def getPairedAndUnpairedSpectra(dtaDir, dtaList, Nmod, Cmod, ppm=5, cutOff=0.1, verbose=False):
specPairs = []
unpairedSpecs = []
delta = Nmod + Cmod
for i in range(len(dtaList)):
paired = False
precMass1 = DataFile.getPrecMassAndCharge(dtaList[i])[0]
spec1 = DataFile.getMassIntPairs(dtaList[i])
for j in range(i + 1, len(dtaList)):
precMass2 = DataFile.getPrecMassAndCharge(dtaList[j])[0]
epsilon = ppm * 10 ** -6 * max(precMass1, precMass2)
if np.abs(np.abs(precMass1 - precMass2) - delta) < epsilon:
spec2 = DataFile.getMassIntPairs(dtaList[j])
if precMass1 < precMass2:
N, C = SA.getNandCIons(spec1, spec2, Nmod, Cmod, epsilon=epsilon)
ratio = SA.getSharedPeaksRatio(spec1, spec2, N, C)
else:
N, C = SA.getNandCIons(spec2, spec1, Nmod, Cmod, epsilon=epsilon)
ratio = SA.getSharedPeaksRatio(spec2, spec1, N, C)
if ratio > cutOff:
if verbose:
print 'Pair found', dtaList[i], dtaList[j]
paired = True
specs = (dtaList[i], dtaList[j])
lightInd = int(precMass2 < precMass1)
specPairs.extend([(ratio, specs[lightInd], specs[1 - lightInd])])
if not paired:
unpairedSpecs.extend([dtaList[i]])
if verbose:
print 'No pairs for', dtaList[i]
return specPairs, unpairedSpecs
def getClusterPairingStats(lightSpecs, heavySpecs, lightPrecMass, pairConfig, epSTD = 0.01):
lightMergedSpec = SA.mergeSpectra(lightSpecs, epsilon=2*epSTD)
heavyMergedSpec = SA.mergeSpectra(heavySpecs, epsilon=2*epSTD)
allPairedIonsDict = getAllPairedIonsDict(lightMergedSpec, heavyMergedSpec, lightPrecMass, pairConfig, epSTD)
specPairedPRMs = {}
pairTypeCount = {}
for pairType in pairTypes:
specPairedPRMs[pairType] = []
pairTypeCount[pairType] = 0
numLightInds = 0
numHeavyInds = 0
for heavyIons in allPairedIonsDict:
deltaMasses = []
pairType = {'light': [], 'heavy': []}
for ion in allPairedIonsDict[heavyIons]:
pairType['light'] += [ion[1]]
deltaMasses += [PN.ProbNetwork.deltaRules[ion[1]](lightPrecMass-Constants.mods['H+']-Constants.mods['H2O'], lightMergedSpec[ion[0]][0], 0, 0)]
for ion in heavyIons:
pairType['heavy'] += [ion[1]]
deltaMasses += [PN.ProbNetwork.deltaRules[ion[1]](lightPrecMass-Constants.mods['H+']-Constants.mods['H2O'], heavyMergedSpec[ion[0]][0], pairConfig['NMod'], pairConfig['CMod'])]
pairTypeString = ''.join(pairType['light']) + '_' + ''.join(pairType['heavy'])
specPairedPRMs[pairTypeString] += [(sum(deltaMasses)/len(deltaMasses), (allPairedIonsDict[heavyIons], heavyIons))]
pairTypeCount[pairTypeString] += 1
numLightInds += len(allPairedIonsDict[heavyIons])
numHeavyInds += len(heavyIons)
sharedPeaksRatio = float(numLightInds + numHeavyInds)/(lightMergedSpec.shape[0] + heavyMergedSpec.shape[0])
return {'Cluster Paired PRM Information': specPairedPRMs, 'Shared Peaks Ratio': sharedPeaksRatio, 'Pair Type Stats': pairTypeCount, 'Light Merged Spec': lightMergedSpec, 'Heavy Merged Spec': heavyMergedSpec, 'Num Paired Ions': numLightInds + numHeavyInds}
def getAllPairedIonsDict(lightMergedSpec, heavyMergedSpec, lightPrecMass, pairConfig, epSTD=0.01):
NTermTable, CTermTable = SA.getNandCIons(lightMergedSpec, heavyMergedSpec, Nmod=pairConfig['NMod'], Cmod=pairConfig['CMod'], epsilon=2*epSTD)
NCrossTable, CCrossTable = SA.getCrossPairedIons(lightMergedSpec, heavyMergedSpec, lightPrecMass, Nmod=pairConfig['NMod'], Cmod=pairConfig['CMod'], epsilon=2*epSTD)
NTermIonDict = SA.prepIonTableForAddition(NTermTable, ['b', 'b'])
CTermIonDict = SA.prepIonTableForAddition(CTermTable, ['y', 'y'])
NCrossIonDict = SA.prepIonTableForAddition(NCrossTable, ['y', 'b'])
CCrossIonDict = SA.prepIonTableForAddition(CCrossTable, ['b', 'y'])
return SA.addDicts(SA.reverseDict(SA.addDicts(NTermIonDict, CCrossIonDict)), SA.reverseDict(SA.addDicts(NCrossIonDict, CTermIonDict)))
def getPairs(pairs, xVals):
for pair in pairs:
lightSpecs = [DataFile.getMassIntPairs(scanFDict[lightScanF]['dta']) for lightScanF in samePeptideClusters[pair[0]]]
heavySpecs = [DataFile.getMassIntPairs(scanFDict[heavyScanF]['dta']) for heavyScanF in samePeptideClusters[pair[1]]]
lightPrecMass = np.average(np.array([scanFDict[lightScanF]['precMass'] for lightScanF in samePeptideClusters[pair[0]]]))
epSTD = (float(paramsDict['ppmstd']['value'])) * 10 ** -6 * lightPrecMass
lightMergedSpec = SA.mergeSpectra(lightSpecs, epsilon=2*epSTD)
heavyMergedSpec = SA.mergeSpectra(heavySpecs, epsilon=2*epSTD)
svmClassificationData = SA.getSpectraPairInfoForSVMClassification(lightMergedSpec, heavyMergedSpec, lightPrecMass, NMod=pairConfig['NMod'], CMod=pairConfig['CMod'], epsilon=2*epSTD)
xVals.put([svmClassificationData])
return xVals
def getAlignmentRatios(scanInfoFName, dtaDir, delta, epsilon=0.02):
scanInfo = DataFile.getScanInfo(scanInfoFName)
dtaNames = DataFile.getDTAFNamesInDir(dtaDir)
scansToUse = scanInfo
"""
for i in range(len(scanInfo) - 1):
if (int(scanInfo[i][0]) + 1 == int(scanInfo[i+1][0])):
if (scanInfo[i][1] == scanInfo[i+1][1]):
scansToUse += [scanInfo[i]]
else:
scansToUse += [scanInfo[i]]
"""
ratios = []
goodRatios = []
for i in range(len(scansToUse)):
for j in range(i + 1, len(scansToUse)):
if j == i + 1:
print '%s percent done' % str(float(i) / len(scansToUse))
if np.abs(np.abs(float(scansToUse[i][1]) - float(scansToUse[j][1])) - delta) < epsilon:
dta1 = '244.%(scanF)04i.%(scanF)04i.1.dta' % {'scanF': int(scansToUse[i][0])}
dta2 = '244.%(scanF)04i.%(scanF)04i.1.dta' % {'scanF': int(scansToUse[j][0])}
spec1 = DataFile.getMassIntPairs(dtaDir + dta1)
spec2 = DataFile.getMassIntPairs(dtaDir + dta2)
ratio = SA.getSharedPeaksRatio(float(scansToUse[i][1]), spec1, float(scansToUse[j][1]), spec2, epsilon)
print ratio, scansToUse[i], scansToUse[j]
ratios.extend([(ratio, scansToUse[i], scansToUse[j])])
with open('heavylightpairs.txt', 'w') as fout:
pickle.dump(ratios, fout)
return ratios
def getSamePeptideClusters(precMassClusters, scanFDict, svmModel, svmRange, ppmSTD=5, cutOff=0):
trueClusters = []
for cluster in precMassClusters:
if len(cluster) == 1:
trueClusters += [cluster]
else:
# print 'testing cluster', cluster
pairIndex = []
xVals = []
specs = []
for i in range(len(cluster)):
specs += [DataFile.getMassIntPairs(scanFDict[cluster[i]]['dta'])]
dMatrix = np.ones((len(cluster), len(cluster))) * -2
for i in range(len(cluster)):
for j in range(i+1, len(cluster)):
epSTD = ppmSTD * 10 ** -6 * scanFDict[cluster[i]]['precMass']
SVMClassificationInfo = SA.getSpectraPairInfoForSVMClassification(specs[i], specs[j], scanFDict[cluster[i]]['precMass'], NMod=0, CMod=0, epsilon=2*epSTD)
xVals += [SVMClassificationInfo]
pairIndex += [(i, j)]
xValsNorm = svmutil.normalize_instances(xVals, svmRange)
pLabs = svmutil.svm_predict([0]*len(xValsNorm), xValsNorm, svmModel)[0]
# print pLabs
for i, pLab in enumerate(pLabs):
# Scale distances by 4: totalTICRatio, 1: TotalSharedPeaksRatio
dMatrix[pairIndex[i][0]][pairIndex[i][1]] = dMatrix[pairIndex[i][1]][pairIndex[i][0]] = xVals[i][1] if pLab==1 else -1
trueClusters += heirarchicalClusteringAverageLinkage([[scanF] for scanF in cluster], dMatrix, cutOff=cutOff)
return trueClusters
def getSharedPRMs(prmLadder1, prmLadder2, epsilon=0.5):
hashTable = {}
for i in range(prmLadder1.size):
key = np.round(prmLadder1[i] / epsilon)
hashTable[key] = [(i, prmLadder1[i])]
temp = np.zeros((prmLadder2.size, 2))
temp[:, 0] = prmLadder2
pairedIonData = SA.getPairedIons(hashTable, temp, delta=0.0, epsilon=epsilon)
sharedPRMs = []
for key in sorted(pairedIonData.keys()):
sharedPRMs += [zip(*pairedIonData[key])[1]]
if sharedPRMs:
return zip(*sharedPRMs)[0]
else:
return []
def getSharedPeaksRatio(lightPath, heavyPath, epsilon):
lightPairs = DataFile.getMassIntPairs(lightPath)
heavyPairs = DataFile.getMassIntPairs(heavyPath)
N, C = SA.getNandCIons(lightPairs, heavyPairs, pairConfig['NMod'], pairConfig['CMod'], epsilon=epsilon)
return SA.getSharedPeaksRatio(lightPairs, heavyPairs, N, C)
addEnds = DNS.getSpectrumGraphEndpointInitFunction(pairConfig['NStatic'], pairConfig['CStatic'], paramsDict['Enzyme']['specificity'])
termModHash = Constants.getTermModHashForPairConfig(pairConfig)
svmModel = svmutil.svm_load_model(parent + pairConfig['Model'])
svmRange = svmutil.load_ranges(parent + os.path.splitext(pairConfig['Model'])[0] + '.range')
xVals = []
# xVals = getPairsThread(pairs)
for pair in pairs:
lightSpecs = [DataFile.getMassIntPairs(scanFDict[lightScanF]['dta']) for lightScanF in samePeptideClusters[pair[0]]]
heavySpecs = [DataFile.getMassIntPairs(scanFDict[heavyScanF]['dta']) for heavyScanF in samePeptideClusters[pair[1]]]
lightPrecMass = np.average(np.array([scanFDict[lightScanF]['precMass'] for lightScanF in samePeptideClusters[pair[0]]]))
epSTD = options.ppmstd * 10 ** -6 * lightPrecMass
lightMergedSpec = SA.mergeSpectra(lightSpecs, epsilon=2*epSTD)
heavyMergedSpec = SA.mergeSpectra(heavySpecs, epsilon=2*epSTD)
svmClassificationData = SA.getSpectraPairInfoForSVMClassification(lightMergedSpec, heavyMergedSpec, lightPrecMass, NMod=pairConfig['NMod'], CMod=pairConfig['CMod'], epsilon=2*epSTD)
xVals += [svmClassificationData]
xValsNorm = svmutil.normalize_instances(xVals, svmRange)
pLab = svmutil.svm_predict([0]*len(xValsNorm), xValsNorm, svmModel)[0]
print 'Pairs found. Time taken:', time.time() - t1, '\n'
heavySeqMap = copy.deepcopy(seqMap['LADS Unit Test'])
heavySeqMap['Mods']['N-Term'] = paramsDict['Pair Configurations'][pairConfigName]['NModSymbol']
heavySeqMap['Mods']['C-Term'] = paramsDict['Pair Configurations'][pairConfigName]['CModSymbol']
def getSharedPeaksRatio(lightPath, heavyPath, epsilon):
lightPairs = DataFile.getMassIntPairs(lightPath)
heavyPairs = DataFile.getMassIntPairs(heavyPath)
N, C = SA.getNandCIons(lightPairs, heavyPairs, 17.0265, -16.0187, epsilon=epsilon)
return SA.getSharedPeaksRatio(lightPairs, heavyPairs, N, C)
def getSharedPeaksRatio(lightPairs, heavyPairs, pairConfig, epsilon):
N, C = SA.getNandCIons(lightPairs, heavyPairs, pairConfig['NMod'], pairConfig['CMod'], epsilon=epsilon)
return SA.getSharedPeaksRatio(lightPairs, heavyPairs, N, C)
for cluster in precMassClusters:
if len(cluster) == 1:
continue
specs = []
for scanF in cluster:
specs += [DataFile.getMassIntPairs(scanFDict[scanF]['dta'])]
for i in range(len(cluster)):
for j in range(i+1, len(cluster)):
if cluster[i] in processedInfo[progName] and cluster[j] in processedInfo[progName]:
epSTD = options.ppmstd * 10 ** -6 * scanFDict[cluster[i]]['precMass']
SVMClassificationInfo = SA.getSpectraPairInfoForSVMClassification(specs[i], specs[j], scanFDict[cluster[i]]['precMass'], NMod=0, CMod=0, epsilon=2*epSTD)
seq1 = processedInfo[progName][cluster[i]][infoMap[progDict[progName]]['Peptide']]
seq2 = processedInfo[progName][cluster[j]][infoMap[progDict[progName]]['Peptide']]
xVal = 1 if seq1 == seq2 else -1
clusterOut.write(' '.join([str(xVal)] + ['%i:%f' % (key, SVMClassificationInfo[key]) for key in sorted(SVMClassificationInfo)]) + ' # Scans %s, %i - %s, %i\n' % (processedInfo[progName][cluster[i]][infoMap[progDict[progName]]['Peptide']], cluster[i], processedInfo[progName][cluster[j]][infoMap[progDict[progName]]['Peptide']], cluster[j]))
clusterOut.close()
for pairConfigName in paramsDict['Pair Configurations']:
pairConfig = paramsDict['Pair Configurations'][pairConfigName]
delta = pairConfig['NMod'] + pairConfig['CMod']
deltaPairs = An.findDeltaPairsClusters(precMassClusters, scanFDict, delta, ppm=options.ppmstd)
lightSpecs = [
DataFile.getMassIntPairs(scanFDict[lightScanF]["dta"]) for lightScanF in samePeptideClusters[pair[0]]
]
heavySpecs = [
DataFile.getMassIntPairs(scanFDict[heavyScanF]["dta"]) for heavyScanF in samePeptideClusters[pair[1]]
]
lightPrecMass = np.average(
np.array([scanFDict[lightScanF]["precMass"] for lightScanF in samePeptideClusters[pair[0]]])
)
# heavyPrecMass = np.average(np.array([scanFDict[lightScanF]['precMass'] for lightScanF in samePeptideClusters[pair[1]]]))
# print lightPrecMass, heavyPrecMass
# print samePeptideClusters[pair[0]], samePeptideClusters[pair[1]]
epSTD = options.ppmstd * 10 ** -6 * lightPrecMass
lightMergedSpec = SA.mergeSpectra(lightSpecs, epsilon=2 * epSTD)
heavyMergedSpec = SA.mergeSpectra(heavySpecs, epsilon=2 * epSTD)
"""
NTermTable, CTermTable = SA.getNandCIons(lightMergedSpec, heavyMergedSpec, Nmod=pairConfig['NMod'], Cmod=pairConfig['CMod'], epsilon=2*epSTD)
NCrossTable, CCrossTable = SA.getCrossPairedIons(lightMergedSpec, heavyMergedSpec, lightPrecMass, Nmod=pairConfig['NMod'], Cmod=pairConfig['CMod'], epsilon=2*epSTD)
NTermIonDict = prepIonTableForAddition(NTermTable, ['b', 'b'])
CTermIonDict = prepIonTableForAddition(CTermTable, ['y', 'y'])
NCrossIonDict = prepIonTableForAddition(NCrossTable, ['y', 'b'])
CCrossIonDict = prepIonTableForAddition(CCrossTable, ['b', 'y'])
allPairedIonsDict = addDicts(reverseDict(addDicts(NTermIonDict, CCrossIonDict)), reverseDict(addDicts(NCrossIonDict, CTermIonDict)))
symLightInds = set()
symHeavyInds = set()
totalLightInds = set()