def scoreMods(self, modCalls):
"""
For each modification in the best scoring configuration, score a config excluding the current mod against the winning config
use this value as the Qmod for the deleted modification
"""
qvModCalls = dict()
modSeq = a.array('c')
modSeq.fromstring(self.sequence)
# Apply the found modifications to the raw sequence
for (pos, call) in modCalls.items():
modSeq[pos] = call
for (pos, call) in modCalls.items():
# Score the modified template at all positions affected by this mod
modScore = self.scoreRegion(pos - self.post, pos + self.pre,
modSeq)
modScores = self.getRegionScores(pos - self.post, pos + self.pre,
modSeq)
if self.methylFractionFlag and self.rawKinetics.has_key(pos):
if self.rawKinetics[pos]["coverage"] > self.methylMinCov:
modifiedMeanVectors = self.getContextMeans(
pos - self.post, pos + self.pre, modSeq)
# Switch back to the unmodified base and re-score
modSeq[pos] = canonicalBaseMap[call]
noModScore = self.scoreRegion(pos - self.post, pos + self.pre,
modSeq)
noModScores = self.getRegionScores(pos - self.post, pos + self.pre,
modSeq)
if self.methylFractionFlag and self.rawKinetics.has_key(pos):
if self.rawKinetics[pos]["coverage"] > self.methylMinCov:
unModifiedMeanVectors = self.getContextMeans(
pos - self.post, pos + self.pre, modSeq)
# Put back the modified base
modSeq[pos] = call
# Compute score difference
llr = modScore - noModScore
# Convert from LLR to phred-scaled probability of modification
qModScore = 10 * llr * log10e + 10 * log1p(exp(-llr)) * log10e
# Figure out which secondary peaks were likely generated by this modification
# What is the posterior that the peak was generated by this mod?
maskPos = self.findMaskPositions(pos, modScores, noModScores)
# FIXME: Without this, currently, the identificationQv score is too low for many Ca5C sites
# if self.useLDA:
# if self.rawKinetics.has_key(pos):
# if self.rawKinetics[pos].has_key('Ca5C'):
# llr = -self.rawKinetics[pos]['Ca5C']
# qModScore = 100 * llr * log10e + 100*log1p(exp(-llr))*log10e
if self.methylFractionFlag and self.rawKinetics.has_key(pos):
if self.rawKinetics[pos]["coverage"] > self.methylMinCov:
# Instantiate mixture estimation methods:
mixture = MixtureEstimationMethods(self.gbmModel.post,
self.gbmModel.pre,
self.rawKinetics,
self.methylMinCov)
# Use modifiedMeanVectors and unmodifiedMeanVectors to calculate mixing proportion, and 95% CI limits.
methylFracEst, methylFracLow, methylFracUpp = mixture.estimateMethylatedFractions(
pos, unModifiedMeanVectors, modifiedMeanVectors,
ModificationPeakMask[modNames[call]])
qvModCalls[pos] = {
'modification': modNames[call],
'QMod': qModScore,
'LLR': llr,
'Mask': maskPos,
FRAC: methylFracEst,
FRAClow: methylFracLow,
FRACup: methylFracUpp
}
else:
qvModCalls[pos] = {
'modification': modNames[call],
'QMod': qModScore,
'LLR': llr,
'Mask': maskPos
}
else:
# Store the full results
qvModCalls[pos] = {
'modification': modNames[call],
'QMod': qModScore,
'LLR': llr,
'Mask': maskPos
}
return qvModCalls
def scoreMods(self, modCalls):
"""
For each modification in the best scoring configuration, score a config excluding the current mod against the winning config
use this value as the Qmod for the deleted modification
"""
qvModCalls = dict()
modSeq = a.array('c')
modSeq.fromstring(self.sequence)
# Apply the found modifications to the raw sequence
for (pos, call) in modCalls.items():
modSeq[pos] = call
for (pos, call) in modCalls.items():
# Score the modified template at all positions affected by this mod
modScore = self.scoreRegion(pos - self.post, pos + self.pre, modSeq)
modScores = self.getRegionScores(pos - self.post, pos + self.pre, modSeq)
if self.methylFractionFlag and self.rawKinetics.has_key(pos):
if self.rawKinetics[pos]["coverage"] > self.methylMinCov:
modifiedMeanVectors = self.getContextMeans(pos - self.post, pos + self.pre, modSeq)
# Switch back to the unmodified base and re-score
modSeq[pos] = canonicalBaseMap[call]
noModScore = self.scoreRegion(pos - self.post, pos + self.pre, modSeq)
noModScores = self.getRegionScores(pos - self.post, pos + self.pre, modSeq)
if self.methylFractionFlag and self.rawKinetics.has_key(pos):
if self.rawKinetics[pos]["coverage"] > self.methylMinCov:
unModifiedMeanVectors = self.getContextMeans(pos - self.post, pos + self.pre, modSeq)
# Put back the modified base
modSeq[pos] = call
# Compute score difference
llr = modScore - noModScore
# Convert from LLR to phred-scaled probability of modification
qModScore = 10 * llr * log10e + 10 * log1p(exp(-llr)) * log10e
# Figure out which secondary peaks were likely generated by this modification
# What is the posterior that the peak was generated by this mod?
maskPos = self.findMaskPositions(pos, modScores, noModScores)
# FIXME: Without this, currently, the identificationQv score is too low for many Ca5C sites
# if self.useLDA:
# if self.rawKinetics.has_key(pos):
# if self.rawKinetics[pos].has_key('Ca5C'):
# llr = -self.rawKinetics[pos]['Ca5C']
# qModScore = 100 * llr * log10e + 100*log1p(exp(-llr))*log10e
if self.methylFractionFlag and self.rawKinetics.has_key(pos):
if self.rawKinetics[pos]["coverage"] > self.methylMinCov:
# Instantiate mixture estimation methods:
mixture = MixtureEstimationMethods(self.gbmModel.post, self.gbmModel.pre, self.rawKinetics, self.methylMinCov)
# Use modifiedMeanVectors and unmodifiedMeanVectors to calculate mixing proportion, and 95% CI limits.
methylFracEst, methylFracLow, methylFracUpp = mixture.estimateMethylatedFractions(pos, unModifiedMeanVectors, modifiedMeanVectors, ModificationPeakMask[modNames[call]])
qvModCalls[pos] = {'modification': modNames[call], 'QMod': qModScore, 'LLR': llr, 'Mask': maskPos,
FRAC: methylFracEst, FRAClow: methylFracLow, FRACup: methylFracUpp}
else:
qvModCalls[pos] = {'modification': modNames[call], 'QMod': qModScore, 'LLR': llr, 'Mask': maskPos}
else:
# Store the full results
qvModCalls[pos] = {'modification': modNames[call], 'QMod': qModScore, 'LLR': llr, 'Mask': maskPos}
return qvModCalls
