/**
* Compute GLs at a given locus. Entry point for engine calls from UGCalcLikelihoods.
*
* @param tracker the meta data tracker
* @param refContext the reference base
* @param rawContext contextual information around the locus
* @param perReadAlleleLikelihoodMap Map to store per-sample, per-read, per-allele likelihoods
* (only used for indels)
* @return the VariantContext object
*/
public VariantContext calculateLikelihoods(
final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext,
final Map<String, org.broadinstitute.sting.utils.genotyper.PerReadAlleleLikelihoodMap>
perReadAlleleLikelihoodMap) {
final List<GenotypeLikelihoodsCalculationModel.Model> models =
getGLModelsToUse(tracker, refContext, rawContext);
if (models.isEmpty()) {
return null;
}
for (final GenotypeLikelihoodsCalculationModel.Model model : models) {
final Map<String, AlignmentContext> stratifiedContexts =
getFilteredAndStratifiedContexts(UAC, refContext, rawContext, model);
// return the first valid one we encounter
if (stratifiedContexts != null)
return calculateLikelihoods(
tracker,
refContext,
stratifiedContexts,
AlignmentContextUtils.ReadOrientation.COMPLETE,
null,
true,
model,
perReadAlleleLikelihoodMap);
}
return null;
}
/**
* Compute genotypes at a given locus. Entry point for engine calls from UGCallVariants.
*
* @param tracker the meta data tracker
* @param refContext the reference base
* @param rawContext contextual information around the locus
* @param vc the GL-annotated variant context
* @return the VariantCallContext object
*/
public VariantCallContext calculateGenotypes(
final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext,
final VariantContext vc) {
final List<GenotypeLikelihoodsCalculationModel.Model> models =
getGLModelsToUse(tracker, refContext, rawContext);
if (models.isEmpty()) {
return null;
}
// return the first one
final GenotypeLikelihoodsCalculationModel.Model model = models.get(0);
final Map<String, AlignmentContext> stratifiedContexts =
getFilteredAndStratifiedContexts(UAC, refContext, rawContext, model);
return calculateGenotypes(tracker, refContext, rawContext, stratifiedContexts, vc, model, null);
}
/**
* Read in a list of ExactCall objects from reader, keeping only those with starts in startsToKeep
* or all sites (if this is empty)
*
* @param reader a just-opened reader sitting at the start of the file
* @param startsToKeep a list of start position of the calls to keep, or empty if all calls should
* be kept
* @param parser a genome loc parser to create genome locs
* @return a list of ExactCall objects in reader
* @throws IOException
*/
public static List<ExactCall> readExactLog(
final BufferedReader reader, final List<Integer> startsToKeep, GenomeLocParser parser)
throws IOException {
if (reader == null) throw new IllegalArgumentException("reader cannot be null");
if (startsToKeep == null) throw new IllegalArgumentException("startsToKeep cannot be null");
if (parser == null) throw new IllegalArgumentException("GenomeLocParser cannot be null");
List<ExactCall> calls = new LinkedList<ExactCall>();
// skip the header line
reader.readLine();
// skip the first "type" line
reader.readLine();
while (true) {
final VariantContextBuilder builder = new VariantContextBuilder();
final List<Allele> alleles = new ArrayList<Allele>();
final List<Genotype> genotypes = new ArrayList<Genotype>();
final double[] posteriors = new double[2];
final double[] priors = MathUtils.normalizeFromLog10(new double[] {0.5, 0.5}, true);
final List<Integer> mle = new ArrayList<Integer>();
final Map<Allele, Double> log10pNonRefByAllele = new HashMap<Allele, Double>();
long runtimeNano = -1;
GenomeLoc currentLoc = null;
while (true) {
final String line = reader.readLine();
if (line == null) return calls;
final String[] parts = line.split("\t");
final GenomeLoc lineLoc = parser.parseGenomeLoc(parts[0]);
final String variable = parts[1];
final String key = parts[2];
final String value = parts[3];
if (currentLoc == null) currentLoc = lineLoc;
if (variable.equals("type")) {
if (startsToKeep.isEmpty() || startsToKeep.contains(currentLoc.getStart())) {
builder.alleles(alleles);
final int stop = currentLoc.getStart() + alleles.get(0).length() - 1;
builder.chr(currentLoc.getContig()).start(currentLoc.getStart()).stop(stop);
builder.genotypes(genotypes);
final int[] mleInts = ArrayUtils.toPrimitive(mle.toArray(new Integer[] {}));
final AFCalcResult result =
new AFCalcResult(mleInts, 1, alleles, posteriors, priors, log10pNonRefByAllele);
calls.add(new ExactCall(builder.make(), runtimeNano, result));
}
break;
} else if (variable.equals("allele")) {
final boolean isRef = key.equals("0");
alleles.add(Allele.create(value, isRef));
} else if (variable.equals("PL")) {
final GenotypeBuilder gb = new GenotypeBuilder(key);
gb.PL(GenotypeLikelihoods.fromPLField(value).getAsPLs());
genotypes.add(gb.make());
} else if (variable.equals("log10PosteriorOfAFEq0")) {
posteriors[0] = Double.valueOf(value);
} else if (variable.equals("log10PosteriorOfAFGt0")) {
posteriors[1] = Double.valueOf(value);
} else if (variable.equals("MLE")) {
mle.add(Integer.valueOf(value));
} else if (variable.equals("pNonRefByAllele")) {
final Allele a = Allele.create(key);
log10pNonRefByAllele.put(a, Double.valueOf(value));
} else if (variable.equals("runtime.nano")) {
runtimeNano = Long.valueOf(value);
} else {
// nothing to do
}
}
}
}
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();
}
/**
* Compute full calls at a given locus. Entry point for engine calls from the UnifiedGenotyper.
*
* <p>If allSamples != null, then the output variantCallContext is guarenteed to contain a
* genotype for every sample in allSamples. If it's null there's no such guarentee. Providing this
* argument is critical when the resulting calls will be written to a VCF file.
*
* @param tracker the meta data tracker
* @param refContext the reference base
* @param rawContext contextual information around the locus
* @param allSamples set of all sample names that we might call (i.e., those in the VCF header)
* @return the VariantCallContext object
*/
public List<VariantCallContext> calculateLikelihoodsAndGenotypes(
final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext,
final Set<String> allSamples) {
final List<VariantCallContext> results = new ArrayList<VariantCallContext>(2);
final List<GenotypeLikelihoodsCalculationModel.Model> models =
getGLModelsToUse(tracker, refContext, rawContext);
final Map<String, org.broadinstitute.sting.utils.genotyper.PerReadAlleleLikelihoodMap>
perReadAlleleLikelihoodMap =
new HashMap<
String, org.broadinstitute.sting.utils.genotyper.PerReadAlleleLikelihoodMap>();
if (models.isEmpty()) {
results.add(
UAC.OutputMode == OUTPUT_MODE.EMIT_ALL_SITES
&& UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE.GENOTYPE_GIVEN_ALLELES
? generateEmptyContext(tracker, refContext, null, rawContext)
: null);
} else {
for (final GenotypeLikelihoodsCalculationModel.Model model : models) {
perReadAlleleLikelihoodMap.clear();
final Map<String, AlignmentContext> stratifiedContexts =
getFilteredAndStratifiedContexts(UAC, refContext, rawContext, model);
if (stratifiedContexts == null) {
results.add(
UAC.OutputMode == OUTPUT_MODE.EMIT_ALL_SITES
&& UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE
.GENOTYPE_GIVEN_ALLELES
? generateEmptyContext(tracker, refContext, null, rawContext)
: null);
} else {
final VariantContext vc =
calculateLikelihoods(
tracker,
refContext,
stratifiedContexts,
AlignmentContextUtils.ReadOrientation.COMPLETE,
null,
true,
model,
perReadAlleleLikelihoodMap);
if (vc != null)
results.add(
calculateGenotypes(
tracker,
refContext,
rawContext,
stratifiedContexts,
vc,
model,
true,
perReadAlleleLikelihoodMap));
}
}
}
return results;
}