/**
* return a deep copy of this collection.
*
* @return a new GenomeLocSortedSet, identical to the current GenomeLocSortedSet.
*/
public GenomeLocSortedSet clone() {
GenomeLocSortedSet ret = new GenomeLocSortedSet(genomeLocParser);
for (GenomeLoc loc : this.mArray) {
// ensure a deep copy
ret.mArray.add(
genomeLocParser.createGenomeLoc(loc.getContig(), loc.getStart(), loc.getStop()));
}
return ret;
}
public GenomeLocSortedSet subtractRegions(GenomeLocSortedSet toRemoveSet) {
LinkedList<GenomeLoc> good = new LinkedList<GenomeLoc>();
Stack<GenomeLoc> toProcess = new Stack<GenomeLoc>();
Stack<GenomeLoc> toExclude = new Stack<GenomeLoc>();
// initialize the stacks
toProcess.addAll(mArray);
Collections.reverse(toProcess);
toExclude.addAll(toRemoveSet.mArray);
Collections.reverse(toExclude);
int i = 0;
while (!toProcess.empty()) { // while there's still stuff to process
if (toExclude.empty()) {
good.addAll(toProcess); // no more excludes, all the processing stuff is good
break;
}
GenomeLoc p = toProcess.peek();
GenomeLoc e = toExclude.peek();
if (p.overlapsP(e)) {
toProcess.pop();
for (GenomeLoc newP : p.subtract(e)) toProcess.push(newP);
} else if (p.compareContigs(e) < 0) {
good.add(toProcess.pop()); // p is now good
} else if (p.compareContigs(e) > 0) {
toExclude.pop(); // e can't effect anything
} else if (p.getStop() < e.getStart()) {
good.add(toProcess.pop()); // p stops before e starts, p is good
} else if (e.getStop() < p.getStart()) {
toExclude.pop(); // p starts after e stops, e is done
} else {
throw new ReviewedStingException("BUG: unexpected condition: p=" + p + ", e=" + e);
}
if (i++ % 10000 == 0) logger.debug("removeRegions operation: i = " + i);
}
return createSetFromList(genomeLocParser, good);
}
@Test
public void deleteSuperRegion() {
GenomeLoc e = genomeLocParser.createGenomeLoc(contigOneName, 10, 20);
GenomeLoc g = genomeLocParser.createGenomeLoc(contigOneName, 70, 100);
mSortedSet.add(g);
mSortedSet.addRegion(e);
assertTrue(mSortedSet.size() == 2);
// now delete a region
GenomeLoc d = genomeLocParser.createGenomeLoc(contigOneName, 15, 75);
mSortedSet = mSortedSet.subtractRegions(new GenomeLocSortedSet(genomeLocParser, d));
Iterator<GenomeLoc> iter = mSortedSet.iterator();
GenomeLoc loc = iter.next();
assertTrue(loc.getStart() == 10);
assertTrue(loc.getStop() == 14);
assertTrue(loc.getContigIndex() == 1);
loc = iter.next();
assertTrue(loc.getStart() == 76);
assertTrue(loc.getStop() == 100);
assertTrue(loc.getContigIndex() == 1);
}
@Test
public void deleteSomeByRegion() {
GenomeLoc e = genomeLocParser.createGenomeLoc(contigOneName, 1, 100);
mSortedSet.add(e);
for (int x = 1; x < 50; x++) {
GenomeLoc del = genomeLocParser.createGenomeLoc(contigOneName, x, x);
mSortedSet = mSortedSet.subtractRegions(new GenomeLocSortedSet(genomeLocParser, del));
}
assertTrue(!mSortedSet.isEmpty());
assertTrue(mSortedSet.size() == 1);
GenomeLoc loc = mSortedSet.iterator().next();
assertTrue(loc.getStop() == 100);
assertTrue(loc.getStart() == 50);
}
@Test
public void fromSequenceDictionary() {
mSortedSet =
GenomeLocSortedSet.createSetFromSequenceDictionary(this.header.getSequenceDictionary());
// we should have sequence
assertTrue(mSortedSet.size() == GenomeLocSortedSetUnitTest.NUMBER_OF_CHROMOSOMES);
int seqNumber = 0;
for (GenomeLoc loc : mSortedSet) {
assertTrue(loc.getStart() == 1);
assertTrue(loc.getStop() == GenomeLocSortedSetUnitTest.CHROMOSOME_SIZE);
assertTrue(loc.getContigIndex() == seqNumber);
++seqNumber;
}
assertTrue(seqNumber == GenomeLocSortedSetUnitTest.NUMBER_OF_CHROMOSOMES);
}
@Test
public void mergingOverlappingAbove() {
GenomeLoc e = genomeLocParser.createGenomeLoc(contigOneName, 0, 50);
GenomeLoc g = genomeLocParser.createGenomeLoc(contigOneName, 49, 100);
assertTrue(mSortedSet.size() == 0);
mSortedSet.add(g);
assertTrue(mSortedSet.size() == 1);
mSortedSet.addRegion(e);
assertTrue(mSortedSet.size() == 1);
Iterator<GenomeLoc> iter = mSortedSet.iterator();
GenomeLoc loc = iter.next();
assertEquals(loc.getStart(), 0);
assertEquals(loc.getStop(), 100);
assertEquals(loc.getContigIndex(), 1);
}
@DataProvider(name = "GetOverlapping")
public Object[][] makeGetOverlappingTest() throws Exception {
final GenomeLocParser genomeLocParser =
new GenomeLocParser(new CachingIndexedFastaSequenceFile(new File(b37KGReference)));
List<Object[]> tests = new ArrayList<Object[]>();
final GenomeLoc prev1 = genomeLocParser.createGenomeLoc("19", 1, 10);
final GenomeLoc prev2 = genomeLocParser.createGenomeLoc("19", 20, 50);
final GenomeLoc post1 = genomeLocParser.createGenomeLoc("21", 1, 10);
final GenomeLoc post2 = genomeLocParser.createGenomeLoc("21", 20, 50);
final int chr20Length = genomeLocParser.getContigs().getSequence("20").getSequenceLength();
for (final int regionStart : Arrays.asList(1, 10, chr20Length - 10, chr20Length)) {
for (final int regionSize : Arrays.asList(1, 10, 100)) {
final GenomeLoc region =
genomeLocParser.createGenomeLocOnContig("20", regionStart, regionStart + regionSize);
final GenomeLoc spanning =
genomeLocParser.createGenomeLocOnContig("20", regionStart - 10, region.getStop() + 10);
final GenomeLoc before_into =
genomeLocParser.createGenomeLocOnContig("20", regionStart - 10, regionStart + 1);
final GenomeLoc middle =
genomeLocParser.createGenomeLocOnContig("20", regionStart + 1, regionStart + 2);
final GenomeLoc middle_past =
genomeLocParser.createGenomeLocOnContig(
"20", region.getStop() - 1, region.getStop() + 10);
final List<GenomeLoc> potentials = new LinkedList<GenomeLoc>();
potentials.add(region);
if (spanning != null) potentials.add(spanning);
if (before_into != null) potentials.add(before_into);
if (middle != null) potentials.add(middle);
if (middle_past != null) potentials.add(middle_past);
for (final int n : Arrays.asList(1, 2, 3)) {
for (final List<GenomeLoc> regions : Utils.makePermutations(potentials, n, false)) {
tests.add(new Object[] {new GenomeLocSortedSet(genomeLocParser, regions), region});
tests.add(
new Object[] {
new GenomeLocSortedSet(genomeLocParser, Utils.append(regions, prev1)), region
});
tests.add(
new Object[] {
new GenomeLocSortedSet(genomeLocParser, Utils.append(regions, prev1, prev2)),
region
});
tests.add(
new Object[] {
new GenomeLocSortedSet(genomeLocParser, Utils.append(regions, post1)), region
});
tests.add(
new Object[] {
new GenomeLocSortedSet(genomeLocParser, Utils.append(regions, post1, post2)),
region
});
tests.add(
new Object[] {
new GenomeLocSortedSet(genomeLocParser, Utils.append(regions, prev1, post1)),
region
});
tests.add(
new Object[] {
new GenomeLocSortedSet(
genomeLocParser, Utils.append(regions, prev1, prev2, post1, post2)),
region
});
}
}
}
}
return tests.toArray(new Object[][] {});
}
/**
* Main entry function to calculate genotypes of a given VC with corresponding GL's
*
* @param tracker Tracker
* @param refContext Reference context
* @param rawContext Raw context
* @param stratifiedContexts Stratified alignment contexts
* @param vc Input VC
* @param model GL calculation model
* @param inheritAttributesFromInputVC Output VC will contain attributes inherited from input vc
* @return VC with assigned genotypes
*/
public VariantCallContext calculateGenotypes(
final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext,
Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc,
final GenotypeLikelihoodsCalculationModel.Model model,
final boolean inheritAttributesFromInputVC,
final Map<String, org.broadinstitute.sting.utils.genotyper.PerReadAlleleLikelihoodMap>
perReadAlleleLikelihoodMap) {
boolean limitedContext =
tracker == null || refContext == null || rawContext == null || stratifiedContexts == null;
// initialize the data for this thread if that hasn't been done yet
if (afcm.get() == null) {
afcm.set(AFCalcFactory.createAFCalc(UAC, N, logger));
}
// estimate our confidence in a reference call and return
if (vc.getNSamples() == 0) {
if (limitedContext) return null;
return (UAC.OutputMode != OUTPUT_MODE.EMIT_ALL_SITES
? estimateReferenceConfidence(vc, stratifiedContexts, getTheta(model), false, 1.0)
: generateEmptyContext(tracker, refContext, stratifiedContexts, rawContext));
}
AFCalcResult AFresult = afcm.get().getLog10PNonRef(vc, getAlleleFrequencyPriors(model));
// is the most likely frequency conformation AC=0 for all alternate alleles?
boolean bestGuessIsRef = true;
// determine which alternate alleles have AF>0
final List<Allele> myAlleles = new ArrayList<Allele>(vc.getAlleles().size());
final List<Integer> alleleCountsofMLE = new ArrayList<Integer>(vc.getAlleles().size());
myAlleles.add(vc.getReference());
for (int i = 0; i < AFresult.getAllelesUsedInGenotyping().size(); i++) {
final Allele alternateAllele = AFresult.getAllelesUsedInGenotyping().get(i);
if (alternateAllele.isReference()) continue;
// we are non-ref if the probability of being non-ref > the emit confidence.
// the emit confidence is phred-scaled, say 30 => 10^-3.
// the posterior AF > 0 is log10: -5 => 10^-5
// we are non-ref if 10^-5 < 10^-3 => -5 < -3
final boolean isNonRef =
AFresult.isPolymorphic(alternateAllele, UAC.STANDARD_CONFIDENCE_FOR_EMITTING / -10.0);
// if the most likely AC is not 0, then this is a good alternate allele to use
if (isNonRef) {
myAlleles.add(alternateAllele);
alleleCountsofMLE.add(AFresult.getAlleleCountAtMLE(alternateAllele));
bestGuessIsRef = false;
}
// if in GENOTYPE_GIVEN_ALLELES mode, we still want to allow the use of a poor allele
else if (UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE.GENOTYPE_GIVEN_ALLELES) {
myAlleles.add(alternateAllele);
alleleCountsofMLE.add(AFresult.getAlleleCountAtMLE(alternateAllele));
}
}
final double PoFGT0 = Math.pow(10, AFresult.getLog10PosteriorOfAFGT0());
// note the math.abs is necessary because -10 * 0.0 => -0.0 which isn't nice
final double phredScaledConfidence =
Math.abs(
!bestGuessIsRef
|| UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE
.GENOTYPE_GIVEN_ALLELES
? -10 * AFresult.getLog10PosteriorOfAFEq0()
: -10 * AFresult.getLog10PosteriorOfAFGT0());
// return a null call if we don't pass the confidence cutoff or the most likely allele frequency
// is zero
if (UAC.OutputMode != OUTPUT_MODE.EMIT_ALL_SITES
&& !passesEmitThreshold(phredScaledConfidence, bestGuessIsRef)) {
// technically, at this point our confidence in a reference call isn't accurately estimated
// because it didn't take into account samples with no data, so let's get a better estimate
return limitedContext
? null
: estimateReferenceConfidence(vc, stratifiedContexts, getTheta(model), true, PoFGT0);
}
// start constructing the resulting VC
final GenomeLoc loc = genomeLocParser.createGenomeLoc(vc);
final VariantContextBuilder builder =
new VariantContextBuilder(
"UG_call", loc.getContig(), loc.getStart(), loc.getStop(), myAlleles);
builder.log10PError(phredScaledConfidence / -10.0);
if (!passesCallThreshold(phredScaledConfidence)) builder.filters(filter);
// create the genotypes
final GenotypesContext genotypes = afcm.get().subsetAlleles(vc, myAlleles, true, ploidy);
builder.genotypes(genotypes);
// print out stats if we have a writer
if (verboseWriter != null && !limitedContext)
printVerboseData(refContext.getLocus().toString(), vc, PoFGT0, phredScaledConfidence, model);
// *** note that calculating strand bias involves overwriting data structures, so we do that
// last
final HashMap<String, Object> attributes = new HashMap<String, Object>();
// inherit attributed from input vc if requested
if (inheritAttributesFromInputVC) attributes.putAll(vc.getAttributes());
// if the site was downsampled, record that fact
if (!limitedContext && rawContext.hasPileupBeenDownsampled())
attributes.put(VCFConstants.DOWNSAMPLED_KEY, true);
if (UAC.ANNOTATE_NUMBER_OF_ALLELES_DISCOVERED)
attributes.put(NUMBER_OF_DISCOVERED_ALLELES_KEY, vc.getAlternateAlleles().size());
// add the MLE AC and AF annotations
if (alleleCountsofMLE.size() > 0) {
attributes.put(VCFConstants.MLE_ALLELE_COUNT_KEY, alleleCountsofMLE);
final int AN = builder.make().getCalledChrCount();
final ArrayList<Double> MLEfrequencies = new ArrayList<Double>(alleleCountsofMLE.size());
// the MLEAC is allowed to be larger than the AN (e.g. in the case of all PLs being 0, the GT
// is ./. but the exact model may arbitrarily choose an AC>1)
for (int AC : alleleCountsofMLE) MLEfrequencies.add(Math.min(1.0, (double) AC / (double) AN));
attributes.put(VCFConstants.MLE_ALLELE_FREQUENCY_KEY, MLEfrequencies);
}
if (UAC.COMPUTE_SLOD && !limitedContext && !bestGuessIsRef) {
// final boolean DEBUG_SLOD = false;
// the overall lod
// double overallLog10PofNull = AFresult.log10AlleleFrequencyPosteriors[0];
double overallLog10PofF = AFresult.getLog10LikelihoodOfAFGT0();
// if ( DEBUG_SLOD ) System.out.println("overallLog10PofF=" + overallLog10PofF);
List<Allele> allAllelesToUse = builder.make().getAlleles();
// the forward lod
VariantContext vcForward =
calculateLikelihoods(
tracker,
refContext,
stratifiedContexts,
AlignmentContextUtils.ReadOrientation.FORWARD,
allAllelesToUse,
false,
model,
perReadAlleleLikelihoodMap);
AFresult = afcm.get().getLog10PNonRef(vcForward, getAlleleFrequencyPriors(model));
// double[] normalizedLog10Posteriors =
// MathUtils.normalizeFromLog10(AFresult.log10AlleleFrequencyPosteriors, true);
double forwardLog10PofNull = AFresult.getLog10LikelihoodOfAFEq0();
double forwardLog10PofF = AFresult.getLog10LikelihoodOfAFGT0();
// if ( DEBUG_SLOD ) System.out.println("forwardLog10PofNull=" + forwardLog10PofNull + ",
// forwardLog10PofF=" + forwardLog10PofF);
// the reverse lod
VariantContext vcReverse =
calculateLikelihoods(
tracker,
refContext,
stratifiedContexts,
AlignmentContextUtils.ReadOrientation.REVERSE,
allAllelesToUse,
false,
model,
perReadAlleleLikelihoodMap);
AFresult = afcm.get().getLog10PNonRef(vcReverse, getAlleleFrequencyPriors(model));
// normalizedLog10Posteriors =
// MathUtils.normalizeFromLog10(AFresult.log10AlleleFrequencyPosteriors, true);
double reverseLog10PofNull = AFresult.getLog10LikelihoodOfAFEq0();
double reverseLog10PofF = AFresult.getLog10LikelihoodOfAFGT0();
// if ( DEBUG_SLOD ) System.out.println("reverseLog10PofNull=" + reverseLog10PofNull + ",
// reverseLog10PofF=" + reverseLog10PofF);
double forwardLod = forwardLog10PofF + reverseLog10PofNull - overallLog10PofF;
double reverseLod = reverseLog10PofF + forwardLog10PofNull - overallLog10PofF;
// if ( DEBUG_SLOD ) System.out.println("forward lod=" + forwardLod + ", reverse lod=" +
// reverseLod);
// strand score is max bias between forward and reverse strands
double strandScore = Math.max(forwardLod, reverseLod);
// rescale by a factor of 10
strandScore *= 10.0;
// logger.debug(String.format("SLOD=%f", strandScore));
if (!Double.isNaN(strandScore)) attributes.put("SB", strandScore);
}
// finish constructing the resulting VC
builder.attributes(attributes);
VariantContext vcCall = builder.make();
// if we are subsetting alleles (either because there were too many or because some were not
// polymorphic)
// then we may need to trim the alleles (because the original VariantContext may have had to pad
// at the end).
if (myAlleles.size() != vc.getAlleles().size()
&& !limitedContext) // limitedContext callers need to handle allele trimming on their own to
// keep their perReadAlleleLikelihoodMap alleles in sync
vcCall = VariantContextUtils.reverseTrimAlleles(vcCall);
if (annotationEngine != null
&& !limitedContext) { // limitedContext callers need to handle annotations on their own by
// calling their own annotationEngine
// Note: we want to use the *unfiltered* and *unBAQed* context for the annotations
final ReadBackedPileup pileup = rawContext.getBasePileup();
stratifiedContexts = AlignmentContextUtils.splitContextBySampleName(pileup);
vcCall =
annotationEngine.annotateContext(
tracker, refContext, stratifiedContexts, vcCall, perReadAlleleLikelihoodMap);
}
return new VariantCallContext(vcCall, confidentlyCalled(phredScaledConfidence, PoFGT0));
}
