metadata[k] = store_value
else:
dataset_metadata[k] = store_value
dataset_metadata['imzml_xml_metadata_header'] = metadata_value(
name='imzml_xml_metadata_header',
value=metdata_header,
unit=None,
description='XML imzML header',
ontology=None)
except:
log_helper.warning(
__name__, "Extraction of additional imzML metadata failed")
return coordinates, np.asarray(
mz_axes
), dtype, file_type, dataset_metadata, instrument_metadata, method_metadata
def __compute_file_info(cls, filename, resolution):
## TODO completely refactor this to make it smartly handle profile or centroid datasets
## TODO: centroid datasets should take in a user parameter "Resolution" and resample data at that resolution
## TODO: profile datasets should work as is
## TODO: checks for profile data vs. centroid data on the variation in length of ['m/z array']
"""
Internal helper function used to compute the mz axis, data type for the intensities, format type
:return: Numpy array with mz axis
:return: string with data type
:return: imzml file type
:return:
"""
reader = ImzMLParser(filename)
# Read the first spectrum
mz_axes, intens = reader.getspectrum(0) # NOTE: mz_axes is a tuple
# Read the coordinates
coordinates = np.asarray(reader.coordinates)
# #Start the data at [0,0,0]
# coordinates[:,0] = coordinates[:,0] - np.amin(coordinates,axis=0)[0]
# coordinates[:,1] = coordinates[:,1] - np.amin(coordinates,axis=0)[1]
# coordinates[:,2] = coordinates[:,2] - np.amin(coordinates,axis=0)[2]
# Determine the data type for the internsity values
dtype = np.asarray(intens).dtype.str
# Compute the mz axis and file type
file_type = cls.available_imzml_types['continuous']
min_mz, max_mz = np.amin(mz_axes), np.amax(mz_axes)
for ind in range(coordinates.shape[0]): #for ind, loc in enumerate(reader.coordinates):
mz, intens = reader.getspectrum(ind)
if mz == mz_axes:
pass
else:
file_type = cls.available_imzml_types['processed']
if min_mz > np.amin(mz):
min_mz = np.amin(mz)
if max_mz < np.amax(mz):
max_mz = np.amax(mz)
# Reinterpolate the mz-axis if we have a processed mode imzml file
if file_type == cls.available_imzml_types['processed']:
f = np.ceil(1e6 * np.log(max_mz/min_mz)/resolution)
mz_axes = np.logspace(np.log10(min_mz), np.log10(max_mz), f)
log_helper.info(__name__, "Reinterpolated m/z axis for processed imzML file")
# Construct the imzml metadata information
dataset_metadata = metadata_dict()
instrument_metadata = metadata_dict()
method_metadata = metadata_dict()
for k, v in reader.imzmldict.iteritems():
dataset_metadata[k] = metadata_value(name=k,
value=v,
unit=None,
description=k,
ontology=None)
# Delete the parser and read the metadata
del reader
# Parse the metadata for the file. We try to parse only the header and ignore the
# <run > group in the XML file to avoid going throught the whole file again
# while extracting the majority of the relevant metadata
try:
with open(filename, 'r') as ins:
metdata_header = ''
for line in ins:
if '<run' in line:
break
else:
metdata_header += line
metdata_header += '</mzML>'
metdata_header_dict = xmltodict.parse(metdata_header)['mzML']
for k, v in metdata_header_dict.iteritems():
store_value = metadata_value(name=k,
value=v,
unit=None,
description=str(k) + " extracted from imzML XML header.",
ontology=None)
if k == 'instrumentConfigurationList':
instrument_metadata[k] = store_value
elif k == 'dataProcessingList':
method_metadata[k] = store_value
elif k == 'scanSettingsList':
dataset_metadata[k] = store_value
elif k == 'softwareList':
method_metadata[k] = store_value
elif k =='sampleList':
method_metadata[k] = store_value
else:
dataset_metadata[k] = store_value
dataset_metadata['imzml_xml_metadata_header'] = metadata_value(name='imzml_xml_metadata_header',
value=metdata_header,
unit=None,
description='XML imzML header',
ontology=None)
except:
log_helper.warning(__name__, "Extraction of additional imzML metadata failed")
return coordinates, np.asarray(mz_axes), dtype, file_type, dataset_metadata, instrument_metadata, method_metadata