/** Converts the supplied adapter sequences to byte arrays in both fwd and rc. */ private byte[][] prepareAdapterSequences() { final Set<String> kmers = new HashSet<String>(); // Make a set of all kmers of adapterMatchLength for (final String seq : adapterSequence) { for (int i = 0; i <= seq.length() - ADAPTER_MATCH_LENGTH; ++i) { final String kmer = seq.substring(i, i + ADAPTER_MATCH_LENGTH).toUpperCase(); int ns = 0; for (final char ch : kmer.toCharArray()) if (ch == 'N') ++ns; if (ns <= MAX_ADAPTER_ERRORS) { kmers.add(kmer); kmers.add(SequenceUtil.reverseComplement(kmer)); } } } // Make an array of byte[] for the kmers final byte[][] adapterKmers = new byte[kmers.size()][]; int i = 0; for (final String kmer : kmers) { adapterKmers[i++] = StringUtil.stringToBytes(kmer); } return adapterKmers; }
private void collectReadData(final SAMRecord record, final ReferenceSequence ref) { metrics.TOTAL_READS++; readLengthHistogram.increment(record.getReadBases().length); if (!record.getReadFailsVendorQualityCheckFlag()) { metrics.PF_READS++; if (isNoiseRead(record)) metrics.PF_NOISE_READS++; if (record.getReadUnmappedFlag()) { // If the read is unmapped see if it's adapter sequence final byte[] readBases = record.getReadBases(); if (!(record instanceof BAMRecord)) StringUtil.toUpperCase(readBases); if (isAdapterSequence(readBases)) { this.adapterReads++; } } else if (doRefMetrics) { metrics.PF_READS_ALIGNED++; if (!record.getReadNegativeStrandFlag()) numPositiveStrand++; if (record.getReadPairedFlag() && !record.getMateUnmappedFlag()) { metrics.READS_ALIGNED_IN_PAIRS++; // Check that both ends have mapq > minimum final Integer mateMq = record.getIntegerAttribute("MQ"); if (mateMq == null || mateMq >= MAPPING_QUALITY_THRESOLD && record.getMappingQuality() >= MAPPING_QUALITY_THRESOLD) { ++this.chimerasDenominator; // With both reads mapped we can see if this pair is chimeric if (Math.abs(record.getInferredInsertSize()) > maxInsertSize || !record.getReferenceIndex().equals(record.getMateReferenceIndex())) { ++this.chimeras; } } } } } }
public static ArrayList<Byte> subseq(char[] fullArray) { byte[] fullByteArray = new byte[fullArray.length]; StringUtil.charsToBytes(fullArray, 0, fullArray.length, fullByteArray, 0); return subseq(fullByteArray); }
static VariantContext reallyMergeIntoMNP( VariantContext vc1, VariantContext vc2, ReferenceSequenceFile referenceFile) { int startInter = vc1.getEnd() + 1; int endInter = vc2.getStart() - 1; byte[] intermediateBases = null; if (startInter <= endInter) { intermediateBases = referenceFile.getSubsequenceAt(vc1.getChr(), startInter, endInter).getBases(); StringUtil.toUpperCase(intermediateBases); } MergedAllelesData mergeData = new MergedAllelesData( intermediateBases, vc1, vc2); // ensures that the reference allele is added GenotypesContext mergedGenotypes = GenotypesContext.create(); for (final Genotype gt1 : vc1.getGenotypes()) { Genotype gt2 = vc2.getGenotype(gt1.getSampleName()); List<Allele> site1Alleles = gt1.getAlleles(); List<Allele> site2Alleles = gt2.getAlleles(); List<Allele> mergedAllelesForSample = new LinkedList<Allele>(); /* NOTE: Since merged alleles are added to mergedAllelesForSample in the SAME order as in the input VC records, we preserve phase information (if any) relative to whatever precedes vc1: */ Iterator<Allele> all2It = site2Alleles.iterator(); for (Allele all1 : site1Alleles) { Allele all2 = all2It.next(); // this is OK, since allSamplesAreMergeable() Allele mergedAllele = mergeData.ensureMergedAllele(all1, all2); mergedAllelesForSample.add(mergedAllele); } double mergedGQ = Math.max(gt1.getLog10PError(), gt2.getLog10PError()); Set<String> mergedGtFilters = new HashSet< String>(); // Since gt1 and gt2 were unfiltered, the Genotype remains unfiltered Map<String, Object> mergedGtAttribs = new HashMap<String, Object>(); PhaseAndQuality phaseQual = calcPhaseForMergedGenotypes(gt1, gt2); if (phaseQual.PQ != null) mergedGtAttribs.put(ReadBackedPhasingWalker.PQ_KEY, phaseQual.PQ); Genotype mergedGt = new Genotype( gt1.getSampleName(), mergedAllelesForSample, mergedGQ, mergedGtFilters, mergedGtAttribs, phaseQual.isPhased); mergedGenotypes.add(mergedGt); } String mergedName = mergeVariantContextNames(vc1.getSource(), vc2.getSource()); double mergedLog10PError = Math.min(vc1.getLog10PError(), vc2.getLog10PError()); Set<String> mergedFilters = new HashSet< String>(); // Since vc1 and vc2 were unfiltered, the merged record remains unfiltered Map<String, Object> mergedAttribs = mergeVariantContextAttributes(vc1, vc2); // ids List<String> mergedIDs = new ArrayList<String>(); if (vc1.hasID()) mergedIDs.add(vc1.getID()); if (vc2.hasID()) mergedIDs.add(vc2.getID()); String mergedID = mergedIDs.isEmpty() ? VCFConstants.EMPTY_ID_FIELD : Utils.join(VCFConstants.ID_FIELD_SEPARATOR, mergedIDs); VariantContextBuilder mergedBuilder = new VariantContextBuilder( mergedName, vc1.getChr(), vc1.getStart(), vc2.getEnd(), mergeData.getAllMergedAlleles()) .id(mergedID) .genotypes(mergedGenotypes) .log10PError(mergedLog10PError) .filters(mergedFilters) .attributes(mergedAttribs); VariantContextUtils.calculateChromosomeCounts(mergedBuilder, true); return mergedBuilder.make(); }
/** * Create a new comparator. * * @param sequence Reference sequence to use as basis for comparison. */ public SuffixArrayComparator(byte[] sequence) { // Processing the suffix array tends to be easier as a string. this.sequence = StringUtil.bytesToString(sequence); }