private Haplotype getHaplotypeFromRead( final PileupElement p, final int contextSize, final int locus) { final GATKSAMRecord read = p.getRead(); int readOffsetFromPileup = p.getOffset(); final byte[] haplotypeBases = new byte[contextSize]; Arrays.fill(haplotypeBases, (byte) REGEXP_WILDCARD); final double[] baseQualities = new double[contextSize]; Arrays.fill(baseQualities, 0.0); byte[] readBases = read.getReadBases(); readBases = AlignmentUtils.readToAlignmentByteArray( read.getCigar(), readBases); // Adjust the read bases based on the Cigar string byte[] readQuals = read.getBaseQualities(); readQuals = AlignmentUtils.readToAlignmentByteArray( read.getCigar(), readQuals); // Shift the location of the qual scores based on the Cigar string readOffsetFromPileup = AlignmentUtils.calcAlignmentByteArrayOffset( read.getCigar(), p, read.getAlignmentStart(), locus); final int baseOffsetStart = readOffsetFromPileup - (contextSize - 1) / 2; for (int i = 0; i < contextSize; i++) { final int baseOffset = i + baseOffsetStart; if (baseOffset < 0) { continue; } if (baseOffset >= readBases.length) { break; } if (readQuals[baseOffset] == PileupElement.DELETION_BASE) { readQuals[baseOffset] = PileupElement.DELETION_QUAL; } if (!BaseUtils.isRegularBase(readBases[baseOffset])) { readBases[baseOffset] = (byte) REGEXP_WILDCARD; readQuals[baseOffset] = (byte) 0; } // N's shouldn't be treated as distinct bases readQuals[baseOffset] = (byte) Math.min((int) readQuals[baseOffset], p.getMappingQual()); if (((int) readQuals[baseOffset]) < 5) { readQuals[baseOffset] = (byte) 0; } // quals less than 5 are used as codes and don't have actual probabilistic meaning behind // them haplotypeBases[i] = readBases[baseOffset]; baseQualities[i] = (double) readQuals[baseOffset]; } return new Haplotype(haplotypeBases, baseQualities); }
private double scoreReadAgainstHaplotype( final PileupElement p, final int contextSize, final Haplotype haplotype, final int locus) { double expected = 0.0; double mismatches = 0.0; // What's the expected mismatch rate under the model that this read is actually sampled from // this haplotype? Let's assume the consensus base c is a random choice one of A, C, G, or T, // and that // the observed base is actually from a c with an error rate e. Since e is the rate at which // we'd // see a miscalled c, the expected mismatch rate is really e. So the expected number of // mismatches // is just sum_i e_i for i from 1..n for n sites // // Now, what's the probabilistic sum of mismatches? Suppose that the base b is equal to c. // Well, it could // actually be a miscall in a matching direction, which would happen at a e / 3 rate. If b != // c, then // the chance that it is actually a mismatch is 1 - e, since any of the other 3 options would be // a mismatch. // so the probability-weighted mismatch rate is sum_i ( matched ? e_i / 3 : 1 - e_i ) for i = 1 // ... n final byte[] haplotypeBases = haplotype.getBases(); final GATKSAMRecord read = p.getRead(); byte[] readBases = read.getReadBases(); readBases = AlignmentUtils.readToAlignmentByteArray( p.getRead().getCigar(), readBases); // Adjust the read bases based on the Cigar string byte[] readQuals = read.getBaseQualities(); readQuals = AlignmentUtils.readToAlignmentByteArray( p.getRead().getCigar(), readQuals); // Shift the location of the qual scores based on the Cigar string int readOffsetFromPileup = p.getOffset(); readOffsetFromPileup = AlignmentUtils.calcAlignmentByteArrayOffset( p.getRead().getCigar(), p, read.getAlignmentStart(), locus); final int baseOffsetStart = readOffsetFromPileup - (contextSize - 1) / 2; for (int i = 0; i < contextSize; i++) { final int baseOffset = i + baseOffsetStart; if (baseOffset < 0) { continue; } if (baseOffset >= readBases.length) { break; } final byte haplotypeBase = haplotypeBases[i]; final byte readBase = readBases[baseOffset]; final boolean matched = (readBase == haplotypeBase || haplotypeBase == (byte) REGEXP_WILDCARD); byte qual = readQuals[baseOffset]; if (qual == PileupElement.DELETION_BASE) { qual = PileupElement.DELETION_QUAL; } // calcAlignmentByteArrayOffset fills the readQuals array with DELETION_BASE at deletions qual = (byte) Math.min((int) qual, p.getMappingQual()); if (((int) qual) >= 5) { // quals less than 5 are used as codes and don't have actual probabilistic meaning // behind them final double e = QualityUtils.qualToErrorProb(qual); expected += e; mismatches += matched ? e : 1.0 - e / 3.0; } // a more sophisticated calculation would include the reference quality, but it's nice to // actually penalize // the mismatching of poorly determined regions of the consensus } return mismatches - expected; }