def onChunk(self, referenceWindow):
# Setup the object for a new window.
self._prepForReferenceWindow(referenceWindow)
# start and end are the windows of the reference that we are responsible for reporting data from.
# We may elect to pull data from a wider window for use with positive control
(reference, start, end) = referenceWindow
# Trim end coordinate to length of current template
end = min(end, self.ipdModel.refLength(reference))
if self.options.identify:
# If we are attempting to identify modifications, get the raw data for a slightly expanded window
# then do the decoding, then weave the modification results back into the main results
padStart = start - self.pad
padEnd = end + self.pad
perSiteResults = self._summarizeReferenceRegion((padStart, padEnd), self.options.methylFraction, self.options.identify)
if self.options.useLDA:
# FIXME: add on a column "Ca5C" containing LDA score for each C-residue site
# Below is an example of how to use an alternative, the BasicLdaEnricher, which does not use the positive control model
# PositiveControlEnricher currently uses a logistic regression model trained using SMRTportal job 65203 (native E. coli)
# lda = BasicLdaEnricher( self.ipdModel.gbmModel, self.sequence, perSiteResults, self.options.identify, self.options.modsToCall )
lda = PositiveControlEnricher(self.ipdModel.gbmModel, self.sequence, perSiteResults)
perSiteResults = lda.callEnricherFunction(perSiteResults)
try:
# Handle different modes of 'extra analysis' here -- this one is for multi-site m5C detection
# mods = self._multiSiteDetection(perSiteResults, (start, end))
mods = self._decodePositiveControl(perSiteResults, (start, end))
except:
type, value, tb = sys.exc_info()
traceback.print_exc()
pdb.post_mortem(tb)
finalCalls = []
# Weave together results
for strand in [0, 1]:
strandSign = 1 if strand == 0 else -1
siteDict = dict((x['tpl'], x) for x in perSiteResults if start <= x['tpl'] < end and x['strand'] == strand)
modDict = dict((x['tpl'], x) for x in mods if start <= x['tpl'] < end and x['strand'] == strand)
# Go through the modifications - add tags for identified mods to per-site stats
# add a 'offTarget' tag to the off target peaks.
for (pos, mod) in modDict.items():
# Only convert to positive control call if we actually have enough
# coverage on the cognate base!
if siteDict.has_key(mod['tpl']):
# Copy mod identification data
#siteDict[mod['tpl']]['modificationScore'] = mod['QMod']
#siteDict[mod['tpl']]['modification'] = mod['modification']
if self.options.methylFraction and mod.has_key(FRAC):
siteDict[mod['tpl']][FRAC] = mod[FRAC]
siteDict[mod['tpl']][FRAClow] = mod[FRAClow]
siteDict[mod['tpl']][FRACup] = mod[FRACup]
# Copy any extra properties that were added
newKeys = set(mod.keys()) - set(siteDict[mod['tpl']].keys())
for nk in newKeys:
siteDict[mod['tpl']][nk] = mod[nk]
if mod.has_key('Mask'):
# The decoder should supply the off-target peak mask
mask = mod['Mask']
mask.append(0) # make sure we always mask the cognate position
else:
# If the decoder doesn't supply a mask - use a hard-coded version
# FIXME - this branch is deprecated
mask = ModificationPeakMask[mod['modification']]
# Mask out neighbor peaks that may have been caused by this mod
for offset in mask:
shadowPos = mod['tpl'] + strandSign * offset
if siteDict.has_key(shadowPos):
siteDict[shadowPos]['offTargetPeak'] = True
finalCalls.extend(siteDict.values())
# Sort by template position
finalCalls.sort(key=lambda x: x['tpl'])
return finalCalls
else:
result = self._summarizeReferenceRegion((start, end), self.options.methylFraction, self.options.identify)
if self.options.useLDA and self.controlCmpH5 is None:
# FIXME: add on a column "Ca5C" containing LDA score for each C-residue site
# lda = BasicLdaEnricher(self.ipdModel.gbmModel, self.sequence, result, self.options.identify)
lda = PositiveControlEnricher(self.ipdModel.gbmModel, self.sequence, result)
results = lda.callEnricherFunction(result)
result.sort(key=lambda x: x['tpl'])
return result
def onChunk(self, referenceWindow):
# start and end are the windows of the reference that we are responsible for reporting data from.
# We may elect to pull data from a wider window for use with positive control
if self.options.smBaseMod:
(reference, smId, start, end) = referenceWindow
else:
(reference, start, end) = referenceWindow
targetBounds = (start,end)
# Trim end coordinate to length of current template
end = min(end,self.ipdModel.refLength(reference))
# Each chunk is from a single reference -- fire up meanIpd func on the current reference
self.meanIpdFunc = self.ipdModel.predictIpdFunc(reference)
# Get the cognate base at a given position
self.cognateBaseFunc = self.ipdModel.cognateBaseFunc(reference)
self.refId = reference
self.sequence = self.ipdModel.getReferenceWindow(self.refId, 0, start, end)
# Compute the data for this chunk
if self.options.identify:
# If we are attempting to identify modifications, get the raw data for a slightly expanded window
# then do the decoding, then weave the modification results back into the main results
padStart = start - 8
padEnd = end + 8
perSiteResults = self._summarizeReferenceRegion((padStart, padEnd), self.options.methylFraction, self.options.identify)
if self.options.useLDA:
# FIXME: add on a column "Ca5C" containing LDA score for each C-residue site
# Below is an example of how to use an alternative, the BasicLdaEnricher, which does not use the positive control model
# PositiveControlEnricher currently uses a logistic regression model trained using SMRTportal job 65203 (native E. coli)
# lda = BasicLdaEnricher( self.ipdModel.gbmModel, self.sequence, perSiteResults, self.options.identify, self.options.modsToCall )
lda = PositiveControlEnricher( self.ipdModel.gbmModel, self.sequence, perSiteResults )
perSiteResults = lda.callEnricherFunction( perSiteResults )
mods = self._decodePositiveControl(perSiteResults, (start, end))
finalCalls = []
# Weave together results
for strand in [0, 1]:
strandSign = 1 if strand == 0 else -1
siteDict = dict((x['tpl'], x) for x in perSiteResults if start <= x['tpl'] < end and x['strand'] == strand)
modDict = dict((x['tpl'], x) for x in mods if start <= x['tpl'] < end and x['strand'] == strand)
# Go through the modifications - add tags for identified mods to per-site stats
# add a 'offTarget' tag to the off target peaks.
for (pos, mod) in modDict.items():
# Only convert to positive control call if we actually have enough
# coverage on the cognate base!
if siteDict.has_key(mod['tpl']):
# Copy mod identification data
siteDict[mod['tpl']]['modificationScore'] = mod['QMod']
siteDict[mod['tpl']]['modification'] = mod['modification']
if self.options.methylFraction and mod.has_key(FRAC):
siteDict[mod['tpl']][FRAC] = mod[FRAC]
siteDict[mod['tpl']][FRAClow] = mod[FRAClow]
siteDict[mod['tpl']][FRACup] = mod[FRACup]
if mod.has_key('Mask'):
# The decoder should supply the off-target peak mask
mask = mod['Mask']
mask.append(0) # make sure we always mask the cognate position
else:
# If the decoder doesn't supply a mask - use a hard-coded version
# FIXME - this branch is deprecated
mask = ModificationPeakMask[mod['modification']]
# Mask out neighbor peaks that may have been caused by this mod
for offset in mask:
shadowPos = mod['tpl'] + strandSign * offset
if siteDict.has_key(shadowPos):
siteDict[shadowPos]['offTargetPeak'] = True
finalCalls.extend(siteDict.values())
# Sort by template position
finalCalls.sort(key = lambda x: x['tpl'])
return finalCalls
else:
if self.options.smBaseMod:
result = self._summarizeMolecule(smId, targetBounds, self.options.methylFraction, self.options.identify)
else:
result = self._summarizeReferenceRegion(targetBounds, self.options.methylFraction, self.options.identify)
if self.options.useLDA and self.controlCmpH5 is None:
# FIXME: add on a column "Ca5C" containing LDA score for each C-residue site
# lda = BasicLdaEnricher(self.ipdModel.gbmModel, self.sequence, result, self.options.identify)
lda = PositiveControlEnricher( self.ipdModel.gbmModel, self.sequence, result )
results = lda.callEnricherFunction( result )
if self.options.smBaseMod:
pass
else:
result.sort(key = lambda x: x['tpl'])
return result
