Examples with Dirichlet org.broadinstitute.hellbender.utils.Dirichlet used on opensource projects

Example 1 with Dirichlet

use of org.broadinstitute.hellbender.utils.Dirichlet in project gatk by broadinstitute.

the class AlleleFrequencyCalculator method getLog10PNonRef.

//TODO: this should be a class of static methods once the old AFCalculator is gone.
/**
     * Compute the probability of the alleles segregating given the genotype likelihoods of the samples in vc
     *
     * @param vc the VariantContext holding the alleles and sample information.  The VariantContext
     *           must have at least 1 alternative allele
     * @param refSnpIndelPseudocounts a total hack.  A length-3 vector containing Dirichlet prior pseudocounts to
     *                                be given to ref, alt SNP, and alt indel alleles.  Hack won't be necessary when we destroy the old AF calculators
     * @return result (for programming convenience)
     */
@Override
public AFCalculationResult getLog10PNonRef(final VariantContext vc, final int defaultPloidy, final int maximumAlternativeAlleles, final double[] refSnpIndelPseudocounts) {
    Utils.nonNull(vc, "VariantContext cannot be null");
    final int numAlleles = vc.getNAlleles();
    final List<Allele> alleles = vc.getAlleles();
    Utils.validateArg(numAlleles > 1, () -> "VariantContext has only a single reference allele, but getLog10PNonRef requires at least one at all " + vc);
    final double[] priorPseudocounts = alleles.stream().mapToDouble(a -> a.isReference() ? refPseudocount : (a.length() > 1 ? snpPseudocount : indelPseudocount)).toArray();
    double[] alleleCounts = new double[numAlleles];
    // log10(1/numAlleles)
    final double flatLog10AlleleFrequency = -MathUtils.log10(numAlleles);
    double[] log10AlleleFrequencies = new IndexRange(0, numAlleles).mapToDouble(n -> flatLog10AlleleFrequency);
    double alleleCountsMaximumDifference = Double.POSITIVE_INFINITY;
    while (alleleCountsMaximumDifference > THRESHOLD_FOR_ALLELE_COUNT_CONVERGENCE) {
        final double[] newAlleleCounts = effectiveAlleleCounts(vc, log10AlleleFrequencies);
        alleleCountsMaximumDifference = Arrays.stream(MathArrays.ebeSubtract(alleleCounts, newAlleleCounts)).map(Math::abs).max().getAsDouble();
        alleleCounts = newAlleleCounts;
        final double[] posteriorPseudocounts = MathArrays.ebeAdd(priorPseudocounts, alleleCounts);
        // first iteration uses flat prior in order to avoid local minimum where the prior + no pseudocounts gives such a low
        // effective allele frequency that it overwhelms the genotype likelihood of a real variant
        // basically, we want a chance to get non-zero pseudocounts before using a prior that's biased against a variant
        log10AlleleFrequencies = new Dirichlet(posteriorPseudocounts).log10MeanWeights();
    }
    double[] log10POfZeroCountsByAllele = new double[numAlleles];
    double log10PNoVariant = 0;
    for (final Genotype g : vc.getGenotypes()) {
        if (!g.hasLikelihoods()) {
            continue;
        }
        final int ploidy = g.getPloidy() == 0 ? defaultPloidy : g.getPloidy();
        final GenotypeLikelihoodCalculator glCalc = GL_CALCS.getInstance(ploidy, numAlleles);
        final double[] log10GenotypePosteriors = log10NormalizedGenotypePosteriors(g, glCalc, log10AlleleFrequencies);
        //the total probability
        log10PNoVariant += log10GenotypePosteriors[HOM_REF_GENOTYPE_INDEX];
        // per allele non-log space probabilities of zero counts for this sample
        // for each allele calculate the total probability of genotypes containing at least one copy of the allele
        final double[] log10ProbabilityOfNonZeroAltAlleles = new double[numAlleles];
        Arrays.fill(log10ProbabilityOfNonZeroAltAlleles, Double.NEGATIVE_INFINITY);
        for (int genotype = 0; genotype < glCalc.genotypeCount(); genotype++) {
            final double log10GenotypePosterior = log10GenotypePosteriors[genotype];
            glCalc.genotypeAlleleCountsAt(genotype).forEachAlleleIndexAndCount((alleleIndex, count) -> log10ProbabilityOfNonZeroAltAlleles[alleleIndex] = MathUtils.log10SumLog10(log10ProbabilityOfNonZeroAltAlleles[alleleIndex], log10GenotypePosterior));
        }
        for (int allele = 0; allele < numAlleles; allele++) {
            // if prob of non hom ref == 1 up to numerical precision, short-circuit to avoid NaN
            if (log10ProbabilityOfNonZeroAltAlleles[allele] >= 0) {
                log10POfZeroCountsByAllele[allele] = Double.NEGATIVE_INFINITY;
            } else {
                log10POfZeroCountsByAllele[allele] += MathUtils.log10OneMinusPow10(log10ProbabilityOfNonZeroAltAlleles[allele]);
            }
        }
    }
    // unfortunately AFCalculationResult expects integers for the MLE.  We really should emit the EM no-integer values
    // which are valuable (eg in CombineGVCFs) as the sufficient statistics of the Dirichlet posterior on allele frequencies
    final int[] integerAlleleCounts = Arrays.stream(alleleCounts).mapToInt(x -> (int) Math.round(x)).toArray();
    final int[] integerAltAlleleCounts = Arrays.copyOfRange(integerAlleleCounts, 1, numAlleles);
    //skip the ref allele (index 0)
    final Map<Allele, Double> log10PRefByAllele = IntStream.range(1, numAlleles).boxed().collect(Collectors.toMap(alleles::get, a -> log10POfZeroCountsByAllele[a]));
    // we compute posteriors here and don't have the same prior that AFCalculationResult expects.  Therefore, we
    // give it our posterior as its "likelihood" along with a flat dummy prior
    //TODO: HACK must be negative for AFCalcResult
    final double[] dummyFlatPrior = { -1e-10, -1e-10 };
    final double[] log10PosteriorOfNoVariantYesVariant = { log10PNoVariant, MathUtils.log10OneMinusPow10(log10PNoVariant) };
    return new AFCalculationResult(integerAltAlleleCounts, alleles, log10PosteriorOfNoVariantYesVariant, dummyFlatPrior, log10PRefByAllele);
}