def consensusForAlignments(refWindow, refSequence, alns, quiverConfig):
"""
Call consensus on this interval---without subdividing the interval
further.
Testable!
Clipping has already been done!
"""
_, refStart, refEnd = refWindow
# Compute the POA consensus, which is our initial guess, and
# should typically be > 99.5% accurate
fwdSequences = [
a.read(orientation="genomic", aligned=False) for a in alns
if a.spansReferenceRange(refStart, refEnd)
]
assert len(fwdSequences) >= quiverConfig.minPoaCoverage
try:
p = cc.PoaConsensus.FindConsensus(
fwdSequences[:quiverConfig.maxPoaCoverage])
except:
logging.info("%s: POA could not be generated" % (refWindow, ))
return QuiverConsensus.noCallConsensus(
quiverConfig.noEvidenceConsensus, refWindow, refSequence)
ga = cc.Align(refSequence, p.Sequence())
numPoaVariants = ga.Errors()
poaCss = p.Sequence()
# Extract reads into ConsensusCore-compatible objects, and map them into the
# coordinates relative to the POA consensus
mappedReads = [
quiverConfig.extractMappedRead(aln, refStart) for aln in alns
]
queryPositions = cc.TargetToQueryPositions(ga)
mappedReads = [lifted(queryPositions, mr) for mr in mappedReads]
# Load the mapped reads into the mutation scorer, and iterate
# until convergence.
configTbl = quiverConfig.ccQuiverConfigTbl
mms = cc.SparseSseQvMultiReadMutationScorer(configTbl, poaCss)
for mr in mappedReads:
mms.AddRead(mr)
# Iterate until covergence
_, quiverConverged = refineConsensus(mms, quiverConfig)
if quiverConverged:
if quiverConfig.refineDinucleotideRepeats:
refineDinucleotideRepeats(mms)
quiverCss = mms.Template()
if quiverConfig.computeConfidence:
confidence = consensusConfidence(mms)
else:
confidence = np.zeros(shape=len(quiverCss), dtype=int)
return QuiverConsensus(refWindow, quiverCss, confidence, mms)
else:
logging.info("%s: Quiver did not converge to MLE" % (refWindow, ))
return QuiverConsensus.noCallConsensus(
quiverConfig.noEvidenceConsensus, refWindow, refSequence)
def consensusForAlignments(refWindow, refSequence, alns, quiverConfig):
"""
Call consensus on this interval---without subdividing the interval
further.
Testable!
Clipping has already been done!
"""
_, refStart, refEnd = refWindow
# Compute the POA consensus, which is our initial guess, and
# should typically be > 99.5% accurate
fwdSequences = [ a.read(orientation="genomic", aligned=False)
for a in alns
if a.spansReferenceRange(refStart, refEnd) ]
assert len(fwdSequences) >= quiverConfig.minPoaCoverage
try:
p = cc.PoaConsensus.FindConsensus(fwdSequences[:quiverConfig.maxPoaCoverage])
except:
logging.info("%s: POA could not be generated" % (refWindow,))
return QuiverConsensus.noCallConsensus(quiverConfig.noEvidenceConsensus,
refWindow, refSequence)
ga = cc.Align(refSequence, p.Sequence)
numPoaVariants = ga.Errors()
poaCss = p.Sequence
# Extract reads into ConsensusCore-compatible objects, and map them into the
# coordinates relative to the POA consensus
mappedReads = [ quiverConfig.extractMappedRead(aln, refStart) for aln in alns ]
queryPositions = cc.TargetToQueryPositions(ga)
mappedReads = [ lifted(queryPositions, mr) for mr in mappedReads ]
# Load the mapped reads into the mutation scorer, and iterate
# until convergence.
configTbl = quiverConfig.ccQuiverConfigTbl
mms = cc.SparseSseQvMultiReadMutationScorer(configTbl, poaCss)
for mr in mappedReads:
mms.AddRead(mr)
# Iterate until covergence
_, quiverConverged = refineConsensus(mms, quiverConfig)
if quiverConverged:
if quiverConfig.refineDinucleotideRepeats:
refineDinucleotideRepeats(mms)
quiverCss = mms.Template()
if quiverConfig.computeConfidence:
confidence = consensusConfidence(mms)
else:
confidence = np.zeros(shape=len(quiverCss), dtype=int)
return QuiverConsensus(refWindow,
quiverCss,
confidence,
mms)
else:
logging.info("%s: Quiver did not converge to MLE" % (refWindow,))
return QuiverConsensus.noCallConsensus(quiverConfig.noEvidenceConsensus,
refWindow, refSequence)
def onChunk(self, workChunk):
referenceWindow = workChunk.window
refId, refStart, refEnd = referenceWindow
refSeqInWindow = reference.sequenceInWindow(referenceWindow)
# Quick cutout for no-coverage case
if not workChunk.hasCoverage:
noCallCss = QuiverConsensus.noCallConsensus(self.quiverConfig.noEvidenceConsensus,
referenceWindow, refSeqInWindow)
return (referenceWindow, (noCallCss, []))
# General case
eWindow = reference.enlargedReferenceWindow(referenceWindow,
options.referenceChunkOverlap)
_, eStart, eEnd = eWindow
# We call consensus on the enlarged window and then map back
# to the reference and clip the consensus at the implied
# bounds. This seems to be more reliable thank cutting the
# consensus bluntly
refContig = reference.byName[refId].sequence
refSequenceInEnlargedWindow = refContig[eStart:eEnd]
#
# Get the consensus for the enlarged window.
#
css_, variants_ = \
consensusAndVariantsForWindow(self._inAlnFile, eWindow,
refContig, options.coverage, self.quiverConfig)
#
# Restrict the consensus and variants to the reference window.
#
ga = cc.Align(refSequenceInEnlargedWindow, css_.sequence)
targetPositions = cc.TargetToQueryPositions(ga)
cssStart = targetPositions[refStart-eStart]
cssEnd = targetPositions[refEnd-eStart]
cssSequence = css_.sequence[cssStart:cssEnd]
cssQv = css_.confidence[cssStart:cssEnd]
variants = [ v for v in variants_
if refStart <= v.refStart < refEnd ]
consensusObj = Consensus(referenceWindow,
cssSequence,
cssQv)
return (referenceWindow, (consensusObj, variants))
def onChunk(self, workChunk):
referenceWindow = workChunk.window
refId, refStart, refEnd = referenceWindow
refSeqInWindow = reference.sequenceInWindow(referenceWindow)
# Quick cutout for no-coverage case
if not workChunk.hasCoverage:
noCallCss = QuiverConsensus.noCallConsensus(self.quiverConfig.noEvidenceConsensus,
referenceWindow, refSeqInWindow)
return (referenceWindow, (noCallCss, []))
# General case
eWindow = reference.enlargedReferenceWindow(referenceWindow,
options.referenceChunkOverlap)
_, eStart, eEnd = eWindow
# We call consensus on the enlarged window and then map back
# to the reference and clip the consensus at the implied
# bounds. This seems to be more reliable thank cutting the
# consensus bluntly
refContig = reference.byName[refId].sequence
refSequenceInEnlargedWindow = refContig[eStart:eEnd]
#
# Get the consensus for the enlarged window.
#
css_, variants_ = \
consensusAndVariantsForWindow(self._inAlnFile, eWindow,
refContig, options.coverage, self.quiverConfig)
#
# Restrict the consensus and variants to the reference window.
#
ga = cc.Align(refSequenceInEnlargedWindow, css_.sequence)
targetPositions = cc.TargetToQueryPositions(ga)
cssStart = targetPositions[refStart-eStart]
cssEnd = targetPositions[refEnd-eStart]
cssSequence = css_.sequence[cssStart:cssEnd]
cssQv = css_.confidence[cssStart:cssEnd]
variants = [ v for v in variants_
if refStart <= v.refStart < refEnd ]
consensusObj = Consensus(referenceWindow,
cssSequence,
cssQv)
return (referenceWindow, (consensusObj, variants))
def consensusAndVariantsForWindow(cmpH5, refWindow, referenceContig,
depthLimit, quiverConfig):
"""
High-level routine for calling the consensus for a
window of the genome given an alignment file.
Identifies the coverage contours of the window in order to
identify subintervals where a good consensus can be called.
Creates the desired "no evidence consensus" where there is
inadequate coverage.
"""
winId, winStart, winEnd = refWindow
logging.info("Quiver operating on %s" %
reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for quiver
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(cmpH5, refWindow,
depthLimit=20000,
minMapQV=quiverConfig.minMapQV,
strategy="long-and-strand-balanced",
stratum=options.readStratum,
barcode=options.barcode)
starts = np.fromiter((hit.tStart for hit in alnHits), np.int)
ends = np.fromiter((hit.tEnd for hit in alnHits), np.int)
intervals = kSpannedIntervals(refWindow, quiverConfig.minPoaCoverage,
starts, ends, minLength=10)
coverageGaps = holes(refWindow, intervals)
allIntervals = sorted(intervals + coverageGaps)
if len(allIntervals) > 1:
logging.info("Usable coverage in %s: %r" %
(reference.windowToString(refWindow), intervals))
else:
allIntervals = [ (winStart, winEnd) ]
# 2) pull out the reads we will use for each interval
# 3) call consensusForAlignments on the interval
subConsensi = []
variants = []
for interval in allIntervals:
intStart, intEnd = interval
intRefSeq = referenceContig[intStart:intEnd]
subWin = subWindow(refWindow, interval)
windowRefSeq = referenceContig[intStart:intEnd]
alns = U.readsInWindow(cmpH5, subWin,
depthLimit=depthLimit,
minMapQV=quiverConfig.minMapQV,
strategy="long-and-strand-balanced",
stratum=options.readStratum,
barcode=options.barcode)
clippedAlns_ = [ aln.clippedTo(*interval) for aln in alns ]
clippedAlns = U.filterAlns(subWin, clippedAlns_, quiverConfig)
if len([ a for a in clippedAlns
if a.spansReferenceRange(*interval) ]) >= quiverConfig.minPoaCoverage:
logging.debug("%s: Reads being used: %s" %
(reference.windowToString(subWin),
" ".join([str(hit.readName) for hit in alns])))
css = U.consensusForAlignments(subWin,
intRefSeq,
clippedAlns,
quiverConfig)
siteCoverage = U.coverageInWindow(subWin, alns)
if options.diploid:
variants_ = diploid.variantsFromConsensus(subWin, windowRefSeq,
css.sequence, css.confidence, siteCoverage,
options.aligner,
css.mms)
else:
variants_ = U.variantsFromConsensus(subWin, windowRefSeq,
css.sequence, css.confidence, siteCoverage,
options.aligner,
mms=None)
filteredVars = filterVariants(options.minCoverage,
options.minConfidence,
variants_)
# Annotate?
if options.annotateGFF:
annotateVariants(filteredVars, clippedAlns)
variants += filteredVars
# Dump?
shouldDumpEvidence = \
((options.dumpEvidence == "all") or
(options.dumpEvidence == "variants") and (len(variants) > 0))
if shouldDumpEvidence:
dumpEvidence(options.evidenceDirectory,
subWin, windowRefSeq,
clippedAlns, css)
else:
css = QuiverConsensus.noCallConsensus(quiverConfig.noEvidenceConsensus,
subWin, intRefSeq)
subConsensi.append(css)
# 4) glue the subwindow consensus objects together to form the
# full window consensus
css = join(subConsensi)
# 5) Return
return css, variants
def consensusAndVariantsForWindow(cmpH5, refWindow, referenceContig,
depthLimit, quiverConfig):
"""
High-level routine for calling the consensus for a
window of the genome given an alignment file.
Identifies the coverage contours of the window in order to
identify subintervals where a good consensus can be called.
Creates the desired "no evidence consensus" where there is
inadequate coverage.
"""
winId, winStart, winEnd = refWindow
logging.info("Quiver operating on %s" %
reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for quiver
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(cmpH5, refWindow,
depthLimit=20000,
minMapQV=quiverConfig.minMapQV,
strategy="long-and-strand-balanced",
stratum=options.readStratum,
barcode=options.barcode)
starts = np.fromiter((hit.tStart for hit in alnHits), np.int)
ends = np.fromiter((hit.tEnd for hit in alnHits), np.int)
intervals = kSpannedIntervals(refWindow, quiverConfig.minPoaCoverage,
starts, ends, minLength=10)
coverageGaps = holes(refWindow, intervals)
allIntervals = sorted(intervals + coverageGaps)
if len(allIntervals) > 1:
logging.info("Usable coverage in %s: %r" %
(reference.windowToString(refWindow), intervals))
else:
allIntervals = [ (winStart, winEnd) ]
# 2) pull out the reads we will use for each interval
# 3) call consensusForAlignments on the interval
subConsensi = []
variants = []
for interval in allIntervals:
intStart, intEnd = interval
intRefSeq = referenceContig[intStart:intEnd]
subWin = subWindow(refWindow, interval)
windowRefSeq = referenceContig[intStart:intEnd]
alns = U.readsInWindow(cmpH5, subWin,
depthLimit=depthLimit,
minMapQV=quiverConfig.minMapQV,
strategy="long-and-strand-balanced",
stratum=options.readStratum,
barcode=options.barcode)
clippedAlns_ = [ aln.clippedTo(*interval) for aln in alns ]
clippedAlns = U.filterAlns(subWin, clippedAlns_, quiverConfig)
if len([ a for a in clippedAlns
if a.spansReferenceRange(*interval) ]) >= quiverConfig.minPoaCoverage:
logging.debug("%s: Reads being used: %s" %
(reference.windowToString(subWin),
" ".join([str(hit.readName) for hit in alns])))
css = U.consensusForAlignments(subWin,
intRefSeq,
clippedAlns,
quiverConfig)
siteCoverage = U.coverageInWindow(subWin, alns)
if options.diploid:
variants_ = diploid.variantsFromConsensus(subWin, windowRefSeq,
css.sequence, css.confidence, siteCoverage,
options.aligner,
css.mms)
else:
variants_ = U.variantsFromConsensus(subWin, windowRefSeq,
css.sequence, css.confidence, siteCoverage,
options.aligner,
mms=None)
filteredVars = filterVariants(options.minCoverage,
options.minConfidence,
variants_)
# Annotate?
if options.annotateGFF:
annotateVariants(filteredVars, clippedAlns)
variants += filteredVars
# Dump?
shouldDumpEvidence = \
((options.dumpEvidence == "all") or
(options.dumpEvidence == "variants") and (len(variants) > 0))
if shouldDumpEvidence:
dumpEvidence(options.evidenceDirectory,
subWin, windowRefSeq,
clippedAlns, css)
else:
css = QuiverConsensus.noCallConsensus(quiverConfig.noEvidenceConsensus,
subWin, intRefSeq)
subConsensi.append(css)
# 4) glue the subwindow consensus objects together to form the
# full window consensus
css = join(subConsensi)
# 5) Return
return css, variants
