def run_real_quiver(cmpH5, quiverConfig, interval, depthLimit, refSeq, refWindow, seedConsensus):
intStart, intEnd = interval
subWin = subWindow(refWindow, interval)
windowRefSeq = refSeq[intStart:intEnd]
rows = readsInWindow(cmpH5, subWin,
depthLimit = depthLimit,
minMapQV = quiverConfig.minMapQV,
strategy = "longest",
stratum = None,
barcode = None)
spanningRows = [row for row in rows if cmpH5[row].spansReferenceRange(intStart, intEnd) ]
alns = cmpH5[spanningRows]
clippedAlns_ = [ aln.clippedTo(*interval) for aln in alns ]
clippedAlns__ = [ aln for aln in clippedAlns_ if aln.alignedLength <= 120]
clippedAlns = filterAlns(subWin, clippedAlns__, quiverConfig)
consensus = consensusForAlignmentsDisregardPOA(subWin, windowRefSeq, clippedAlns, quiverConfig, "A"*100)
print(str(consensus.sequence))
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