private static void mergeGenotypes( GenotypesContext mergedGenotypes, VariantContext oneVC, AlleleMapper alleleMapping, boolean uniqifySamples) { for (Genotype g : oneVC.getGenotypes()) { String name = mergedSampleName(oneVC.getSource(), g.getSampleName(), uniqifySamples); if (!mergedGenotypes.containsSample(name)) { // only add if the name is new Genotype newG = g; if (uniqifySamples || alleleMapping.needsRemapping()) { final List<Allele> alleles = alleleMapping.needsRemapping() ? alleleMapping.remap(g.getAlleles()) : g.getAlleles(); newG = new Genotype( name, alleles, g.getLog10PError(), g.getFilters(), g.getAttributes(), g.isPhased()); } mergedGenotypes.add(newG); } } }
public static Genotype removePLs(Genotype g) { Map<String, Object> attrs = new HashMap<String, Object>(g.getAttributes()); attrs.remove(VCFConstants.PHRED_GENOTYPE_LIKELIHOODS_KEY); attrs.remove(VCFConstants.GENOTYPE_LIKELIHOODS_KEY); return new Genotype( g.getSampleName(), g.getAlleles(), g.getLog10PError(), g.filtersWereApplied() ? g.getFilters() : null, attrs, g.isPhased()); }
public static VariantContextBuilder pruneVariantContext( final VariantContextBuilder builder, Collection<String> keysToPreserve) { final VariantContext vc = builder.make(); if (keysToPreserve == null) keysToPreserve = Collections.emptyList(); // VC info final Map<String, Object> attributes = subsetAttributes(vc.commonInfo, keysToPreserve); // Genotypes final GenotypesContext genotypes = GenotypesContext.create(vc.getNSamples()); for (final Genotype g : vc.getGenotypes()) { Map<String, Object> genotypeAttributes = subsetAttributes(g.commonInfo, keysToPreserve); genotypes.add( new Genotype( g.getSampleName(), g.getAlleles(), g.getLog10PError(), g.getFilters(), genotypeAttributes, g.isPhased())); } return builder.genotypes(genotypes).attributes(attributes); }
public static VariantContext createVariantContextWithPaddedAlleles( VariantContext inputVC, boolean refBaseShouldBeAppliedToEndOfAlleles) { // see if we need to pad common reference base from all alleles boolean padVC; // We need to pad a VC with a common base if the length of the reference allele is less than the // length of the VariantContext. // This happens because the position of e.g. an indel is always one before the actual event (as // per VCF convention). long locLength = (inputVC.getEnd() - inputVC.getStart()) + 1; if (inputVC.hasSymbolicAlleles()) padVC = true; else if (inputVC.getReference().length() == locLength) padVC = false; else if (inputVC.getReference().length() == locLength - 1) padVC = true; else throw new IllegalArgumentException( "Badly formed variant context at location " + String.valueOf(inputVC.getStart()) + " in contig " + inputVC.getChr() + ". Reference length must be at most one base shorter than location size"); // nothing to do if we don't need to pad bases if (padVC) { if (!inputVC.hasReferenceBaseForIndel()) throw new ReviewedStingException( "Badly formed variant context at location " + inputVC.getChr() + ":" + inputVC.getStart() + "; no padded reference base is available."); Byte refByte = inputVC.getReferenceBaseForIndel(); List<Allele> alleles = new ArrayList<Allele>(); for (Allele a : inputVC.getAlleles()) { // get bases for current allele and create a new one with trimmed bases if (a.isSymbolic()) { alleles.add(a); } else { String newBases; if (refBaseShouldBeAppliedToEndOfAlleles) newBases = a.getBaseString() + new String(new byte[] {refByte}); else newBases = new String(new byte[] {refByte}) + a.getBaseString(); alleles.add(Allele.create(newBases, a.isReference())); } } // now we can recreate new genotypes with trimmed alleles GenotypesContext genotypes = GenotypesContext.create(inputVC.getNSamples()); for (final Genotype g : inputVC.getGenotypes()) { List<Allele> inAlleles = g.getAlleles(); List<Allele> newGenotypeAlleles = new ArrayList<Allele>(g.getAlleles().size()); for (Allele a : inAlleles) { if (a.isCalled()) { if (a.isSymbolic()) { newGenotypeAlleles.add(a); } else { String newBases; if (refBaseShouldBeAppliedToEndOfAlleles) newBases = a.getBaseString() + new String(new byte[] {refByte}); else newBases = new String(new byte[] {refByte}) + a.getBaseString(); newGenotypeAlleles.add(Allele.create(newBases, a.isReference())); } } else { // add no-call allele newGenotypeAlleles.add(Allele.NO_CALL); } } genotypes.add( new Genotype( g.getSampleName(), newGenotypeAlleles, g.getLog10PError(), g.getFilters(), g.getAttributes(), g.isPhased())); } return new VariantContextBuilder(inputVC).alleles(alleles).genotypes(genotypes).make(); } else return inputVC; }
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(); }