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 getScanScoreDictSVM(LADSSeqInfo, seqEntry, scanFDict, svmModel, svmRange, pairConfig, PNet, desired_feats=None):
scanScoreDict = {}
spectrumAndPSMSpecificFeatureDict = getSpectrumAndPSMFeatureDict(LADSSeqInfo, seqEntry, scanFDict, pairConfig, PNet)
# Now get PSM with highest rank score for each scan
fullPSMList = LADSSeqInfo[seqEntry]
for scan in lightScans + heavyScans:
xVals = []
for PSM in fullPSMList:
featureList = spectrumAndPSMSpecificFeatureDict[(scan, PSM[:2])]
if desired_feats != None:
xVals += [dict((i+1, featureList[desired_feats[i] - 1]) for i in range(len(desired_feats)))]
else:
xVals += [dict((i+1, featureList[i]) for i in range(len(featureList)))]
xValsNorm = svmutil.normalize_instances(xVals, svmRange)
probs = zip(*svmutil.svm_predict([0] * len(xValsNorm), xValsNorm, svmModel, '-b 1')[2])[0]
#probs = zip(*svmutil.svm_predict([0] * len(xValsNorm), xValsNorm, svmModel, '-b 1')[2])[1]
highestProbInd = np.argmax(probs)
scanScoreDict[scan] = {'Seq': (fullPSMList[highestProbInd][1], fullPSMList[highestProbInd][2]), 'Raw Score': fullPSMList[highestProbInd][0], 'Post Score': probs[highestProbInd]}
return scanScoreDict
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']
# hyperParameters = PNet.getHyperParameters(pairConfigName)
# ambigPenaltyFun = DNS.getAmbigEdgePenaltyFunction(hyperParameters['minedge'], hyperParameters['ambigopen'], hyperParameters['ambigextend'])
# ppmPenaltyFun = DNS.getPPMPenaltyFun(hyperParameters['ppmstd'], hashedAAs, hyperParameters['minedge'], hyperParameters['ppmpen'], 0, epStep)
getSequencingThread(pairs, xVals, paramsDict, outFile, cols, pLab)
# for i, pair in enumerate(pairs):
# if pLab[i] == -1:
# continue
)
possPairs = [
(lightScanF, heavyScanF)
for lightScanF in samePeptideClusters[pair[0]]
for heavyScanF in samePeptideClusters[pair[1]]
]
# possPairsList += [set(possPairs)]
y += [1 if any([pair in progPairs[pairConfigName] for pair in possPairs]) else -1]
# x += [{1: totalSharedPeaksRatio, 2: singleSymSharedPeaksRatio, 3: scanFDict[pair[0]]['precMass']}]
x += [SVMClassificationInfo]
# pairs[pairConfigName][pair] = getSharedPeaksRatio(lightSpec, heavySpec, pairConfig, epsilon)
# print pair, pairs[pairConfigName][pair]
x = svmutil.normalize_instances(x, svmRange)
pLab = svmutil.svm_predict(y, x, svmModel)[0]
pairs[pairConfigName] = {"test labels": pLab, "true labels": y, "pairs": testedDeltaPairs}
times[pairConfigName] = time.time() - startTime
# for i, pair in enumerate(testedPairs):
# print pairs['same']['test labels'][i], pairs['same']['true labels'][i], pairs['same']['tested pairs'][i]
# print processedInfo[progName][pairs['same']['tested pairs'][i][0]]['Peptide'], processedInfo[progName][pairs['same']['tested pairs'][i][1]]['Peptide']
for pairConfigName in paramsDict["Pair Configurations"]:
truePairedScanFs = set()
for pair in progPairs[pairConfigName]:
truePairedScanFs.add(pair[0])
truePairedScanFs.add(pair[1])
# print 'number of true paired scanFs', len(truePairedScanFs)