/**
* Helper function to add the read underneath a pileup element to the map
*
* @param p Pileup element
* @param a Corresponding allele
* @param likelihood Allele likelihood
*/
public void add(PileupElement p, Allele a, Double likelihood) {
if (p == null) throw new IllegalArgumentException("Pileup element cannot be null");
if (p.getRead() == null)
throw new IllegalArgumentException("Read underlying pileup element cannot be null");
if (a == null) throw new IllegalArgumentException("Allele for add() cannot be null");
add(p.getRead(), a, likelihood);
}
/**
* Computes an allele biased version of the given pileup
*
* @param pileup the original pileup
* @param downsamplingFraction the fraction of total reads to remove per allele
* @return allele biased pileup
*/
public static ReadBackedPileup createAlleleBiasedBasePileup(
final ReadBackedPileup pileup, final double downsamplingFraction) {
// special case removal of all or no reads
if (downsamplingFraction <= 0.0) return pileup;
if (downsamplingFraction >= 1.0)
return new ReadBackedPileupImpl(pileup.getLocation(), new ArrayList<PileupElement>());
final PileupElementList[] alleleStratifiedElements = new PileupElementList[4];
for (int i = 0; i < 4; i++) alleleStratifiedElements[i] = new PileupElementList();
// start by stratifying the reads by the alleles they represent at this position
for (final PileupElement pe : pileup) {
final int baseIndex = BaseUtils.simpleBaseToBaseIndex(pe.getBase());
if (baseIndex != -1) alleleStratifiedElements[baseIndex].add(pe);
}
// make a listing of allele counts and calculate the total count
final int[] alleleCounts = calculateAlleleCounts(alleleStratifiedElements);
final int totalAlleleCount = (int) MathUtils.sum(alleleCounts);
// do smart down-sampling
final int numReadsToRemove = (int) (totalAlleleCount * downsamplingFraction); // floor
final int[] targetAlleleCounts = runSmartDownsampling(alleleCounts, numReadsToRemove);
final HashSet<PileupElement> readsToRemove = new HashSet<PileupElement>(numReadsToRemove);
for (int i = 0; i < 4; i++) {
final PileupElementList alleleList = alleleStratifiedElements[i];
// if we don't need to remove any reads, then don't
if (alleleCounts[i] > targetAlleleCounts[i])
readsToRemove.addAll(
downsampleElements(
alleleList, alleleCounts[i], alleleCounts[i] - targetAlleleCounts[i]));
}
// we need to keep the reads sorted because the FragmentUtils code will expect them in
// coordinate order and will fail otherwise
final List<PileupElement> readsToKeep =
new ArrayList<PileupElement>(totalAlleleCount - numReadsToRemove);
for (final PileupElement pe : pileup) {
if (!readsToRemove.contains(pe)) {
readsToKeep.add(pe);
}
}
return new ReadBackedPileupImpl(
pileup.getLocation(), new ArrayList<PileupElement>(readsToKeep));
}
@Override
public Map<String, Object> annotate(
final RefMetaDataTracker tracker,
final AnnotatorCompatible walker,
final ReferenceContext ref,
final Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc,
final Map<String, PerReadAlleleLikelihoodMap> stratifiedPerReadAlleleLikelihoodMap) {
// Can only call from UnifiedGenotyper
if (!(walker instanceof UnifiedGenotyper)) {
if (!walkerIdentityCheckWarningLogged) {
if (walker != null)
logger.warn(
"Annotation will not be calculated, must be called from UnifiedGenotyper, not "
+ walker.getClass().getName());
else logger.warn("Annotation will not be calculated, must be called from UnifiedGenotyper");
walkerIdentityCheckWarningLogged = true;
}
return null;
}
if (stratifiedContexts.isEmpty()) return null;
// not meaningful when we're at an indel location: deletions that start at location N are by
// definition called at the position N-1, and at position N-1
// there are no informative deletions in the pileup
if (!vc.isSNP()) return null;
int deletions = 0;
int depth = 0;
for (Map.Entry<String, AlignmentContext> sample : stratifiedContexts.entrySet()) {
for (final PileupElement p : sample.getValue().getBasePileup()) {
depth++;
if (p.isDeletion()) deletions++;
}
}
Map<String, Object> map = new HashMap<>();
map.put(
getKeyNames().get(0),
String.format("%.2f", depth == 0 ? 0.0 : (double) deletions / (double) depth));
return map;
}
@Override
public CallableBaseState map(
RefMetaDataTracker tracker, ReferenceContext ref, AlignmentContext context) {
CalledState state;
if (BaseUtils.isNBase(ref.getBase())) {
state = CalledState.REF_N;
} else {
// count up the depths of all and QC+ bases
int rawDepth = 0, QCDepth = 0, lowMAPQDepth = 0;
for (PileupElement e : context.getBasePileup()) {
rawDepth++;
if (e.getMappingQual() <= maxLowMAPQ) lowMAPQDepth++;
if (e.getMappingQual() >= minMappingQuality
&& (e.getQual() >= minBaseQuality || e.isDeletion())) {
QCDepth++;
}
}
// System.out.printf("%s rawdepth = %d QCDepth = %d lowMAPQ = %d%n", context.getLocation(),
// rawDepth, QCDepth, lowMAPQDepth);
if (rawDepth == 0) {
state = CalledState.NO_COVERAGE;
} else if (rawDepth >= minDepthLowMAPQ
&& MathUtils.ratio(lowMAPQDepth, rawDepth) >= maxLowMAPQFraction) {
state = CalledState.POOR_MAPPING_QUALITY;
} else if (QCDepth < minDepth) {
state = CalledState.LOW_COVERAGE;
} else if (rawDepth >= maxDepth && maxDepth != -1) {
state = CalledState.EXCESSIVE_COVERAGE;
} else {
state = CalledState.CALLABLE;
}
}
return new CallableBaseState(getToolkit().getGenomeLocParser(), context.getLocation(), state);
}
public Event map(RefMetaDataTracker tracker, ReferenceContext ref, AlignmentContext context) {
boolean hasIndel = false;
boolean hasInsertion = false;
boolean hasPointEvent = false;
int furthestStopPos = -1;
// look at the rods for indels or SNPs
if (tracker != null) {
for (VariantContext vc : tracker.getValues(known)) {
switch (vc.getType()) {
case INDEL:
hasIndel = true;
if (vc.isSimpleInsertion()) hasInsertion = true;
break;
case SNP:
hasPointEvent = true;
break;
case MIXED:
hasPointEvent = true;
hasIndel = true;
if (vc.isSimpleInsertion()) hasInsertion = true;
break;
default:
break;
}
if (hasIndel) furthestStopPos = vc.getEnd();
}
}
// look at the normal context to get deletions and positions with high entropy
final ReadBackedPileup pileup = context.getBasePileup();
int mismatchQualities = 0, totalQualities = 0;
final byte refBase = ref.getBase();
for (PileupElement p : pileup) {
// check the ends of the reads to see how far they extend
furthestStopPos = Math.max(furthestStopPos, p.getRead().getAlignmentEnd());
// is it a deletion or insertion?
if (p.isDeletion() || p.isBeforeInsertion()) {
hasIndel = true;
if (p.isBeforeInsertion()) hasInsertion = true;
}
// look for mismatches
else if (lookForMismatchEntropy) {
if (p.getBase() != refBase) mismatchQualities += p.getQual();
totalQualities += p.getQual();
}
}
// make sure we're supposed to look for high entropy
if (lookForMismatchEntropy
&& pileup.getNumberOfElements() >= minReadsAtLocus
&& (double) mismatchQualities / (double) totalQualities >= mismatchThreshold)
hasPointEvent = true;
// return null if no event occurred
if (!hasIndel && !hasPointEvent) return null;
// return null if we didn't find any usable reads/rods associated with the event
if (furthestStopPos == -1) return null;
GenomeLoc eventLoc = context.getLocation();
if (hasInsertion)
eventLoc =
getToolkit()
.getGenomeLocParser()
.createGenomeLoc(eventLoc.getContig(), eventLoc.getStart(), eventLoc.getStart() + 1);
EVENT_TYPE eventType =
(hasIndel
? (hasPointEvent ? EVENT_TYPE.BOTH : EVENT_TYPE.INDEL_EVENT)
: EVENT_TYPE.POINT_EVENT);
return new Event(eventLoc, furthestStopPos, eventType);
}
@Override
protected boolean isUsableBase(final PileupElement p) {
return super.isUsableBase(p) && p.getRead().getCigar() != null;
}
@Override
protected Double getElementForPileupElement(final PileupElement p) {
final int offset = AlignmentUtils.calcAlignmentByteArrayOffset(p.getRead().getCigar(), p, 0, 0);
return (double) AnnotationUtils.getFinalVariantReadPosition(p.getRead(), offset);
}
public Map<Allele, Double> getLikelihoodsAssociatedWithPileupElement(final PileupElement p) {
if (!likelihoodReadMap.containsKey(p.getRead())) return null;
return likelihoodReadMap.get(p.getRead());
}
/**
* Does the current map contain the key associated with a particular SAM record in pileup?
*
* @param p Pileup element
* @return true if the map contains pileup element, else false
*/
public boolean containsPileupElement(final PileupElement p) {
return likelihoodReadMap.containsKey(p.getRead());
}
@Override
protected Double getElementForPileupElement(final PileupElement p) {
return (double) p.getQual();
}