pairConfigName = pairConfigurations.keys()[0]
dtaList = glob.glob(options.dtadir + '/*.dta')
scanFDict = SDTDV.getScanFDict(dtaList)
if options.sequest:
SEQUESTMASCOTResults = DataFile.indexDataByKey(DataFile.getScanInfo(options.sequest, delimiter='\t'))
else:
SEQUESTMASCOTResults = {}
outFile = open(options.output, 'w')
# rankModel = loadRankingModel(options.discmodel)
# linearDiscVec = np.loadtxt(options.discmodel)
svmModel = svmutil.svm_load_model(options.discmodel)
svmRange = svmutil.load_ranges(os.path.splitext(options.discmodel)[0] + '.range')
"""
cols = ['ScanF', 'M+H', 'PEAKS ALC', 'PEAKS TLC', 'PEAKS Sequence', 'SEQUEST XCorr', 'MASCOT Ion Score', 'SEQUEST MASCOT Sequence', 'Accuracy', 'Precision']
outFile.write('\t'.join([col for col in cols]) + '\n')
PEAKSInfo = DataFile.indexDataByKey(DataFile.getScanInfo(options.lads, delimiter='\t'), key='ScanF')
for scan in PEAKSInfo:
if scan not in SEQUESTMASCOTResults:
continue
scanData = {'ScanF': scan}
scanData['M+H'] = scanFDict[scan]['precMass']
scanData['PEAKS ALC'] = PEAKSInfo[scan]['ALC (%)']
scanData['PEAKS TLC'] = PEAKSInfo[scan]['TLC']
scanData['PEAKS Sequence'] = PEAKSInfo[scan]['Peptide']
PNet = PN.ProbNetwork(options.config, options.model)
dtaList = glob.glob(options.dtadir + '/*.dta')
scanFDict = getScanFDict(dtaList)
aas = Constants.addPepsToAADict(300)
hashedAAs = Constants.hashAAsEpsilonRange(aas, epStep, maxEp)
ambigOpenPenalty = 0
ambigPenaltyFun = DNS.getAmbigEdgePenaltyFunction(options.minedge, ambigOpenPenalty, options.ambigpenalty)
ppmPenaltyFun = DNS.getPPMPenaltyFun(options.ppmstd, hashedAAs, options.minedge, options.ppmpenalty, options.ppmsyserror, epStep)
print 'Getting Clusters'
parent = os.path.abspath(os.pardir)
clusterSVMModel = svmutil.svm_load_model(parent + paramsDict['Cluster Configuration']['model'])
clusterSVMRanges = svmutil.load_ranges(parent + os.path.splitext((paramsDict['Cluster Configuration']['model']))[0] + '.range')
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()
dbDict["infoMap"],
progDict,
paramsDict["Pair Configurations"][pairConfigName],
progName=progName,
isComp=False,
ppm=options.ppmstd,
)
pairs = {}
times = {}
t1 = time.time()
print "Getting Clusters"
clusterSVMModel = svmutil.svm_load_model(paramsDict["Cluster Configuration"]["model"])
clusterSVMRanges = svmutil.load_ranges(
os.path.splitext((paramsDict["Cluster Configuration"]["model"]))[0] + ".range"
)
precMassClusters = An.findSamePrecMassClusters(dtaList, ppm=options.ppmstd)
# print 'precMassClusters', precMassClusters
samePeptideClusters = An.getSamePeptideClusters(
precMassClusters,
scanFDict,
clusterSVMModel,
clusterSVMRanges,
ppmSTD=options.ppmstd,
cutOff=float(paramsDict["Cluster Configuration"]["cutoff"]),
)
# samePeptideClusters = An.getSamePeptideClusters(precMassClusters, scanFDict, clusterSVMModel, clusterSVMRanges, ppmSTD=options.ppmstd, cutOff=4)
outFile.write("\n%i Clusters Found. Time taken: %f\n" % (len(samePeptideClusters), time.time() - t1))
trueClusters = An.getTrueClusters(
