def getAccAndPrecForModRefPeptide(modList, newRefEndInds, deNovoSeq, deNovoUnmodSeq, refSeq, alignedIndsMap, deNovoAmbigEdges=[]):
prevIntervalStart = newRefEndInds['start']
#print 'End Inds', newRefEndInds
tempSeq = ''
tempAmbigEdges = []
for interval in sorted(modList):
if 'Isobaric' not in modList[interval][0][0] and not ('Insertion' in modList[interval][0][0] and (alignedIndsMap['De Novo'][interval[0]] < 2 or (len(deNovoUnmodSeq) - alignedIndsMap['De Novo'][interval[1]]) < 2)):
tempSeq += refSeq[prevIntervalStart:alignedIndsMap['Ref'][interval[0]]] + 'X'
#print 'Mod list interval', modList[interval]
tempAmbigEdges += [(0, modList[interval][0][3])]
#print 'temp ambig edges', tempAmbigEdges
prevIntervalStart = alignedIndsMap['Ref'][interval[1]]
#print 'TempSeq', tempSeq, tempAmbigEdges
tempSeq += refSeq[prevIntervalStart:(len(refSeq) + newRefEndInds['end'])]
#print deNovoSeq, refSeq, tempSeq, deNovoAmbigEdges, tempAmbigEdges
comp = An.comparePeptideResults(deNovoSeq, tempSeq, ambigEdges1=deNovoAmbigEdges, ambigEdges2=tempAmbigEdges, ppm=10)
return comp[0], comp[1]
# 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
scanData['MASCOT Ion Score'] = None
scanData['SEQUEST MASCOT Sequence'] = None
scanData['Accuracy'] = None
scanData['Precision'] = None
outFile.write('\t'.join([str(scanData[col]) for col in cols]) + '\n')
for i, scan in enumerate(heavyScans):
# 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)
addPeakAnnotationStatsToFeatureList(PNet, peakAnnotationMassOffsetStats, spectrumSpecificFeatureList, peptLength)
addMassOffsetStatsToFeatureList(peakAnnotationMassOffsetStats, spectrumSpecificFeatureList)
spectrumSpecificFeatureList += [precMass, getChargeStateFromDTAFName(scanFDict[scan]['dta']), peptLength]
comp = An.comparePeptideResults(lightSeq, SEQUESTMASCOTResults[scan]['Peptide'], ambigEdges1=PSM[2], ambigEdges2=[], ppm=5)
acc, prec = comp[0], comp[1]
# print lightSeq, SEQUESTMASCOTResults[scan]['Peptide']
# print "acc, prec", acc, prec
if prec < 1:
rank = -1
else:
rank = 1
writeFeatures(spectrumSpecificFeatureList, rank, 1, outFile, comment="Scan %i From DTA Directory %s" % (int(scan), dtadir))
# printFeatures(featureNames, spectrumSpecificFeatureList)
for j, scan in enumerate(heavyScans):
if int(scan) not in SEQUESTMASCOTResults:
for i in getAllScanF(processedInfo):
scanData = {}
scanData['ScanF'] = i
for progName in progNames:
for col in dbDict[progDict[progName]]['cols']:
try:
scanData[progName + ' ' + col] = processedInfo[progName][i][col]
except KeyError:
scanData[progName + ' ' + col] = None
progPept = getPeptideData(progName, progDict, i)
for sprogName in consensi[progName]:
sProgPept = getPeptideData(sprogName, progDict, i)
if progPept and sProgPept:
comp = An.comparePeptideResults(progPept[0], sProgPept[0], ambigEdges1=progPept[1], ambigEdges2=sProgPept[1])
else:
comp = (None, None, None)
for j, item in enumerate(['Precision', 'Accuracy', 'Consensus']):
scanData[progName + ' ' + sprogName + ' ' + item] = comp[j]
outFile.write('\t'.join([str(scanData[col]) for col in cols]) + '\n')
print '\nScan Number %i \n' % i
print '\t'.join(['Program', 'Peptide', 'Reference', 'Score', 'Obs M+H'])
for progName in progNames:
peptide = str(scanData[progName + ' ' + dbDict['infoMap'][progDict[progName]]['Peptide']])
score = dbDict['infoMap'][progDict[progName]]['Score'] + ': ' + str(scanData[progName + ' ' + dbDict['infoMap'][progDict[progName]]['Score']])
try:
MH = str(scanData[progName + ' ' + dbDict['infoMap'][progDict[progName]]['Obs M+H']])
except KeyError:
