def getUniquePeptDict(scanDict, scoreKey, peptideKey, scanKey = 'ScanF', nullVal = 'None', noStrip=['#'], datasets=None):
scanFDict = defaultdict(lambda: dict([(dataset, []) for dataset in datasets]))
uniquePeptDict = {}
if datasets == None:
datasets = scanDict.keys()
for dataset in datasets:
for item in scanDict[dataset]:
if item[peptideKey] == nullVal:
continue
strippedPept = An.stripModifications(item[peptideKey], noRemove=noStrip)
if strippedPept in uniquePeptDict and float(item[scoreKey]) > float(uniquePeptDict[strippedPept][scoreKey]):
uniquePeptDict[strippedPept] = item
elif strippedPept not in uniquePeptDict:
uniquePeptDict[strippedPept] = item
scanFDict[strippedPept][dataset] += [item[scanKey]]
return uniquePeptDict, scanFDict
with open(options.unimoddict) as fin:
unimodDict = pickle.load(fin)
hashedUnimodDict = hashUnimodDict(unimodDict)
outFile = open(options.output, 'w')
cols = ['ScanF', 'Score', 'Peptide', 'Unmod Peptide', 'References', 'Modifications', 'DB Peptide', 'Alignment Score']
if 'Ambig Edges' in infoDict:
cols.insert(2, 'Ambig Edges')
outFile.write('\t'.join([col for col in cols]) + '\n')
for entry in DataFile.getScanInfo(options.comp, delimiter='\t'):
scanData = {}
scanData['ScanF'] = entry[infoDict['ScanF']]
scanData['Peptide'] = entry[infoDict['Peptide']]
scanData['Unmod Peptide'] = An.stripModifications(scanData['Peptide'], noRemove=[])
scanData['Score'] = entry[infoDict['Score']]
scanData['Alignment Score'] = None
if 'Ambig Edges' in infoDict:
ambigEdges = eval(entry[infoDict['Ambig Edges']])
scanData['Ambig Edges'] = ambigEdges
else:
ambigEdges = []
deNovoPRMLadder = An.getPRMLadder(scanData['Peptide'], ambigEdges=ambigEdges)
refList = eval(entry[infoDict['References']])
subjSequence = getSequence(options.fasta, refList[0][0])[refList[0][1]-1:refList[0][2]]
if scanData['Unmod Peptide'] == subjSequence:
scanData['Modifications'] = []
pairConfig = paramsDict['Pair Configurations'][pairConfigName]
delta = pairConfig['NMod'] + pairConfig['CMod']
deltaPairs = An.findDeltaPairsClusters(precMassClusters, scanFDict, delta, ppm=options.ppmstd)
pairsOut = open(options.output + '_' + pairConfigName + '.txt', 'w')
for pair in deltaPairs:
epSTD = options.ppmstd * 10 ** -6 * scanFDict[precMassClusters[pair[0]][0]]['precMass']
# Get all possible true pairings from database search results
uniquePeptideDict = defaultdict(lambda: {'light': [], 'heavy': []})
for scanF in precMassClusters[pair[0]]:
if scanF in processedInfo[progName]:
uniquePeptideDict[An.stripModifications(processedInfo[progName][scanF][infoMap[progDict[progName]]['Peptide']], noRemove=['#'])]['light'] += [scanF]
for scanF in precMassClusters[pair[1]]:
if scanF in processedInfo[progName]:
uniquePeptideDict[An.stripModifications(processedInfo[progName][scanF][infoMap[progDict[progName]]['Peptide']], noRemove=['#'])]['heavy'] += [scanF]
mergedSpecDictLight = {}
mergedSpecDictHeavy = {}
for peptide in uniquePeptideDict:
if len(uniquePeptideDict[peptide]['light']) > 0:
mergedSpecDictLight[peptide] = SA.mergeSpectra([DataFile.getMassIntPairs(scanFDict[lightScanF]['dta']) for lightScanF in uniquePeptideDict[peptide]['light']], epsilon = 2*epSTD)
if len(uniquePeptideDict[peptide]['heavy']) > 0:
mergedSpecDictHeavy[peptide] = SA.mergeSpectra([DataFile.getMassIntPairs(scanFDict[heavyScanF]['dta']) for heavyScanF in uniquePeptideDict[peptide]['heavy']], epsilon = 2*epSTD)
for lightPept in mergedSpecDictLight:
unimodDict = pickle.load(fin)
hashedUnimodDict = hashUnimodDict(unimodDict)
outFile = open(options.output, 'w')
cols = ['ScanF', 'Score', 'Peptide', 'Unmod Peptide', 'References', 'Modifications', 'DB Peptide', 'Alignment Score']
if 'Ambig Edges' in infoDict:
cols.insert(2, 'Ambig Edges')
outFile.write('\t'.join([col for col in cols]) + '\n')
for entry in DataFile.getScanInfo(options.comp, delimiter='\t'):
scanData = {}
print "New scan", entry
scanData['ScanF'] = entry[infoDict['ScanF']]
scanData['Peptide'] = entry[infoDict['Peptide']]
scanData['Unmod Peptide'] = An.stripModifications(scanData['Peptide'])
scanData['Score'] = entry[infoDict['Score']]
scanData['Alignment Score'] = None
if 'Ambig Edges' in infoDict:
ambigEdges = eval(entry[infoDict['Ambig Edges']])
scanData['Ambig Edges'] = ambigEdges
else:
ambigEdges = []
massIntPairs = DataFile.getMassIntPairs(scanFDict[int(scanData['ScanF'])]['dta'])
spec = PN.Spectrum(PNet, precMass, epsilon=2*epSTD, spectrum=massIntPairs)
try:
#Ignore de novo peptides with noncanonical amino acids for now
epsilon = 2 * 10**-6 * options.ppmstd * An.getPRMLadder(scanData['Peptide'], ambigEdges=ambigEdges)[-1]
except KeyError:
