internal static double GetGtLogLikelihoodScore(Balleles gtObservedCounts, List <PhasedGenotype> gtModelCounts, ref int?selectedGtState, ICopyNumberModel copyNumberModel)
{
const int maxGQscore = 60;
var gtLogLikelihoods = Enumerable.Repeat(Double.NegativeInfinity, gtModelCounts.Count).ToList();
var gtModelCounter = -1;
foreach (var gtModelCount in gtModelCounts)
{
gtModelCounter++;
// As we don't estimate allele CN but only MCC, focus on upper-triangle
if (gtModelCount.CopyNumberA < gtModelCount.CopyNumberB)
{
continue;
}
gtLogLikelihoods[gtModelCounter] = copyNumberModel.GetGenotypeLogLikelihood(gtObservedCounts, gtModelCount);
}
var maxLogLikelihood = gtLogLikelihoods.Max();
if (!selectedGtState.HasValue)
{
selectedGtState = gtLogLikelihoods.IndexOf(maxLogLikelihood);
}
double normalizationConstant = gtLogLikelihoods.Sum(ll => Math.Exp(ll - maxLogLikelihood));
double gqscore = -10.0 * Math.Log10((normalizationConstant - 1) / normalizationConstant);
if (Double.IsInfinity(gqscore) | gqscore > maxGQscore)
{
gqscore = maxGQscore;
}
return(Double.IsNaN(gqscore) || Double.IsInfinity(gqscore) ? 0 : gqscore);
}
public void MergeIn_PreviousSegment_KeepsBAllelesOrdered()
{
List <SampleGenomicBin> emptyBins = new List <SampleGenomicBin>();
var bAllelesBefore = new Balleles(new List <Ballele> {
new Ballele(1, 1, 1)
});
CanvasSegment segmentBefore = new CanvasSegment("chr1", 1, 2, emptyBins, bAllelesBefore);
var bAlleles = new Balleles(new List <Ballele> {
new Ballele(2, 1, 1)
});
CanvasSegment segment = new CanvasSegment("chr1", 2, 3, emptyBins, bAlleles);
segment.MergeIn(segmentBefore);
Assert.Equal(bAllelesBefore.Range.Concat(bAlleles.Range), segment.Balleles.Range);
}
public void TestGetGtLogLikelihoodScore()
{
var copyNumberModelFactory = new HaplotypeCopyNumberModelFactory();
var copyNumberModel = copyNumberModelFactory.CreateModel(numCnStates: 5, maxCoverage: 200,
meanCoverage: 100, diploidAlleleMeanCounts: 50.0);
var simulatedCn = 3;
var gtModelCounts = PedigreeInfo.GeneratePhasedGenotype(numCnStates: 5).Where(gt => gt.TotalCopyNumber == simulatedCn)
.Select(gt => gt.PhasedGenotype).ToList();
var gtObservedCounts = new Balleles(new List <Ballele>
{
new Ballele(1, 1, 73),
new Ballele(100, 2, 74),
new Ballele(200, 1, 76),
new Ballele(300, 0, 74),
new Ballele(400, 1, 75),
new Ballele(500, 2, 74)
});
var gt0_3 = new PhasedGenotype(3, 0);
int?selectedGtState = null;
// variant caller only calls MCC, only upper triangle of CN genotypes is selected - i.e. CNa=3,CNb=0 from [CNa=3,CNb=0,CNa=0,CNb=3]
double logLikelihoodScore =
VariantCaller.GetGtLogLikelihoodScore(gtObservedCounts, gtModelCounts, ref selectedGtState,
copyNumberModel);
Assert.Equal(gtModelCounts.IndexOf(gt0_3), selectedGtState);
gtObservedCounts = new Balleles(new List <Ballele>
{
new Ballele(1, 23, 53),
new Ballele(100, 22, 54),
new Ballele(200, 25, 46),
new Ballele(300, 24, 50),
new Ballele(400, 26, 51),
new Ballele(500, 24, 51)
});
var gt1_2 = new PhasedGenotype(2, 1);
selectedGtState = null;
// variant caller only calls MCC, only upper triangle of CN genotypes is selected - i.e. CNa=3,CNb=0 from [CNa=3,CNb=0,CNa=0,CNb=3]
logLikelihoodScore =
VariantCaller.GetGtLogLikelihoodScore(gtObservedCounts, gtModelCounts, ref selectedGtState,
copyNumberModel);
Assert.Equal(gtModelCounts.IndexOf(gt1_2), selectedGtState);
}
public void HaplotypeCopyNumberModelTester_HetLoss()
{
var copyNumberModelFactory = new HaplotypeCopyNumberModelFactory();
var copyNumberModel = copyNumberModelFactory.CreateModel(numCnStates: 5, maxCoverage: 200, meanCoverage: 100, diploidAlleleMeanCounts: 50.0);
var bAlleles = new Balleles(new List <Ballele>
{
new Ballele(1, 31, 1),
new Ballele(100, 39, 2),
new Ballele(200, 33, 3),
new Ballele(300, 1, 33),
new Ballele(400, 36, 2),
new Ballele(500, 27, 1)
});
double gt10 = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(1, 0));
double gt20 = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(2, 0));
double gt01 = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(0, 1));
Assert.True(gt10 > gt20);
Assert.True(gt10 == gt01);
}
public void HaplotypeCopyNumberModelTester_Gain_CN4()
{
var copyNumberModelFactory = new HaplotypeCopyNumberModelFactory();
var copyNumberModel = copyNumberModelFactory.CreateModel(numCnStates: 5, maxCoverage: 300, meanCoverage: 100, diploidAlleleMeanCounts: 50.0);
var bAlleles = new Balleles(new List <Ballele>
{
new Ballele(1, 200, 1),
new Ballele(100, 202, 2),
new Ballele(200, 209, 3),
new Ballele(300, 1, 198),
new Ballele(400, 201, 2),
new Ballele(500, 199, 1)
});
double gt40 = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(4, 0));
double gt31 = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(3, 1));
double gt04 = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(0, 4));
Assert.True(gt40 > gt31);
Assert.True(gt40 == gt04);
}
public void HaplotypeCopyNumberModelTester_PhasedGenotype_LossOfHeterozygosity()
{
var copyNumberModelFactory = new HaplotypeCopyNumberModelFactory();
var copyNumberModel = copyNumberModelFactory.CreateModel(numCnStates: 5, maxCoverage: 200, meanCoverage: 100, diploidAlleleMeanCounts: 50.0);
var bAlleles = new Balleles(new List <Ballele>
{
new Ballele(1, 50, 1),
new Ballele(100, 25, 24),
new Ballele(200, 23, 27),
new Ballele(300, 25, 24),
new Ballele(400, 1, 50),
new Ballele(500, 25, 25)
});
double diploidHet = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(1, 1));
double lohB = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(0, 2));
double lohA = copyNumberModel.GetGenotypeLogLikelihood(bAlleles, new PhasedGenotype(2, 0));
Assert.True(diploidHet > lohB);
Assert.True(diploidHet > lohA);
var bAllelesLohWithNoise = new Balleles(new List <Ballele>
{
new Ballele(1, 53, 1),
new Ballele(100, 50, 1),
new Ballele(200, 47, 2),
new Ballele(300, 46, 0),
new Ballele(400, 48, 2),
new Ballele(500, 53, 0)
});
diploidHet = copyNumberModel.GetGenotypeLogLikelihood(bAllelesLohWithNoise, new PhasedGenotype(1, 1));
lohB = copyNumberModel.GetGenotypeLogLikelihood(bAllelesLohWithNoise, new PhasedGenotype(0, 2));
lohA = copyNumberModel.GetGenotypeLogLikelihood(bAllelesLohWithNoise, new PhasedGenotype(2, 0));
Assert.True(diploidHet < lohB);
Assert.True(diploidHet < lohA);
}
public double GetGenotypeLogLikelihood(Balleles gtObservedCounts, PhasedGenotype gtModelCount)
{
double minLogLikelihood = Math.Log(1.0 / Double.MaxValue);
double currentLogLikelihood = 0;
foreach (var gtCount in gtObservedCounts.GetTruncatedAlleleCounts())
{
int rowId = Math.Min(gtCount.Item1, _maxCoverage - 1);
int colId = Math.Min(gtCount.Item2, _maxCoverage - 1);
int numHapsNonZero = (gtModelCount.CopyNumberA > 0 ? 1 : 0) + (gtModelCount.CopyNumberB > 0 ? 1 : 0);
double likelihoodThisLocus = 0;
// the observations can arise from a het locus, if both copy numbers are positive
if (numHapsNonZero == 2)
{
// Given a variant locus with two haplotypes, we have a roughly 2/3 chance of it being het.
// Alleles have 50:50 chance of being 'A' or 'B'.
// We ignore error terms, as they should have a negligible impact here.
likelihoodThisLocus += 1.0 / 3.0 *
(
_alleleDistribution[gtModelCount.CopyNumberA][gtModelCount.CopyNumberB].Item1[rowId] *
_alleleDistribution[gtModelCount.CopyNumberA][gtModelCount.CopyNumberB].Item2[colId]
+
_alleleDistribution[gtModelCount.CopyNumberA][gtModelCount.CopyNumberB].Item1[colId] *
_alleleDistribution[gtModelCount.CopyNumberA][gtModelCount.CopyNumberB].Item2[rowId]
);
}
// they can also arise from a hom locus in various ways
if (numHapsNonZero > 0)
{
// these should be constants to avoid calling Log over and over.
double logErrorProb = Math.Log(0.01);
double logNoErrorProb = Math.Log(.99);
// If both haplotypes have non-zero depth and the locus is non-ref, a locus has a prior prob of 1/3 of being hom,
// assuming a well-mixed population. We could adjust for observed het:hom, but we do not at this time.
// Of course, if only one haplotype has non-zero depth, it must be hom.
double priorFactorHom = numHapsNonZero == 2 ? 0.5 * (1.0 / 3.0) : 1.0;
// limit ttlReads to maxTotalDepth as that is all we have _readDepth probabilities for
int totalReads = Math.Min(rowId + colId, _maxAlleleCounts);
int totalCN = gtModelCount.CopyNumberA + gtModelCount.CopyNumberB;
// Split the likelihood into two parts:
// First, the probability of getting the observed total number of reads, given the total copy number
double probTotalReadDepth = _totalAlleleCountsDistribution[totalCN][totalReads];
// Second, the probability of the observed per-allele read counts assuming one of the alleles is an error.
// The calculation here is simply binomial, in log space
double logProbCountAErrors = LogCombinations(rowId, colId) + rowId * logErrorProb + colId * logNoErrorProb;
double logProbCountBErrors = LogCombinations(rowId, colId) + colId * logErrorProb + rowId * logNoErrorProb;
likelihoodThisLocus += priorFactorHom * probTotalReadDepth * (
Math.Exp(logProbCountAErrors) + Math.Exp(logProbCountBErrors));
}
else
{
// uses alleleStateZeroCorrector to enable non-zero likelihoods
int totalReads = Math.Min(rowId + colId, _maxAlleleCounts);
likelihoodThisLocus = _totalAlleleCountsDistribution[0][totalReads];
}
likelihoodThisLocus = Math.Max(minLogLikelihood, likelihoodThisLocus);
currentLogLikelihood += Math.Log(likelihoodThisLocus);
}
return(currentLogLikelihood);
}
public void TestCommonCnvAssignment_DeNovoVariants()
{
var bins = new List <SampleGenomicBin>
{
new SampleGenomicBin("chr1", 1, 2, 100),
new SampleGenomicBin("chr1", 1, 2, 100),
new SampleGenomicBin("chr1", 1, 2, 100)
};
var balleles = new Balleles(new List <Ballele> {
new Ballele(5501, 30, 30)
});
var segmentParent1 = new CanvasSegment("chr1", 1, 2, bins, balleles)
{
CopyNumber = 2
};
bins = new List <SampleGenomicBin>
{
new SampleGenomicBin("chr1", 1, 2, 100),
new SampleGenomicBin("chr1", 1, 2, 100),
new SampleGenomicBin("chr1", 1, 2, 100)
};
balleles = new Balleles(new List <Ballele> {
new Ballele(5501, 30, 30)
});
var segmentParent2 = new CanvasSegment("chr1", 1, 2, bins, balleles)
{
CopyNumber = 2
};
bins = new List <SampleGenomicBin>
{
new SampleGenomicBin("chr1", 1, 2, 0),
new SampleGenomicBin("chr1", 1, 2, 0),
new SampleGenomicBin("chr1", 1, 2, 0)
};
balleles = new Balleles(new List <Ballele> {
new Ballele(5501, 0, 0)
});
var segmentProband = new CanvasSegment("chr1", 1, 2, bins, balleles)
{
CopyNumber = 0
};
var pedigreeSegments = new SampleMap <CanvasSegment>
{
{ new SampleId("parent1"), segmentParent1 },
{ new SampleId("parent2"), segmentParent2 },
{ new SampleId("proband"), segmentProband }
};
var sampleMetricsParent1 = SampleMetrics.GetSampleInfo(new List <CanvasSegment> {
segmentParent1
},
ploidyBedPath: null,
numberOfTrimmedBins: 2, id: new SampleId("parent1"));
var sampleMetricsParent2 = SampleMetrics.GetSampleInfo(new List <CanvasSegment> {
segmentParent2
},
ploidyBedPath: null,
numberOfTrimmedBins: 2, id: new SampleId("parent2"));
var sampleMetricsProband = SampleMetrics.GetSampleInfo(new List <CanvasSegment> {
segmentProband
},
ploidyBedPath: null,
numberOfTrimmedBins: 2, id: new SampleId("proband"));
var sampleMetrics = new SampleMap <SampleMetrics>
{
{ new SampleId("parent1"), sampleMetricsParent1 },
{ new SampleId("parent2"), sampleMetricsParent2 },
{ new SampleId("proband"), sampleMetricsProband }
};
bool isCommonCnv = global::CanvasPedigreeCaller.CanvasPedigreeCaller.IsSharedCnv(pedigreeSegments, sampleMetrics,
new List <SampleId> {
new SampleId("parent1"), new SampleId("parent2")
},
new SampleId("proband"), maximumCopyNumber: 5);
Assert.False(isCommonCnv);
var pedigreeGenotypes = new SampleMap <Genotype>
{
{ new SampleId("parent1"), Genotype.Create(new PhasedGenotype(1, 1)) },
{ new SampleId("parent2"), Genotype.Create(new PhasedGenotype(1, 1)) },
{ new SampleId("proband"), Genotype.Create(new PhasedGenotype(0, 1)) }
};
isCommonCnv = global::CanvasPedigreeCaller.CanvasPedigreeCaller.IsSharedCnv(pedigreeGenotypes, pedigreeSegments,
sampleMetrics, new List <SampleId> {
new SampleId("parent1"), new SampleId("parent2")
},
new SampleId("proband"), maximumCopyNumber: 5);
Assert.False(isCommonCnv);
pedigreeGenotypes = new SampleMap <Genotype>
{
{ new SampleId("parent1"), Genotype.Create(new PhasedGenotype(2, 1)) },
{ new SampleId("parent2"), Genotype.Create(new PhasedGenotype(1, 1)) },
{ new SampleId("proband"), Genotype.Create(new PhasedGenotype(0, 1)) }
};
isCommonCnv = global::CanvasPedigreeCaller.CanvasPedigreeCaller.IsSharedCnv(pedigreeGenotypes, pedigreeSegments,
sampleMetrics, new List <SampleId> {
new SampleId("parent1"), new SampleId("parent2")
},
new SampleId("proband"), maximumCopyNumber: 5);
Assert.False(isCommonCnv);
}
