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
return rankingModel
if __name__ == '__main__':
print 'This program generates a results file containing Raw lads output postscored with the algorithm of choice. The discmodel is a supplied model, if necessary for the postscoring algorithm'
options = ArgLib.parse(['init', 'ppmstd', 'dtadir', 'lads', 'sequest', 'config', 'model', 'output', 'symbolmap'], optArgs=[{'opts': ('-D', '--discmodel'), 'attrs': {'type': 'string', 'dest': 'discmodel', 'help': 'Model used to calculate discriminant score'}}, {'opts': ('-P', '--pairconfig'), 'attrs': {'type': 'string', 'dest': 'pairconfig', 'help': 'Name of LADS Pair Configuration'}}, {'opts': ('-F', '--featurelist'), 'attrs': {'type': 'string', 'dest': 'featurelist', 'help': 'File containing pickled list of desired features (optional)'}}])
parent = os.path.abspath(os.pardir)
PNet = PN.ProbNetwork(options.config, options.model)
paramsDict = ArgLib.parseInitFile(options.init, options)
pairConfigurations = paramsDict['Pair Configurations']
LADSSeqInfo = GLFD.parseSequenceDTAsLogfile(options.lads)
with open(options.symbolmap, 'r') as fin:
symbolMap = pickle.load(fin)
seqMap = DataFile.generateSeqMap({'LADS Unit Test': 'LADS'}, symbolMap, paramsDict)
seqMap = seqMap['LADS Unit Test']
if options.featurelist:
with open(options.featurelist) as fin:
desired_feats = pickle.load(fin)
else:
desired_feats = None
heavySeqMaps = {}
for confName in pairConfigurations:
heavySeqMaps[confName] = copy.deepcopy(seqMap)
