public double[] computeReadHaplotypeLikelihoods(
ReadBackedPileup pileup, HashMap<Allele, Haplotype> haplotypesInVC) {
double[][] haplotypeLikehoodMatrix = new double[haplotypesInVC.size()][haplotypesInVC.size()];
double readLikelihoods[][] = new double[pileup.getReads().size()][haplotypesInVC.size()];
int i = 0;
for (GATKSAMRecord read : pileup.getReads()) {
if (ReadUtils.is454Read(read)) {
continue;
}
// for each read/haplotype combination, compute likelihoods, ie -10*log10(Pr(R | Hi))
// = sum_j(-10*log10(Pr(R_j | Hi) since reads are assumed to be independent
int j = 0;
for (Map.Entry<Allele, Haplotype> a : haplotypesInVC.entrySet()) {
readLikelihoods[i][j] = computeReadLikelihoodGivenHaplotype(a.getValue(), read);
if (DEBUG) {
System.out.print(read.getReadName() + " ");
System.out.format(
"%d %d S:%d US:%d E:%d UE:%d C:%s %3.4f\n",
i,
j,
read.getAlignmentStart(),
read.getUnclippedStart(),
read.getAlignmentEnd(),
read.getUnclippedEnd(),
read.getCigarString(),
readLikelihoods[i][j]);
}
j++;
}
i++;
}
for (i = 0; i < haplotypesInVC.size(); i++) {
for (int j = i; j < haplotypesInVC.size(); j++) {
// combine likelihoods of haplotypeLikelihoods[i], haplotypeLikelihoods[j]
// L(Hi, Hj) = sum_reads ( Pr(R|Hi)/2 + Pr(R|Hj)/2)
// readLikelihoods[k][j] has log10(Pr(R_k) | H[j] )
double[] readLikelihood = new double[2]; // diploid sample
for (int readIdx = 0; readIdx < pileup.getReads().size(); readIdx++) {
readLikelihood[0] = -readLikelihoods[readIdx][i] / 10;
readLikelihood[1] = -readLikelihoods[readIdx][j] / 10;
// Compute log10(10^x1/2 + 10^x2/2) = log10(10^x1+x0^x2)-log10(2)
// First term is approximated by Jacobian log with table lookup.
// Second term is a constant added to both likelihoods so will be ignored
haplotypeLikehoodMatrix[i][j] +=
MathUtils.approximateLog10SumLog10(readLikelihood[0], readLikelihood[1]);
}
}
}
return getHaplotypeLikelihoods(haplotypeLikehoodMatrix);
}
