def test_getKeys_exclusive(self):
# test getKeys with some keys excluded
expectedSpectrumKeys = set(['total ion current chromatogram', 'time array', '32-bit float', 'total ion current chromatogram', 'no compression', 'total ion current'])
expectedPrecursorKeys = set([])
msrun = pymzml.run.Reader(testFolder+'mzml_testFIle_withBinary.mzML')
actualSpectrumKeys, actualPrecursorKeys, spectrumList = mzmlFunctions.getKeys(msrun, excludeList = ['scan time', 'filter string', 'PY:0000000', 'precursors', 'id', 'profile mass spectrum','collision-induced dissociation', '64-bit float', 'defaultArrayLength', 'm/z array', 'charge state', 'None', 'ms level', 'intensity array', 'BinaryArrayOrder', 'encodedData', 'mz'])
self.assertSetEqual(expectedSpectrumKeys, actualSpectrumKeys)
self.assertSetEqual(expectedPrecursorKeys, actualPrecursorKeys)
def test_getKeys_default(self):
# test getKeys with default, so no excluded or included keys
expectedSpectrumKeys = set(['no compression', 'total ion current', 'scan time', 'filter string', 'id', 'profile mass spectrum',
'64-bit float', 'defaultArrayLength', 'm/z array', 'ms level', 'intensity array',
'BinaryArrayOrder', '32-bit float', 'total ion current chromatogram', 'time array'])
expectedPrecursorKeys = set([])
msrun = pymzml.run.Reader(testFolder+'mzml_testFIle_withBinary.mzML')
actualSpectrumKeys, actualPrecursorKeys, spectrumList = mzmlFunctions.getKeys(msrun)
self.assertSetEqual(expectedSpectrumKeys, actualSpectrumKeys)
self.assertSetEqual(expectedPrecursorKeys, actualPrecursorKeys)
def __init__(self, path, msrun):
# using r in front of doc string because otherwise \t isn't recognised
r"""
@type path: string
@param path: path for output file
@type msrun: pymzml.run.Reader
@param msrun: An instance of pymzml.run.Reader()
B{Example}:
Write an instance of pymzml.run.Reader to a csv file:
>>> msrun = pymzml.run.Reader('example_mzML_file.mzML') # instance of pymzml.run.Reader
>>> writer = MsrunCsvWriter('example_outfile.csv', msrun) # write the csv file
"""
# Use the FileHandler class to open the file and close if after writing is done
with FileWriter(path) as fw:
# a list of all the columns the user do not want in the ms/ms file from the configfile
excludeList = config.get(
'data', 'excludeMsrunCsvColumns').strip(' ').split(',')
# a list of all the columns the user want sin the ms/ms file from the configfile that are not in feature.keys()
includeList = config.get(
'data', 'includeMsrunCsvColumns').strip(' ').split(',')
# spectrumKeys will contain the column header names
spectrumKeys, precursorKeys, spectrumList = mzmlFunctions.getKeys(
msrun, excludeList, includeList)
# write the column names
fw.csvWriteLine(list(spectrumKeys))
# loop through the spectra that were used in mzmlFunctions.getKeys (spectrumList) and the ones left over in msrun
# itertools.izip makes an iterator of two lists
for spectrum in itertools.izip(spectrumList, msrun):
if spectrum[0]['id'] != 'TIC':
# list to contain the content for each row
rowContent = []
# only the keys specefied by spectrumKeys above
for key in spectrumKeys:
try:
if key in precursorKeys:
rowContent.append(
spectrum[0]['precursors'][0][key])
else:
rowContent.append(spectrum[0][key])
except KeyError:
rowContent.append('N/A')
fw.csvWriteLine(rowContent)
def __init__(self, path, msrun):
# using r in front of doc string because otherwise \t isn't recognised
r"""
@type path: string
@param path: path for output file
@type msrun: pymzml.run.Reader
@param msrun: An instance of pymzml.run.Reader()
B{Example}:
Write an instance of pymzml.run.Reader to a csv file:
>>> msrun = pymzml.run.Reader('example_mzML_file.mzML') # instance of pymzml.run.Reader
>>> writer = MsrunCsvWriter('example_outfile.csv', msrun) # write the csv file
"""
# Use the FileHandler class to open the file and close if after writing is done
with FileWriter(path) as fw:
# a list of all the columns the user do not want in the ms/ms file from the configfile
excludeList = config.get('data', 'excludeMsrunCsvColumns').strip(' ').split(',')
# a list of all the columns the user want sin the ms/ms file from the configfile that are not in feature.keys()
includeList = config.get('data','includeMsrunCsvColumns').strip(' ').split(',')
# spectrumKeys will contain the column header names
spectrumKeys, precursorKeys, spectrumList = mzmlFunctions.getKeys(msrun, excludeList, includeList)
# write the column names
fw.csvWriteLine(list(spectrumKeys))
# loop through the spectra that were used in mzmlFunctions.getKeys (spectrumList) and the ones left over in msrun
# itertools.izip makes an iterator of two lists
for spectrum in itertools.izip(spectrumList, msrun):
if spectrum[0]['id'] != 'TIC':
# list to contain the content for each row
rowContent = []
# only the keys specefied by spectrumKeys above
for key in spectrumKeys:
try:
if key in precursorKeys:
rowContent.append(spectrum[0]['precursors'][0][key])
else:
rowContent.append(spectrum[0][key])
except KeyError:
rowContent.append('N/A')
fw.csvWriteLine(rowContent)
def test_getKeys_default(self):
# test getKeys with default, so no excluded or included keys
expectedSpectrumKeys = set([
'no compression', 'total ion current', 'scan time',
'filter string', 'id', 'profile mass spectrum', '64-bit float',
'defaultArrayLength', 'm/z array', 'ms level', 'intensity array',
'BinaryArrayOrder', '32-bit float',
'total ion current chromatogram', 'time array'
])
expectedPrecursorKeys = set([])
msrun = pymzml.run.Reader(testFolder + 'mzml_testFIle_withBinary.mzML')
actualSpectrumKeys, actualPrecursorKeys, spectrumList = mzmlFunctions.getKeys(
msrun)
self.assertSetEqual(expectedSpectrumKeys, actualSpectrumKeys)
self.assertSetEqual(expectedPrecursorKeys, actualPrecursorKeys)
def test_getKeys_inclusive(self):
# test getKeys with some keys excluded and some keys includes
expectedSpectrumKeys = set([
'no compression', 'total ion current', 'time array',
'32-bit float', 'total ion current chromatogram'
])
expectedPrecursorKeys = set([])
msrun = pymzml.run.Reader(testFolder + 'mzml_testFIle_withBinary.mzML')
actualSpectrumKeys, actualPrecursorKeys, spectrumList = mzmlFunctions.getKeys(
msrun,
excludeList=[
'charge', 'scan time', 'filter string', 'PY:0000000',
'precursors', 'id', 'profile mass spectrum', 'charge',
'collision-induced dissociation', '64-bit float',
'defaultArrayLength', 'm/z array', 'charge state', 'None',
'ms level', 'intensity array', 'BinaryArrayOrder',
'encodedData', 'charge'
])
self.assertSetEqual(expectedSpectrumKeys, actualSpectrumKeys)
self.assertSetEqual(expectedPrecursorKeys, actualPrecursorKeys)
