def getPairedAndUnpairedSpectra(dtaDir, dtaList, Nmod, Cmod, ppm=5, cutOff=0.1, verbose=False):
specPairs = []
unpairedSpecs = []
delta = Nmod + Cmod
for i in range(len(dtaList)):
paired = False
precMass1 = DataFile.getPrecMassAndCharge(dtaList[i])[0]
spec1 = DataFile.getMassIntPairs(dtaList[i])
for j in range(i + 1, len(dtaList)):
precMass2 = DataFile.getPrecMassAndCharge(dtaList[j])[0]
epsilon = ppm * 10 ** -6 * max(precMass1, precMass2)
if np.abs(np.abs(precMass1 - precMass2) - delta) < epsilon:
spec2 = DataFile.getMassIntPairs(dtaList[j])
if precMass1 < precMass2:
N, C = SA.getNandCIons(spec1, spec2, Nmod, Cmod, epsilon=epsilon)
ratio = SA.getSharedPeaksRatio(spec1, spec2, N, C)
else:
N, C = SA.getNandCIons(spec2, spec1, Nmod, Cmod, epsilon=epsilon)
ratio = SA.getSharedPeaksRatio(spec2, spec1, N, C)
if ratio > cutOff:
if verbose:
print 'Pair found', dtaList[i], dtaList[j]
paired = True
specs = (dtaList[i], dtaList[j])
lightInd = int(precMass2 < precMass1)
specPairs.extend([(ratio, specs[lightInd], specs[1 - lightInd])])
if not paired:
unpairedSpecs.extend([dtaList[i]])
if verbose:
print 'No pairs for', dtaList[i]
return specPairs, unpairedSpecs
def findDeltaPairs(dtaList, delta, ppm=5, intEp=20):
precMassArr = np.zeros((len(dtaList), 2))
pairs = []
for i in range(len(dtaList)):
precMassArr[i] = [DataFile.getPrecMassAndCharge(dtaList[i])[0], DataFile.getScanNum(dtaList[i])]
maxPrecMass = np.max(precMassArr, 0)[0]
epsilon = ppm * 10**-6 * maxPrecMass
resolution = epsilon/intEp
hPrecMassArr = copy.copy(precMassArr)
hPrecMassArr[:,0] = np.round(hPrecMassArr[:,0]/resolution)
hashedDict = {}
for elem in hPrecMassArr:
hInd = int(elem[0])
for hMass in range(hInd-intEp, hInd+intEp+1):
try:
hashedDict[hMass] += [(hMass-hInd, elem[1])]
except KeyError:
hashedDict[hMass] = [(hMass-hInd, elem[1])]
shiftHashDict = copy.copy(precMassArr)
shiftHashDict[:,0] = np.round((shiftHashDict[:,0] - delta)/resolution)
for i, elem in enumerate(shiftHashDict):
hInd = int(elem[0])
if hInd in hashedDict:
for possiblePair in hashedDict[hInd]:
if abs(possiblePair[0]) * resolution * 10**6/precMassArr[i][0] < ppm:
pairs += [(int(possiblePair[1]), int(elem[1]))]
return pairs
def findSamePrecMassClusters(dtaList, ppm=5):
precMassArr = np.zeros((len(dtaList), 2))
for i in range(len(dtaList)):
precMassArr[i] = [DataFile.getPrecMassAndCharge(dtaList[i])[0], DataFile.getScanNum(dtaList[i])]
precMassArr = precMassArr[np.argsort(precMassArr[:,0])]
clusters = [[i] for i in range(precMassArr.shape[0])]
i = 0
while i < len(clusters):
mergeClusters = False
epsilon = ppm * 10**-6 * precMassArr[clusters[i][0]][0]
for precMassInd1 in clusters[i]:
for precMassInd2 in clusters[i - 1]:
if (np.abs(precMassArr[precMassInd1][0] - precMassArr[precMassInd2][0]) < epsilon):
mergeClusters = True
break
if mergeClusters:
clusters[i - 1].extend(clusters[i])
del clusters[i]
else:
i = i + 1
scanFClusters = []
for cluster in clusters:
scanFClusters += [[precMassArr[i][1] for i in cluster]]
return scanFClusters
def getScanFDict(dtaList):
scanFDict = {}
for dta in dtaList:
scanF = DataFile.getScanNum(dta)
precMass = DataFile.getPrecMassAndCharge(dta)[0]
scanFDict[scanF] = {'dta': dta, 'precMass': precMass, 'sequenced': False}
return scanFDict
def getScanFDict(dtaList):
scanFDict = {}
for dta in dtaList:
scanF = DataFile.getScanNum(dta)
precMass = DataFile.getPrecMassAndCharge(dta)[0]
scanFDict[scanF] = {"dta": dta, "precMass": precMass, "sequenced": False}
return scanFDict
def getLADSPScore(seq, dtaPath, PNet, ppm=5, ambigEdges=None, ambigAA='X', ambigPenalty=20):
pairs = DataFile.getMassIntPairs(dtaPath)
precMass = DataFile.getPrecMassAndCharge(dtaPath)[0]
epsilon = ppm * precMass * 10 ** -6
spec = PN.Spectrum(PNet, precMass, Nmod=0, Cmod=0, epsilon=epsilon, spectrum=pairs)
spec.initializeNoiseModel()
nodeGen = Constants.nodeInfoGen(seq, considerTerminalMods=True, ambigEdges=ambigEdges)
pScore = 0
node = nodeGen.next()
pScore += spec.getNodeScore(**node)
pScore += spec.getPriorScore(prm=0, formAA=None, lattAA=node['formAA'])
if node['formAA'] == ambigAA:
pScore -= ambigPenalty
for node in nodeGen:
pScore += spec.getNodeScore(**node)
if node['formAA'] == ambigAA:
pScore -= ambigPenalty
pScore += spec.getPriorScore(prm=precMass- Constants.mods['H+'] - Constants.mods['H2O'], formAA=node['lattAA'], lattAA=None)
if node['lattAA'] == ambigAA:
pScore -= ambigPenalty
return pScore
if len(cluster) > 1:
combMasses += [sum(cluster) / len(cluster)]
else:
combMasses += cluster
return np.sort(np.array(combMasses))
if __name__ == '__main__':
dirPath = 'C:\\Users\\Arun\\Pythonprojects\\DeNovoSequencing\\LF2_short_HCD+CID_ath001862_244\\'
ppm = 5
heavyPath = dirPath + '244.3611.3611.1.dta'
lightPath = dirPath + '244.3619.3619.1.dta'
heavyPairs = DataFile.getMassIntPairs(heavyPath)
lightPairs = DataFile.getMassIntPairs(lightPath)
heavyPrecMass, heavyCharge = DataFile.getPrecMassAndCharge(heavyPath)
lightPrecMass, lightCharge = DataFile.getPrecMassAndCharge(lightPath)
print ppm * 10 ** -6 * heavyPrecMass
print getSharedPeaksRatio(lightPairs, heavyPairs, Nmod=0, Cmod=Constants.mods['*'], epsilon=ppm * heavyPrecMass * 10 ** -6)
"""
tPath = dirPath + '244.0855.0855.1.dta'
tMass = DataFile.getPrecMassAndCharge(tPath)[0]
tPairs = DataFile.getMassIntPairs(tPath)
tIons = tPairs[:,0]
tIons = np.insert(tIons, 0, 0)
tIons = np.append(tIons, tMass)
tIons = getSymmetrizedSpectrum(tIons, tMass)
print tIons
(lightSpec, heavySpec) = pair[1:]
if options.verbose:
print 'Now sequencing %s %s with shared peaks ratio %f' % (lightSpec, heavySpec, pair[0])
s1 = time.time()
heavyPath = heavySpec
lightPath = lightSpec
sharedInfo = DNS.getPairedSpectraInfoForSequencing(lightPath, heavyPath, options.verbose)
DNS.sequencePairedSpectra(sharedInfo['NInd'], sharedInfo['CInd'], sharedInfo['lightPairs'], sharedInfo['heavyPairs'], sharedInfo['lightPrecMass'] - Constants.mods['H+'] - Constants.mods['H2O'], PNet, alpha=options.alpha, unknownPenalty=options.ambigEdgePenalty, maxEdge=options.maxEdge, minEdge=options.minEdge, Nmod=options.Nmod, Cmod=options.Cmod, aas=aas, verbose=options.verbose)
if options.verbose:
print 'Time taken:', time.time() - s1
for spec in unpaired:
if options.verbose:
print 'Now sequencing unpaired spectrum %s' % spec
s1 = time.time()
precMass = DataFile.getPrecMassAndCharge(spec)[0]
pairs = DataFile.getMassIntPairs(spec)
DNS.sequenceSingleSpectrum(pairs, precMass - Constants.mods['H+'] - Constants.mods['H2O'], PNet, alpha=options.alpha, unknownPenalty=options.ambigEdgePenalty, maxEdge=options.maxEdge, minEdge=options.minEdge, aas=aas, verbose=options.verbose)
if options.verbose:
print 'Time taken:', time.time() - s1
if options.verbose:
print 'Finished sequencing. Time taken: ', time.time() - t2
print 'Total time taken for program: ', time.time() - t1