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)
pairsOut = open(options.output + '_' + pairConfigName + '.txt', 'w')
for pair in deltaPairs:
epSTD = options.ppmstd * 10 ** -6 * scanFDict[precMassClusters[pair[0]][0]]['precMass']
# Get all possible true pairings from database search results
uniquePeptideDict = defaultdict(lambda: {'light': [], 'heavy': []})
for scanF in precMassClusters[pair[0]]:
if scanF in processedInfo[progName]:
uniquePeptideDict[An.stripModifications(processedInfo[progName][scanF][infoMap[progDict[progName]]['Peptide']], noRemove=['#'])]['light'] += [scanF]
for scanF in precMassClusters[pair[1]]:
if scanF in processedInfo[progName]:
precMassClusters = Analytics.findSamePrecMassClusters(dtaList, ppm=options.ppmstd)
# print 'precMassClusters', precMassClusters
samePeptideClusters = Analytics.getSamePeptideClusters(precMassClusters, scanFDict, clusterSVMModel, clusterSVMRanges, ppmSTD=options.ppmstd, cutOff=float(paramsDict['Cluster Configuration']['cutoff']))
# samePeptideClusters = Analytics.getSamePeptideClusters(precMassClusters, scanFDict, clusterSVMModel, clusterSVMRanges, ppmSTD=options.ppmstd, cutOff=4)
# samePeptideClusters = An.getSamePeptideClusters(precMassClusters, scanFDict, clusterSVMModel, clusterSVMRanges, ppmSTD=options.ppmstd, cutOff=4)
# To test without any clustering
#samePeptideClusters = [[scanF] for scanF in scanFDict]
for pairConfigName in paramsDict['Pair Configurations']:
print 'Getting heavy-light pairs for %s' % (pairConfigName,)
t1 = time.time()
pairConfig = paramsDict['Pair Configurations'][pairConfigName]
pairs = Analytics.findDeltaPairsClusters(samePeptideClusters, scanFDict, pairConfig['NMod']+pairConfig['CMod'], ppm=options.ppmstd)
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
precision = int(float(TP) / (TP + FP) * 10000) / float(100)
except ZeroDivisionError:
precision = 100
outFile.write("\n" + "\t".join(["TP", "FP", "TN", "FN", "Sensitivity", "Precision"]) + "\n")
outFile.write("\t".join([str(val) for val in [TP, FP, TN, FN, sensitivity, precision]]) + "\n")
for pairConfigName in paramsDict["Pair Configurations"]:
pairs[pairConfigName] = {}
pairConfig = paramsDict["Pair Configurations"][pairConfigName]
startTime = time.time()
svmModel = svmutil.svm_load_model(pairConfig["Model"])
svmRange = svmutil.load_ranges(os.path.splitext(pairConfig["Model"])[0] + ".range")
delta = pairConfig["NMod"] + pairConfig["CMod"]
deltaPairs = An.findDeltaPairsClusters(samePeptideClusters, scanFDict, delta, ppm=options.ppmstd)
outFile.write(
"\nTotal number of cluster pairs considered for pair Config %s (including pairs not reported by database search results): %i\n"
% (pairConfigName, len(deltaPairs))
)
x, y = [], []
# testedDeltaPairedScanFs = set()
# testedPairs = set()
# possPairsList = []
testedDeltaPairs = []
for pair in deltaPairs:
if not (
any([scanF in processedInfo[progName] for scanF in samePeptideClusters[pair[0]]])
and any([scanF in processedInfo[progName] for scanF in samePeptideClusters[pair[1]]])
):
continue
