def sequenceDTAs(self):
curPairedScanData = self._indexedPairData[int(self._pairedScanListbox.curselection()[0])]
t1 = time.time()
if curPairedScanData['heavy'] != 'N/A':
heavySeqMap = copy.deepcopy(self._seqMap)
heavySeqMap['Mods']['N-Term'] = self._paramsDict['Pair Configurations'][curPairedScanData['pair configuration']]['NModSymbol']
heavySeqMap['Mods']['C-Term'] = self._paramsDict['Pair Configurations'][curPairedScanData['pair configuration']]['CModSymbol']
sharedInfo, starts, ends, deltas, termModHash, specs, G = DNS.initializeSpectrumGraph(self._pnet, self._paramsDict, self._scanFDict[curPairedScanData['light']]['dta'], heavyPath=self._scanFDict[curPairedScanData['heavy']]['dta'], ppm=self._ppm, usePaired=True, pairConfigName=curPairedScanData['pair configuration'], verbose=False)
precMass = sharedInfo['lightPrecMass']
else:
sharedInfo, starts, ends, deltas, termModHash, specs, G = DNS.initializeSpectrumGraph(self._pnet, self._paramsDict, self._scanFDict[curPairedScanData['light']]['dta'], ppm=self._ppm, verbose=False)
precMass = sharedInfo['precMass']
epsilon = self._ppm * precMass * 10 ** -6
paths, subG = DNS.getSpectrumGraphPaths(G, deltas, specs, starts, ends, precMass - Constants.mods['H+'] - Constants.mods['H2O'], termModHash=termModHash, unknownPenalty=self._ambigpenalty, maxEdge=self._maxedge, minEdge=self._minedge, subGraphCut=self._subgraphcut, subAlpha=0.3, alpha=self._alpha, epsilon=epsilon, aas=self._aas, verbose=False)
seqTime = time.time() - t1
if paths:
seqs = []
for path in paths:
seqs.extend([DNS.getSequenceFromNodes(subG, path[1], precMass - Constants.mods['H+'] - Constants.mods['H2O'], termModHash)])
scores = list(zip(*paths)[0])
Ord = np.argsort(-1 * np.array(scores))
ambigEdges = []
numAmbig = 0
for j in range(self._numseq):
try:
for i in range(len(seqs[Ord[j]])):
if type(seqs[Ord[j]][i]) == tuple:
ambigEdges.extend([seqs[Ord[j]][i]])
numAmbig += 1
seqs[Ord[j]][i] = '-'
curSeq = ''.join(seqs[Ord[j]])
curSeq = An.preprocessSequence(curSeq, self._seqMap, ambigEdges=ambigEdges)
if j == 0 and curPairedScanData['heavy'] != 'N/A':
try:
curHeavySeq = An.preprocessSequence(curSeq, heavySeqMap, replaceExistingTerminalMods=True, ambigEdges=ambigEdges)
AAs = An.getAllAAs(curHeavySeq, ambigEdges=ambigEdges)
self._seqStatus.set('Paired Sequencing Successful! Heavy Sequence: %s. Time taken: %f seconds' % (curHeavySeq, seqTime))
except KeyError:
self._seqStatus.set('ERROR: Heavy Sequence %s is not a valid sequence! Time wasted: %f seconds' % (curHeavySeq, seqTime))
elif j == 0:
self._seqStatus.set('Unpaired Sequencing Successful! Time taken: %f seconds' % (seqTime))
for labelInst in self._seqScoreData[j]['seq'].children.values():
labelInst.destroy()
self.displayConfColoredSequence(subG, self._seqScoreData[j]['seq'], paths[Ord[j]][1], curSeq, ambigEdges=ambigEdges)
self._seqScoreData[j]['score'].set(str(scores[Ord[j]]))
except IndexError:
for labelInst in self._seqScoreData[j]['seq'].children.values():
labelInst.destroy()
self._seqScoreData[j]['score'].set('')
else:
self._seqStatus.set('ERROR: No Sequences Found! Time wasted: %f seconds' % seqTime)
def validateHeavySequence(seq, heavySeqMap, ambigEdges):
try:
if seq != '-':
heavySeq = Analytics.preprocessSequence(seq, heavySeqMap, replaceExistingTerminalMods=True, ambigEdges=ambigEdges)
AAs = Analytics.getAllAAs(heavySeq, ambigEdges=ambigEdges)
return True
else:
return False
except KeyError:
return False
def getSpectrumAndPSMFeatureDict(LADSSeqInfo, seqEntry, scanFDict, pairConfig, PNet):
featureList = []
lightScans = seqEntry[0]
heavyScans = seqEntry[1]
lightSpecs = [DataFile.getMassIntPairs(scanFDict[int(lightScanF)]['dta']) for lightScanF in lightScans]
heavySpecs = [DataFile.getMassIntPairs(scanFDict[int(heavyScanF)]['dta']) for heavyScanF in heavyScans]
avgLightPrecMass = np.average(np.array([scanFDict[lightScanF]['precMass'] for lightScanF in lightScans]))
epSTD = options.ppmstd * 10**-6 * avgLightPrecMass
specs = []
for i, massIntPairs in enumerate(lightSpecs):
specs += [PN.Spectrum(PNet, scanFDict[lightScans[i]]['precMass'], Nmod=0.0, Cmod=0.0, epsilon=2*epSTD, spectrum=massIntPairs)]
for i, massIntPairs in enumerate(heavySpecs):
specs += [PN.Spectrum(PNet, scanFDict[heavyScans[i]]['precMass'], Nmod=pairConfig['NMod'], Cmod=pairConfig['CMod'], epsilon=2*epSTD, spectrum=massIntPairs)]
for spec in specs:
spec.initializeNoiseModel()
clusterPairingStats = Discriminator.getClusterPairingStats(lightSpecs, heavySpecs, avgLightPrecMass, pairConfig, epSTD=epSTD)
GLFD.addClusterPairingStatsToFeatureList(clusterPairingStats, featureList)
scoreStats = {}
truePMs = {}
prmLadders = {}
for PSM in LADSSeqInfo[seqEntry]:
lightSeq = An.preprocessSequence(PSM[1], seqMap, ambigEdges=PSM[2])
scoreStats[PSM[:2]] = Discriminator.getScoreStats(specs, lightSeq, ambigEdges=PSM[2])
prmLadderWithEnds = An.getPRMLadder(lightSeq, ambigEdges=PSM[2], addEnds=True)
truePMs[PSM[:2]] = prmLadderWithEnds[-1]
prmLadders[PSM[:2]] = prmLadderWithEnds[1:-1]
PSMList = scoreStats.keys()
spectrumOrderedScoreStats, clusterScoreStats = GLFD.compileScoreStats(scoreStats, specs, PSMList)
spectrumAndPSMSpecificFeatureDict = {}
PSMIndexDict = dict([(PSM, i) for i, PSM in enumerate(PSMList)])
for i, PSM in enumerate(LADSSeqInfo[seqEntry]):
PSMSpecificFeatureList = copy.copy(featureList)
peptLength = len(prmLadders[PSM[:2]]) + 1
# Add LADS PScore (and normalized variants) and delta rank, delta score (LADS PScore) to feature list
PSMSpecificFeatureList += [PSM[0], PSM[0]/peptLength, PSM[0]/len(specs), -i, PSM[0]-LADSSeqInfo[seqEntry][0][0]]
# Add Total Path Score (and normalized variants) and delta rank, delta score (total path score) and total minimum node score to feature list
totalPathScore = scoreStats[PSM[:2]]['Total Path Score']
PSMSpecificFeatureList += [totalPathScore, totalPathScore/peptLength, totalPathScore/len(specs), -clusterScoreStats['PSM Rankings'][PSMIndexDict[PSM[:2]]], totalPathScore-clusterScoreStats['Max Cluster Path Score'], scoreStats[PSM[:2]]['Total Minimum Node Score']]
# Add minimum path score, maximum path score, (and normalized variants) and minimum score/maximum score for cluster to feature list
PSMSpecificFeatureList += [scoreStats[PSM[:2]]['Minimum Path Score'], scoreStats[PSM[:2]]['Minimum Path Score']/peptLength, scoreStats[PSM[:2]]['Maximum Path Score'], scoreStats[PSM[:2]]['Maximum Path Score']/peptLength, scoreStats[PSM[:2]]['Minimum Path Score']/scoreStats[PSM[:2]]['Maximum Path Score']]
# Add difference between minimum and maximum ranking for PSM across cluster to feature list
rankingsForPSM = [spectrumOrderedScoreStats[i]['PSM Rankings'][PSMIndexDict[PSM[:2]]] for i in spectrumOrderedScoreStats]
PSMSpecificFeatureList += [min(rankingsForPSM) - max(rankingsForPSM)]
#Add Number forbidden node pairs (and normalized variants) to feature list
numForbiddenPairs = Discriminator.getNumForbiddenPairs(prmLadders[PSM[:2]], avgLightPrecMass)
PSMSpecificFeatureList += [numForbiddenPairs, 2.0*numForbiddenPairs/(peptLength-1)]
# Add number of ambiguous edges to feature list
PSMSpecificFeatureList += [len(PSM[2])]
# Add stats for PRM Evidence over cluster (and normalized variants) to feature list
PSMSpecificFeatureList += [scoreStats[PSM[:2]]['Aggregate PRM Score Statistics']['All Evidence'], scoreStats[PSM[:2]]['Aggregate PRM Score Statistics']['All Evidence']/float(peptLength-1), scoreStats[PSM[:2]]['Aggregate PRM Score Statistics']['Majority Evidence'], scoreStats[PSM[:2]]['Aggregate PRM Score Statistics']['Majority Evidence']/float(peptLength-1), scoreStats[PSM[:2]]['Aggregate PRM Score Statistics']['None Evidence'], scoreStats[PSM[:2]]['Aggregate PRM Score Statistics']['None Evidence']/float(peptLength-1)]
# Add stats for paired PRMs and their corresponding ion types to feature list
pairedPRMStats = Discriminator.getPairedPRMStats(prmLadders[PSM[:2]], clusterPairingStats['Light Merged Spec'], clusterPairingStats['Heavy Merged Spec'], lightSpecs, heavySpecs, clusterPairingStats['Cluster Paired PRM Information'], epSTD=epSTD)
GLFD.addPairedPRMStatsToFeatureList(pairedPRMStats, PSMSpecificFeatureList, len(prmLadders[PSM[:2]]))
pairedPRMLadder = pairedPRMStats['Paired PRM Ladder']
for i, scan in enumerate(lightScans):
spectrumSpecificFeatureList = copy.copy(PSMSpecificFeatureList)
# Add path score (and normalized variants), delta rank, delta score, number of negative PRMs, and minimum node score for spectrum to feature list
pathScore = spectrumOrderedScoreStats[i]['Path Scores'][PSMIndexDict[PSM[:2]]]
numNegativePRMs = spectrumOrderedScoreStats[i]['Num Negative PRMs'][PSMIndexDict[PSM[:2]]]
spectrumSpecificFeatureList += [pathScore, pathScore/peptLength, pathScore/scoreStats[PSM[:2]]['Maximum Path Score'], -spectrumOrderedScoreStats[i]['PSM Rankings'][PSMIndexDict[PSM[:2]]], spectrumOrderedScoreStats[i]['Delta Scores'][PSMIndexDict[PSM[:2]]], numNegativePRMs, numNegativePRMs/float(peptLength-1), spectrumOrderedScoreStats[i]['Min Node Scores'][PSMIndexDict[PSM[:2]]]]
# Add mass deviation from true peptide mass to feature list
precMass = scanFDict[scan]['precMass']
spectrumSpecificFeatureList += [abs(truePMs[PSM[:2]] + Constants.mods['H2O'] + Constants.mods['H+'] - precMass)]
peakAnnotationMassOffsetStats = Discriminator.getPeakAnnotationAndMassOffsetStats(DataFile.getMassIntPairs(scanFDict[scan]['dta']), specs[i], prmLadders[PSM[:2]], pairedPRMLadder, PNet)
GLFD.addPeakAnnotationStatsToFeatureList(PNet, peakAnnotationMassOffsetStats, spectrumSpecificFeatureList, peptLength)
GLFD.addMassOffsetStatsToFeatureList(peakAnnotationMassOffsetStats, spectrumSpecificFeatureList)
spectrumSpecificFeatureList += [precMass, GLFD.getChargeStateFromDTAFName(scanFDict[scan]['dta']), peptLength]
spectrumAndPSMSpecificFeatureDict[(scan, PSM[:2])] = spectrumSpecificFeatureList
for j, scan in enumerate(heavyScans):
i = j + len(lightScans)
spectrumSpecificFeatureList = copy.copy(PSMSpecificFeatureList)
# Add path score (and normalized variants), delta rank, delta score, number of negative PRMs, and minimum node score for spectrum to feature list
pathScore = spectrumOrderedScoreStats[i]['Path Scores'][PSMIndexDict[PSM[:2]]]
numNegativePRMs = spectrumOrderedScoreStats[i]['Num Negative PRMs'][PSMIndexDict[PSM[:2]]]
spectrumSpecificFeatureList += [pathScore, pathScore/peptLength, pathScore/scoreStats[PSM[:2]]['Maximum Path Score'], -spectrumOrderedScoreStats[i]['PSM Rankings'][PSMIndexDict[PSM[:2]]], spectrumOrderedScoreStats[i]['Delta Scores'][PSMIndexDict[PSM[:2]]], numNegativePRMs, numNegativePRMs/float(peptLength-1), spectrumOrderedScoreStats[i]['Min Node Scores'][PSMIndexDict[PSM[:2]]]]
# Add mass deviation from true peptide mass to feature list
precMass = scanFDict[scan]['precMass']
spectrumSpecificFeatureList += [abs(truePMs[PSM[:2]] + pairConfig['NMod'] + pairConfig['CMod'] + Constants.mods['H2O'] + Constants.mods['H+'] - precMass)]
peakAnnotationMassOffsetStats = Discriminator.getPeakAnnotationAndMassOffsetStats(DataFile.getMassIntPairs(scanFDict[scan]['dta']), specs[i], prmLadders[PSM[:2]], pairedPRMLadder, PNet)
GLFD.addPeakAnnotationStatsToFeatureList(PNet, peakAnnotationMassOffsetStats, spectrumSpecificFeatureList, peptLength)
GLFD.addMassOffsetStatsToFeatureList(peakAnnotationMassOffsetStats, spectrumSpecificFeatureList)
spectrumSpecificFeatureList += [precMass, GLFD.getChargeStateFromDTAFName(scanFDict[scan]['dta']), peptLength]
spectrumAndPSMSpecificFeatureDict[(scan, PSM[:2])] = spectrumSpecificFeatureList
return spectrumAndPSMSpecificFeatureDict
outFile.write('\t'.join([col for col in cols]) + '\n')
for seqEntry in LADSSeqInfo:
lightScans = seqEntry[0]
heavyScans = seqEntry[1]
scanScoreDict = getScanScoreDictSVM(LADSSeqInfo, seqEntry, scanFDict, svmModel, svmRange, pairConfigurations[pairConfigName], PNet, desired_feats = desired_feats)
# scanScoreDict = getScanScoreDictRankBoost(LADSSeqInfo, seqEntry, scanFDict, rankModel, pairConfigurations['lightdimethyl_heavydimethyl'], PNet)
# scanScoreDict = getScanScoreDictClusterNormScore(LADSSeqInfo, seqEntry)
for i, scan in enumerate(lightScans):
scanData = {'ScanF': scan}
lightSeq = An.preprocessSequence(scanScoreDict[scan]['Seq'][0], seqMap, ambigEdges=scanScoreDict[scan]['Seq'][1])
scanData['LADS Sequence'] = lightSeq
scanData['LADS Ambig Edges'] = scanScoreDict[scan]['Seq'][1]
scanData['LADS Raw Score'] = scanScoreDict[scan]['Raw Score']
scanData['LADS Post Score'] = scanScoreDict[scan]['Post Score']
scanData['M+H'] = scanFDict[scan]['precMass']
try:
comp = An.comparePeptideResults(lightSeq, SEQUESTMASCOTResults[scan]['Peptide'], ambigEdges1=scanScoreDict[scan]['Seq'][1], ambigEdges2=[], ppm=20)
scanData['SEQUEST XCorr'] = SEQUESTMASCOTResults[scan]['SEQUEST XCorr']
scanData['MASCOT Ion Score'] = SEQUESTMASCOTResults[scan]['MASCOT Ion Score']
scanData['SEQUEST MASCOT Sequence'] = SEQUESTMASCOTResults[scan]['Peptide']
scanData['Accuracy'] = comp[0]
scanData['Precision'] = comp[1]
except KeyError:
scanData['SEQUEST XCorr'] = None
specs = []
for i, massIntPairs in enumerate(lightSpecs):
specs += [PN.Spectrum(PNet, scanFDict[lightScans[i]]['precMass'], Nmod=0.0, Cmod=0.0, epsilon=2*epSTD, spectrum=massIntPairs)]
for i, massIntPairs in enumerate(heavySpecs):
specs += [PN.Spectrum(PNet, scanFDict[heavyScans[i]]['precMass'], Nmod=pairConfig['NMod'], Cmod=pairConfig['CMod'], epsilon=2*epSTD, spectrum=massIntPairs)]
for spec in specs:
spec.initializeNoiseModel()
clusterPairingStats = Discriminator.getClusterPairingStats(lightSpecs, heavySpecs, avgLightPrecMass, pairConfig, epSTD=epSTD)
addClusterPairingStatsToFeatureList(clusterPairingStats, featureList)
scoreStats = {}
truePMs = {}
prmLadders = {}
for PSM in LADSSeqInfo[seqEntry]:
lightSeq = An.preprocessSequence(PSM[1], seqMap, ambigEdges=PSM[2])
scoreStats[PSM[:2]] = Discriminator.getScoreStats(specs, lightSeq, ambigEdges=PSM[2])
prmLadderWithEnds = An.getPRMLadder(lightSeq, ambigEdges=PSM[2], addEnds=True)
truePMs[PSM[:2]] = prmLadderWithEnds[-1]
prmLadders[PSM[:2]] = prmLadderWithEnds[1:-1]
PSMList = scoreStats.keys()
spectrumOrderedScoreStats, clusterScoreStats = compileScoreStats(scoreStats, specs, PSMList)
PSMIndexDict = dict([(PSM, i) for i, PSM in enumerate(PSMList)])
for i, PSM in enumerate(LADSSeqInfo[seqEntry]):
PSMSpecificFeatureList = copy.copy(featureList)
lightSeq = An.preprocessSequence(PSM[1], seqMap, ambigEdges=PSM[2])
heavySeq = An.preprocessSequence(PSM[1], heavySeqMaps['silac_light_heavy'], replaceExistingTerminalMods=True, ambigEdges=PSM[2])
