def __init__(self, path):
"""
Initialize the Reader instance and check if the file is a valid peaks.mzML file and put it in a fileHandling.FileHandle instance.
@type path: string
@param path: The path of the feature XML file
"""
# filepath
self.path = path
# if the file at path does not start with <?xml, raise an exception that the xml file is invalid
file = fileHandling.FileHandle(self.path)
file.isXML()
file.isMzML()
# the current element
self.element = None
# current userParam
# a list of all the keys that can be used for __getItem__
self.__spectraKeySet = []
# element dictionary to contain all the elements
# uses collections.defaultidct to enable unknown keys to be added to the dictionary
self.spectraInfo = collections.defaultdict(dict)
self.simpleFlag = True
def __init__(self, path):
"""
Initialize the Reader instance and check if the file is a valid featureXML file and put it in a fileHandling.FileHandle instance.
@type path: string
@param path: The path of the feature XML file
"""
# filepath
self.path = path
# if the file at path does not start with <?xml, raise an exception that the xml file is invalid
file = fileHandling.FileHandle(self.path)
file.isXML()
# if the second line of the file does not start with <featureMap, raise an exception that the file is not a featureXML file
file.isFeatureXML()
# a flag to see if simpleFeatureInfo or allFeatureInfo is used. This makes a difference in the __getItem__ function
self.simpleFlag = True
# the current element
self.element = None
# a list of all the keys that can be used for __getItem__
self.__elementKeySet = set([])
# element dictionary to contain all the elements
# uses collections.defaultidct to enable unknown keys to be added to the dictionary
self.elementInfo = collections.defaultdict(dict)
# add the keys to _elementKeySet that __getitem__ takes
self.__elementKeySet.add('intensity')
self.__elementKeySet.add('overallquality')
self.__elementKeySet.add('userParam')
self.__elementKeySet.add('convexhull')
self.__elementKeySet.add('mz')
self.__elementKeySet.add('retention time')
self.__elementKeySet.add('quality')
self.__elementKeySet.add('charge')
self.__elementKeySet.add('content')
self.__elementKeySet.add('id')
return
def test_isMascot(self):
validMascot = testFolder + 'test_mascot.xml'
fileHandler = fileHandling.FileHandle(validMascot)
fileHandler.isMascot()
def test_isMascotException(self):
invalidMascot = testFolder + 'featurexmlTestFile_1.featureXML'
fileHandler = fileHandling.FileHandle(invalidMascot)
self.assertRaises(IOError, fileHandler.isMascot)
def test_isFeatureXML_invalidException(self):
invalidFeatureXML = testFolder + 'invalidFeatureXML_noheader.featureXML'
fileHandler = fileHandling.FileHandle(invalidFeatureXML)
# test if isFeatureXML gives the right error (IOError) when called with an invalid XML file
self.assertRaises(IOError, fileHandler.isFeatureXML)
def test_isMzML(self):
validMzML = testFolder + 'mzml_test_file_1.mzML'
fileHandler = fileHandling.FileHandle(validMzML)
fileHandler.isMzML()
self.assertEqual(fileHandler.isMzML(), None)
def test_isFeatureXML(self):
validFeatureXML = testFolder + 'featurexmlTestFile_1.featureXML'
# if no error is given test passes
fileHandler = fileHandling.FileHandle(validFeatureXML)
self.assertEqual(fileHandler.isFeatureXML(), None)
def test_isXML_invalidException(self):
invalidXmlFile = testFolder + '/invalidXML.XML'
fileHandler = fileHandling.FileHandle(invalidXmlFile)
# test if isXML gives the right error (IOError) when called with an invalid XML file
self.assertRaises(IOError, fileHandler.isXML)
def test_isXML(self):
validXmlFile = testFolder + 'validXML.XML'
fileHandler = fileHandling.FileHandle(validXmlFile)
# if no error is given test passes
self.assertEqual(fileHandler.isXML(), None)
def test_getFile(self):
fileHandle = fileHandling.FileHandle(testFolder +
'featurexmlTestFile_1.featureXML')
self.assertEqual(fileHandle.getFile(),
testFolder + 'featurexmlTestFile_1.featureXML')
def compareCoordinate(mzmlFile,
featureFile,
writeCSV=False,
writeTo='precursorPerFeature.csv'):
r"""
Compare the precursors scan time and m/z values of a spectrum with all the retention time and m/z values in the convexhull of a feature. The spectrum information can come from
a mzml File or a peaks.mzml file. It returns a dictionary with 3 keys: totalPrecursorsInFeatures, averagePrecursorsInFeatures and featPerPrecursorDict. totalPrecursorsInFeatures
is a numeric value: the total amount of precursors that are in all features, averagePrecursorsInFeatures is a numeric value: the average amount of precursors in a feature and
totalPrecursorsInFeatures is a dictionary with as key every feature and as value the amount of precursors per feature.
A third input is writeCSV. If this is set to true, totalPrecursorsInFeatures is written out to a CSV file with a column featureID and a column # of precursors.
@type mzmlFile: string
@param mzmlFile: The path of the .mzML file
@type featureFile: string
@param featureFile: The path of the .featureXML file
@type writeCSV: bool
@param writeCSV: Flag if a CSV file has to be written out of the precursor per feature data (default: false)
@type writeTo: string
@param writeTo: The file and path where writeCSV has to be written to, default is precursorPerFeature.csv in the same folder as the script
@rtype: Dictionary
@returns: A dictionary with 3 keys: totalPrecursorsInFeatures, averagePrecursorsInFeatures and featPerPrecursorDict. totalPrecursorsInFeatures
is a numeric value: the total amount of precursors that are in all features, averagePrecursorsInFeatures is a numeric value: the average amount of precursors in a feature and
totalPrecursorsInFeatures is a dictionary with as key every feature and as value the amount of precursors per feature
B{Examples}:
Print the return value:
>>> print compareCoordinate('example_mzML_file.mzML', 'example_feature_file.featureXML')
{'totalPrecursorsInFeatures': 2, 'featPerPrecursorDict': {'f_43922326584371237334': 1, 'f_8613715360396561740': 0, 'f_13020522388175237334': 1}, 'averagePrecursorsInFeatures': 0.66666666666666663}
Write the results to a csv file:
>>> compareCoordinate(testFolder+'mzmlTestFile.mzML', testFolder+'featurexmlTestFile.featureXML', True, testFolder+'testPrecursorPerFeature.csv') # note the True
"""
fileHandle = fileHandling.FileHandle(os.path.abspath(mzmlFile))
# getting the absolute path of the given mzml file
mzmlFile = os.path.abspath(mzmlFile)
# parsing of mzml file
msrun = pymzml.run.Reader(mzmlFile)
# get the retention times and m/z of all precursors in msrun
retentionTime = mzmlFunctions.getPrecursorRtMz(msrun)
featureFile = os.path.abspath(featureFile)
# make an instance of the parseFeatureXML.Reader object, with file as input
featureXML = parseFeatureXML.Reader(featureFile)
# featPrecursor will hold the amount of precursors per feature, with id as key and amount of precursors as feature
featPrecursor = {}
totalPrecursor = 0
countZero = 0
x = 0
# get all features out of featureXML
for feature in featureXML.getSimpleFeatureInfo():
# set the amount of precursor per feature to 0 at every feature
precursorPerFeature = 0
# get the coordinates of all features
featureCoordinates = featureFunctions.getFeatureConvexhullCoordinates(
feature)
# loop for every feature coordinate through every MS/MS precursor coordinate
for mzAndRT in retentionTime:
# if the retention time (*60 to go from minutes to seconds) is larger than xMin and smaller than xMax and the m/z is
# larger than xMin and smaller than xMax, count the precursors
if float(mzAndRT['rt']) * 60 > float(featureCoordinates[feature]['rtMin']) and float(mzAndRT['rt'] * 60) < float(featureCoordinates[feature]['rtMax']) \
and float(mzAndRT['mz']) > float(featureCoordinates[feature]['mzMin']) and float(mzAndRT['mz']) < float(featureCoordinates[feature]['mzMax']):
precursorPerFeature += 1
totalPrecursor += 1
if precursorPerFeature == 0:
countZero += 1
featPrecursor[featureXML['id']] = precursorPerFeature
x += 1
# if writeCSV flag is set to True, write out csv file to the absolute path of writeTo (default: precursorPerFeature.csv in the same folder)
if writeCSV:
compareDataWriter = output.CompareDataWriter(os.path.abspath(writeTo))
compareDataWriter.precursorPerFeatureCsvWriter(featPrecursor)
# calculate the average precursor per feature
averagePrecursFeature = float(totalPrecursor) / float(len(featPrecursor))
return {
'totalPrecursorsInFeatures': totalPrecursor,
'averagePrecursorsInFeatures': averagePrecursFeature,
'featPerPrecursorDict': featPrecursor
}
