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(alnFile, refWindow, referenceContig,
depthLimit, arrowConfig):
"""
High-level routine for calling the consensus for a
window of the genome given a cmp.h5.
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("Arrow operating on %s" %
reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for arrow
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(alnFile, refWindow,
depthLimit=20000,
minMapQV=arrowConfig.minMapQV,
strategy="longest",
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, arrowConfig.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(alnFile, subWin,
depthLimit=depthLimit,
minMapQV=arrowConfig.minMapQV,
strategy="longest",
stratum=options.readStratum,
barcode=options.barcode)
clippedAlns_ = [ aln.clippedTo(*interval) for aln in alns ]
clippedAlns = U.filterAlns(subWin, clippedAlns_, arrowConfig)
if len([ a for a in clippedAlns
if a.spansReferenceRange(*interval) ]) >= arrowConfig.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,
arrowConfig)
siteCoverage = U.coverageInWindow(subWin, alns)
variants_ = U.variantsFromConsensus(subWin, windowRefSeq,
css.sequence, css.confidence, siteCoverage,
options.aligner,
ai=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:
logging.info("Arrow does not yet support --dumpEvidence")
# dumpEvidence(options.evidenceDirectory,
# subWin, windowRefSeq,
# clippedAlns, css)
else:
css = ArrowConsensus.noCallConsensus(arrowConfig.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(alnFile, refWindow, referenceContig,
depthLimit, arrowConfig):
"""
High-level routine for calling the consensus for a
window of the genome given a BAM 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("Arrow operating on %s" % reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for arrow
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(alnFile,
refWindow,
depthLimit=20000,
minMapQV=arrowConfig.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,
arrowConfig.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(alnFile,
subWin,
depthLimit=depthLimit,
minMapQV=arrowConfig.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_, arrowConfig)
if len([a for a in clippedAlns if a.spansReferenceRange(*interval)
]) >= arrowConfig.minPoaCoverage:
logging.debug("%s: Reads being used: %s" %
(reference.windowToString(subWin), " ".join(
[str(hit.readName) for hit in alns])))
alnsUsed = [] if options.reportEffectiveCoverage else None
css = U.consensusForAlignments(subWin,
intRefSeq,
clippedAlns,
arrowConfig,
alnsUsed=alnsUsed)
# Tabulate the coverage implied by these alignments, as
# well as the post-filtering ("effective") coverage
siteCoverage = U.coverageInWindow(subWin, alns)
effectiveSiteCoverage = U.coverageInWindow(
subWin, alnsUsed) if options.reportEffectiveCoverage else None
variants_, newPureCss = U.variantsFromConsensus(
subWin,
windowRefSeq,
css.sequence,
css.confidence,
siteCoverage,
effectiveSiteCoverage,
options.aligner,
ai=None,
diploid=arrowConfig.polishDiploid)
# Annotate?
if options.annotateGFF:
annotateVariants(variants_, clippedAlns)
variants += variants_
# The nascent consensus sequence might contain ambiguous bases, these
# need to be removed as software in the wild cannot deal with such
# characters and we only use IUPAC for *internal* bookkeeping.
if arrowConfig.polishDiploid:
css.sequence = newPureCss
else:
css = ArrowConsensus.noCallConsensus(
arrowConfig.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(alnFile, refWindow, referenceContig,
depthLimit, arrowConfig):
"""
High-level routine for calling the consensus for a
window of the genome given a cmp.h5.
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("Arrow operating on %s" % reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for arrow
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(alnFile,
refWindow,
depthLimit=20000,
minMapQV=arrowConfig.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,
arrowConfig.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(alnFile,
subWin,
depthLimit=depthLimit,
minMapQV=arrowConfig.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_, arrowConfig)
if len([a for a in clippedAlns if a.spansReferenceRange(*interval)
]) >= arrowConfig.minPoaCoverage:
logging.debug("%s: Reads being used: %s" %
(reference.windowToString(subWin), " ".join(
[str(hit.readName) for hit in alns])))
alnsUsed = [] if options.reportEffectiveCoverage else None
css = U.consensusForAlignments(subWin,
intRefSeq,
clippedAlns,
arrowConfig,
alnsUsed=alnsUsed)
# Tabulate the coverage implied by these alignments, as
# well as the post-filtering ("effective") coverage
siteCoverage = U.coverageInWindow(subWin, alns)
effectiveSiteCoverage = U.coverageInWindow(
subWin, alnsUsed) if options.reportEffectiveCoverage else None
variants_ = U.variantsFromConsensus(subWin,
windowRefSeq,
css.sequence,
css.confidence,
siteCoverage,
effectiveSiteCoverage,
options.aligner,
ai=None)
filteredVars = filterVariants(options.minCoverage,
options.minConfidence, variants_)
# Annotate?
if options.annotateGFF:
annotateVariants(filteredVars, clippedAlns)
variants += filteredVars
# Dump?
maybeDumpEvidence = \
((options.dumpEvidence == "all") or
(options.dumpEvidence == "outliers") or
(options.dumpEvidence == "variants") and (len(variants) > 0))
if maybeDumpEvidence:
refId, refStart, refEnd = subWin
refName = reference.idToName(refId)
windowDirectory = os.path.join(options.evidenceDirectory,
refName,
"%d-%d" % (refStart, refEnd))
ev = ArrowEvidence.fromConsensus(css)
if options.dumpEvidence != "outliers":
ev.save(windowDirectory)
elif (np.max(ev.delta) > 20):
# Mathematically I don't think we should be seeing
# deltas > 6 in magnitude, but let's just restrict
# attention to truly bonkers outliers.
ev.save(windowDirectory)
else:
css = ArrowConsensus.noCallConsensus(
arrowConfig.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(alnFile, refWindow, referenceContig,
depthLimit, arrowConfig):
"""
High-level routine for calling the consensus for a
window of the genome given a cmp.h5.
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("Arrow operating on %s" %
reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for arrow
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(alnFile, refWindow,
depthLimit=20000,
minMapQV=arrowConfig.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, arrowConfig.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(alnFile, subWin,
depthLimit=depthLimit,
minMapQV=arrowConfig.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_, arrowConfig)
if len([ a for a in clippedAlns
if a.spansReferenceRange(*interval) ]) >= arrowConfig.minPoaCoverage:
logging.debug("%s: Reads being used: %s" %
(reference.windowToString(subWin),
" ".join([str(hit.readName) for hit in alns])))
alnsUsed = [] if options.reportEffectiveCoverage else None
css = U.consensusForAlignments(subWin,
intRefSeq,
clippedAlns,
arrowConfig,
alnsUsed=alnsUsed)
# Tabulate the coverage implied by these alignments, as
# well as the post-filtering ("effective") coverage
siteCoverage = U.coverageInWindow(subWin, alns)
effectiveSiteCoverage = U.coverageInWindow(subWin, alnsUsed) if options.reportEffectiveCoverage else None
variants_ = U.variantsFromConsensus(subWin, windowRefSeq,
css.sequence, css.confidence, siteCoverage, effectiveSiteCoverage,
options.aligner,
ai=None)
filteredVars = filterVariants(options.minCoverage,
options.minConfidence,
variants_)
# Annotate?
if options.annotateGFF:
annotateVariants(filteredVars, clippedAlns)
variants += filteredVars
# Dump?
maybeDumpEvidence = \
((options.dumpEvidence == "all") or
(options.dumpEvidence == "outliers") or
(options.dumpEvidence == "variants") and (len(variants) > 0))
if maybeDumpEvidence:
refId, refStart, refEnd = subWin
refName = reference.idToName(refId)
windowDirectory = os.path.join(
options.evidenceDirectory,
refName,
"%d-%d" % (refStart, refEnd))
ev = ArrowEvidence.fromConsensus(css)
if options.dumpEvidence != "outliers":
ev.save(windowDirectory)
elif (np.max(ev.delta) > 20):
# Mathematically I don't think we should be seeing
# deltas > 6 in magnitude, but let's just restrict
# attention to truly bonkers outliers.
ev.save(windowDirectory)
else:
css = ArrowConsensus.noCallConsensus(arrowConfig.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(alnFile, refWindow, referenceContig,
depthLimit, arrowConfig):
"""
High-level routine for calling the consensus for a
window of the genome given a BAM 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("Arrow operating on %s" %
reference.windowToString(refWindow))
if options.fancyChunking:
# 1) identify the intervals with adequate coverage for arrow
# consensus; restrict to intervals of length > 10
alnHits = U.readsInWindow(alnFile, refWindow,
depthLimit=20000,
minMapQV=arrowConfig.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, arrowConfig.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(alnFile, subWin,
depthLimit=depthLimit,
minMapQV=arrowConfig.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_, arrowConfig)
if len([ a for a in clippedAlns
if a.spansReferenceRange(*interval) ]) >= arrowConfig.minPoaCoverage:
logging.debug("%s: Reads being used: %s" %
(reference.windowToString(subWin),
" ".join([str(hit.readName) for hit in alns])))
alnsUsed = [] if options.reportEffectiveCoverage else None
css = U.consensusForAlignments(subWin,
intRefSeq,
clippedAlns,
arrowConfig,
alnsUsed=alnsUsed)
# Tabulate the coverage implied by these alignments, as
# well as the post-filtering ("effective") coverage
siteCoverage = U.coverageInWindow(subWin, alns)
effectiveSiteCoverage = U.coverageInWindow(subWin, alnsUsed) if options.reportEffectiveCoverage else None
variants_, newPureCss = U.variantsFromConsensus(subWin, windowRefSeq, css.sequence, css.confidence,
siteCoverage, effectiveSiteCoverage,
options.aligner, ai=None,
diploid=arrowConfig.polishDiploid)
# Annotate?
if options.annotateGFF:
annotateVariants(variants_, clippedAlns)
variants += variants_
# The nascent consensus sequence might contain ambiguous bases, these
# need to be removed as software in the wild cannot deal with such
# characters and we only use IUPAC for *internal* bookkeeping.
if arrowConfig.polishDiploid:
css.sequence = newPureCss
else:
css = ArrowConsensus.noCallConsensus(arrowConfig.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 getReads(cmpH5,
reference,
interval,
paddedTemplateWidth,
depthLimit,
real_quiver=False):
minMapQV = 10
minPoaCoverage = 3
maxPoaCoverage = 11
mutationSeparation = 10
mutationNeighborhood = 20
maxIterations = 20
refineDinucleotideRepeats = True
noEvidenceConsensus = "nocall"
computeConfidence = True
readStumpinessThreshold = 0.1
refId = [x for x in reference.enumerateIds()][0]
refSeq = reference.byId[refId].sequence
refWindow = (refId, 0, reference.byId[refId].length)
intStart, intEnd = interval
subWin = subWindow(refWindow, interval)
windowRefSeq = refSeq[intStart:intEnd]
rows = readsInWindow(cmpH5,
subWin,
depthLimit=depthLimit,
minMapQV=minMapQV,
strategy="longest",
stratum=None,
barcode=None)
#print([cmpH5[row].alignedLength for row in rows if cmpH5[row].spansReferenceRange(intStart, intEnd)])
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 <= paddedTemplateWidth - 7
]
clippedAlns = filterAlns(subWin, clippedAlns__, readStumpinessThreshold)
# 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 clippedAlns
]
p = cc.PoaConsensus.FindConsensus(fwdSequences[:maxPoaCoverage])
template = p.Sequence()
tmplSeq = np.zeros((paddedTemplateWidth), dtype=np.uint8)
tmplOrds = map(ord, template)
tmplSeq[:len(tmplOrds)] = tmplOrds
#read pos y, read x
readSeqs = np.zeros((paddedTemplateWidth, len(clippedAlns)),
dtype=np.uint8)
for i in xrange(len(clippedAlns)):
alnOrds = map(ord, fwdSequences[i])
readSeqs[:len(alnOrds), i] = alnOrds
#uint8
#metric z, read pos y, read x
qvInfo = np.zeros((8, paddedTemplateWidth, len(clippedAlns)),
dtype=np.uint8)
for i in xrange(len(clippedAlns)):
qvInfo[0, :clippedAlns[i].readLength,
i] = clippedAlns[i].InsertionQV(orientation="genomic",
aligned=False)
qvInfo[1, :clippedAlns[i].readLength,
i] = clippedAlns[i].MergeQV(orientation="genomic",
aligned=False)
qvInfo[2, :clippedAlns[i].readLength,
i] = clippedAlns[i].DeletionQV(orientation="genomic",
aligned=False)
qvInfo[3, :clippedAlns[i].readLength,
i] = clippedAlns[i].DeletionTag(orientation="genomic",
aligned=False)
qvInfo[4, :clippedAlns[i].readLength,
i] = clippedAlns[i].SubstitutionQV(orientation="genomic",
aligned=False)
if real_quiver:
return template, len(tmplOrds), fwdSequences, qvInfo
else:
return tmplSeq, len(tmplOrds), readSeqs, qvInfo
def getReads(cmpH5, reference, interval, paddedTemplateWidth, depthLimit, real_quiver=False):
minMapQV = 10
minPoaCoverage = 3
maxPoaCoverage = 11
mutationSeparation = 10
mutationNeighborhood = 20
maxIterations = 20
refineDinucleotideRepeats = True
noEvidenceConsensus = "nocall"
computeConfidence = True
readStumpinessThreshold = 0.1
refId = [x for x in reference.enumerateIds()][0]
refSeq = reference.byId[refId].sequence
refWindow = (refId, 0, reference.byId[refId].length)
intStart, intEnd = interval
subWin = subWindow(refWindow, interval)
windowRefSeq = refSeq[intStart:intEnd]
rows = readsInWindow(cmpH5, subWin,
depthLimit = depthLimit,
minMapQV = minMapQV,
strategy = "longest",
stratum = None,
barcode = None)
#print([cmpH5[row].alignedLength for row in rows if cmpH5[row].spansReferenceRange(intStart, intEnd)])
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 <= paddedTemplateWidth - 7]
clippedAlns = filterAlns(subWin, clippedAlns__, readStumpinessThreshold)
# 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 clippedAlns]
p = cc.PoaConsensus.FindConsensus(fwdSequences[:maxPoaCoverage])
template = p.Sequence()
tmplSeq = np.zeros((paddedTemplateWidth), dtype=np.uint8)
tmplOrds = map(ord, template)
tmplSeq[:len(tmplOrds)] = tmplOrds
#read pos y, read x
readSeqs = np.zeros((paddedTemplateWidth, len(clippedAlns)), dtype=np.uint8)
for i in xrange(len(clippedAlns)):
alnOrds = map(ord, fwdSequences[i])
readSeqs[:len(alnOrds), i] = alnOrds
#uint8
#metric z, read pos y, read x
qvInfo = np.zeros((8, paddedTemplateWidth, len(clippedAlns)), dtype=np.uint8)
for i in xrange(len(clippedAlns)):
qvInfo[0, :clippedAlns[i].readLength, i] = clippedAlns[i].InsertionQV(orientation="genomic", aligned=False)
qvInfo[1, :clippedAlns[i].readLength, i] = clippedAlns[i].MergeQV(orientation="genomic", aligned=False)
qvInfo[2, :clippedAlns[i].readLength, i] = clippedAlns[i].DeletionQV(orientation="genomic", aligned=False)
qvInfo[3, :clippedAlns[i].readLength, i] = clippedAlns[i].DeletionTag(orientation="genomic", aligned=False)
qvInfo[4, :clippedAlns[i].readLength, i] = clippedAlns[i].SubstitutionQV(orientation="genomic", aligned=False)
if real_quiver:
return template, len(tmplOrds), fwdSequences, qvInfo
else:
return tmplSeq, len(tmplOrds), readSeqs, qvInfo
