// decide whether we are currently processing SNPs, indels, neither, or both
private List<GenotypeLikelihoodsCalculationModel.Model> getGLModelsToUse(
final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext) {
final List<GenotypeLikelihoodsCalculationModel.Model> models =
new ArrayList<GenotypeLikelihoodsCalculationModel.Model>(2);
String modelPrefix = "";
if (UAC.GLmodel.name().toUpperCase().contains("BOTH"))
modelPrefix = UAC.GLmodel.name().toUpperCase().replaceAll("BOTH", "");
if (!UAC.GLmodel.name().contains(GPSTRING)
&& UAC.samplePloidy != VariantContextUtils.DEFAULT_PLOIDY)
modelPrefix = GPSTRING + modelPrefix;
// if we're genotyping given alleles and we have a requested SNP at this position, do SNP
if (UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE.GENOTYPE_GIVEN_ALLELES) {
final VariantContext vcInput =
getVCFromAllelesRod(
tracker, refContext, rawContext.getLocation(), false, logger, UAC.alleles);
if (vcInput == null) return models;
if (vcInput.isSNP()) {
// ignore SNPs if the user chose INDEL mode only
if (UAC.GLmodel.name().toUpperCase().contains("BOTH")
|| UAC.GLmodel.name().toUpperCase().contains("SNP"))
models.add(GenotypeLikelihoodsCalculationModel.Model.valueOf(modelPrefix + "SNP"));
} else if (vcInput.isIndel() || vcInput.isMixed()) {
// ignore INDELs if the user chose SNP mode only
if (UAC.GLmodel.name().toUpperCase().contains("BOTH")
|| UAC.GLmodel.name().toUpperCase().contains("INDEL"))
models.add(GenotypeLikelihoodsCalculationModel.Model.valueOf(modelPrefix + "INDEL"));
}
// No support for other types yet
} else {
if (UAC.GLmodel.name().toUpperCase().contains("BOTH")) {
models.add(GenotypeLikelihoodsCalculationModel.Model.valueOf(modelPrefix + "SNP"));
models.add(GenotypeLikelihoodsCalculationModel.Model.valueOf(modelPrefix + "INDEL"));
} else {
models.add(
GenotypeLikelihoodsCalculationModel.Model.valueOf(
modelPrefix + UAC.GLmodel.name().toUpperCase()));
}
}
return models;
}
static Map<String, Object> mergeVariantContextAttributes(VariantContext vc1, VariantContext vc2) {
Map<String, Object> mergedAttribs = new HashMap<String, Object>();
List<VariantContext> vcList = new LinkedList<VariantContext>();
vcList.add(vc1);
vcList.add(vc2);
String[] MERGE_OR_ATTRIBS = {VCFConstants.DBSNP_KEY};
for (String orAttrib : MERGE_OR_ATTRIBS) {
boolean attribVal = false;
for (VariantContext vc : vcList) {
attribVal = vc.getAttributeAsBoolean(orAttrib, false);
if (attribVal) // already true, so no reason to continue:
break;
}
mergedAttribs.put(orAttrib, attribVal);
}
return mergedAttribs;
}
/**
* 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();
}
/**
* Main entry function to calculate genotypes of a given VC with corresponding GL's
*
* @param tracker Tracker
* @param refContext Reference context
* @param rawContext Raw context
* @param stratifiedContexts Stratified alignment contexts
* @param vc Input VC
* @param model GL calculation model
* @param inheritAttributesFromInputVC Output VC will contain attributes inherited from input vc
* @return VC with assigned genotypes
*/
public VariantCallContext calculateGenotypes(
final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext,
Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc,
final GenotypeLikelihoodsCalculationModel.Model model,
final boolean inheritAttributesFromInputVC,
final Map<String, org.broadinstitute.sting.utils.genotyper.PerReadAlleleLikelihoodMap>
perReadAlleleLikelihoodMap) {
boolean limitedContext =
tracker == null || refContext == null || rawContext == null || stratifiedContexts == null;
// initialize the data for this thread if that hasn't been done yet
if (afcm.get() == null) {
afcm.set(AFCalcFactory.createAFCalc(UAC, N, logger));
}
// estimate our confidence in a reference call and return
if (vc.getNSamples() == 0) {
if (limitedContext) return null;
return (UAC.OutputMode != OUTPUT_MODE.EMIT_ALL_SITES
? estimateReferenceConfidence(vc, stratifiedContexts, getTheta(model), false, 1.0)
: generateEmptyContext(tracker, refContext, stratifiedContexts, rawContext));
}
AFCalcResult AFresult = afcm.get().getLog10PNonRef(vc, getAlleleFrequencyPriors(model));
// is the most likely frequency conformation AC=0 for all alternate alleles?
boolean bestGuessIsRef = true;
// determine which alternate alleles have AF>0
final List<Allele> myAlleles = new ArrayList<Allele>(vc.getAlleles().size());
final List<Integer> alleleCountsofMLE = new ArrayList<Integer>(vc.getAlleles().size());
myAlleles.add(vc.getReference());
for (int i = 0; i < AFresult.getAllelesUsedInGenotyping().size(); i++) {
final Allele alternateAllele = AFresult.getAllelesUsedInGenotyping().get(i);
if (alternateAllele.isReference()) continue;
// we are non-ref if the probability of being non-ref > the emit confidence.
// the emit confidence is phred-scaled, say 30 => 10^-3.
// the posterior AF > 0 is log10: -5 => 10^-5
// we are non-ref if 10^-5 < 10^-3 => -5 < -3
final boolean isNonRef =
AFresult.isPolymorphic(alternateAllele, UAC.STANDARD_CONFIDENCE_FOR_EMITTING / -10.0);
// if the most likely AC is not 0, then this is a good alternate allele to use
if (isNonRef) {
myAlleles.add(alternateAllele);
alleleCountsofMLE.add(AFresult.getAlleleCountAtMLE(alternateAllele));
bestGuessIsRef = false;
}
// if in GENOTYPE_GIVEN_ALLELES mode, we still want to allow the use of a poor allele
else if (UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE.GENOTYPE_GIVEN_ALLELES) {
myAlleles.add(alternateAllele);
alleleCountsofMLE.add(AFresult.getAlleleCountAtMLE(alternateAllele));
}
}
final double PoFGT0 = Math.pow(10, AFresult.getLog10PosteriorOfAFGT0());
// note the math.abs is necessary because -10 * 0.0 => -0.0 which isn't nice
final double phredScaledConfidence =
Math.abs(
!bestGuessIsRef
|| UAC.GenotypingMode
== GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE
.GENOTYPE_GIVEN_ALLELES
? -10 * AFresult.getLog10PosteriorOfAFEq0()
: -10 * AFresult.getLog10PosteriorOfAFGT0());
// return a null call if we don't pass the confidence cutoff or the most likely allele frequency
// is zero
if (UAC.OutputMode != OUTPUT_MODE.EMIT_ALL_SITES
&& !passesEmitThreshold(phredScaledConfidence, bestGuessIsRef)) {
// technically, at this point our confidence in a reference call isn't accurately estimated
// because it didn't take into account samples with no data, so let's get a better estimate
return limitedContext
? null
: estimateReferenceConfidence(vc, stratifiedContexts, getTheta(model), true, PoFGT0);
}
// start constructing the resulting VC
final GenomeLoc loc = genomeLocParser.createGenomeLoc(vc);
final VariantContextBuilder builder =
new VariantContextBuilder(
"UG_call", loc.getContig(), loc.getStart(), loc.getStop(), myAlleles);
builder.log10PError(phredScaledConfidence / -10.0);
if (!passesCallThreshold(phredScaledConfidence)) builder.filters(filter);
// create the genotypes
final GenotypesContext genotypes = afcm.get().subsetAlleles(vc, myAlleles, true, ploidy);
builder.genotypes(genotypes);
// print out stats if we have a writer
if (verboseWriter != null && !limitedContext)
printVerboseData(refContext.getLocus().toString(), vc, PoFGT0, phredScaledConfidence, model);
// *** note that calculating strand bias involves overwriting data structures, so we do that
// last
final HashMap<String, Object> attributes = new HashMap<String, Object>();
// inherit attributed from input vc if requested
if (inheritAttributesFromInputVC) attributes.putAll(vc.getAttributes());
// if the site was downsampled, record that fact
if (!limitedContext && rawContext.hasPileupBeenDownsampled())
attributes.put(VCFConstants.DOWNSAMPLED_KEY, true);
if (UAC.ANNOTATE_NUMBER_OF_ALLELES_DISCOVERED)
attributes.put(NUMBER_OF_DISCOVERED_ALLELES_KEY, vc.getAlternateAlleles().size());
// add the MLE AC and AF annotations
if (alleleCountsofMLE.size() > 0) {
attributes.put(VCFConstants.MLE_ALLELE_COUNT_KEY, alleleCountsofMLE);
final int AN = builder.make().getCalledChrCount();
final ArrayList<Double> MLEfrequencies = new ArrayList<Double>(alleleCountsofMLE.size());
// the MLEAC is allowed to be larger than the AN (e.g. in the case of all PLs being 0, the GT
// is ./. but the exact model may arbitrarily choose an AC>1)
for (int AC : alleleCountsofMLE) MLEfrequencies.add(Math.min(1.0, (double) AC / (double) AN));
attributes.put(VCFConstants.MLE_ALLELE_FREQUENCY_KEY, MLEfrequencies);
}
if (UAC.COMPUTE_SLOD && !limitedContext && !bestGuessIsRef) {
// final boolean DEBUG_SLOD = false;
// the overall lod
// double overallLog10PofNull = AFresult.log10AlleleFrequencyPosteriors[0];
double overallLog10PofF = AFresult.getLog10LikelihoodOfAFGT0();
// if ( DEBUG_SLOD ) System.out.println("overallLog10PofF=" + overallLog10PofF);
List<Allele> allAllelesToUse = builder.make().getAlleles();
// the forward lod
VariantContext vcForward =
calculateLikelihoods(
tracker,
refContext,
stratifiedContexts,
AlignmentContextUtils.ReadOrientation.FORWARD,
allAllelesToUse,
false,
model,
perReadAlleleLikelihoodMap);
AFresult = afcm.get().getLog10PNonRef(vcForward, getAlleleFrequencyPriors(model));
// double[] normalizedLog10Posteriors =
// MathUtils.normalizeFromLog10(AFresult.log10AlleleFrequencyPosteriors, true);
double forwardLog10PofNull = AFresult.getLog10LikelihoodOfAFEq0();
double forwardLog10PofF = AFresult.getLog10LikelihoodOfAFGT0();
// if ( DEBUG_SLOD ) System.out.println("forwardLog10PofNull=" + forwardLog10PofNull + ",
// forwardLog10PofF=" + forwardLog10PofF);
// the reverse lod
VariantContext vcReverse =
calculateLikelihoods(
tracker,
refContext,
stratifiedContexts,
AlignmentContextUtils.ReadOrientation.REVERSE,
allAllelesToUse,
false,
model,
perReadAlleleLikelihoodMap);
AFresult = afcm.get().getLog10PNonRef(vcReverse, getAlleleFrequencyPriors(model));
// normalizedLog10Posteriors =
// MathUtils.normalizeFromLog10(AFresult.log10AlleleFrequencyPosteriors, true);
double reverseLog10PofNull = AFresult.getLog10LikelihoodOfAFEq0();
double reverseLog10PofF = AFresult.getLog10LikelihoodOfAFGT0();
// if ( DEBUG_SLOD ) System.out.println("reverseLog10PofNull=" + reverseLog10PofNull + ",
// reverseLog10PofF=" + reverseLog10PofF);
double forwardLod = forwardLog10PofF + reverseLog10PofNull - overallLog10PofF;
double reverseLod = reverseLog10PofF + forwardLog10PofNull - overallLog10PofF;
// if ( DEBUG_SLOD ) System.out.println("forward lod=" + forwardLod + ", reverse lod=" +
// reverseLod);
// strand score is max bias between forward and reverse strands
double strandScore = Math.max(forwardLod, reverseLod);
// rescale by a factor of 10
strandScore *= 10.0;
// logger.debug(String.format("SLOD=%f", strandScore));
if (!Double.isNaN(strandScore)) attributes.put("SB", strandScore);
}
// finish constructing the resulting VC
builder.attributes(attributes);
VariantContext vcCall = builder.make();
// if we are subsetting alleles (either because there were too many or because some were not
// polymorphic)
// then we may need to trim the alleles (because the original VariantContext may have had to pad
// at the end).
if (myAlleles.size() != vc.getAlleles().size()
&& !limitedContext) // limitedContext callers need to handle allele trimming on their own to
// keep their perReadAlleleLikelihoodMap alleles in sync
vcCall = VariantContextUtils.reverseTrimAlleles(vcCall);
if (annotationEngine != null
&& !limitedContext) { // limitedContext callers need to handle annotations on their own by
// calling their own annotationEngine
// Note: we want to use the *unfiltered* and *unBAQed* context for the annotations
final ReadBackedPileup pileup = rawContext.getBasePileup();
stratifiedContexts = AlignmentContextUtils.splitContextBySampleName(pileup);
vcCall =
annotationEngine.annotateContext(
tracker, refContext, stratifiedContexts, vcCall, perReadAlleleLikelihoodMap);
}
return new VariantCallContext(vcCall, confidentlyCalled(phredScaledConfidence, PoFGT0));
}
/**
* 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;
}