/**
* Helper method to subset a VC record, modifying some metadata stored in the INFO field (i.e. AN,
* AC, AF).
*
* @param vc the VariantContext record to subset
* @param samples the samples to extract
* @return the subsetted VariantContext
*/
private VariantContext subsetRecord(VariantContext vc, Set<String> samples) {
if (samples == null || samples.isEmpty()) return vc;
ArrayList<Genotype> genotypes = new ArrayList<Genotype>();
for (Map.Entry<String, Genotype> genotypePair : vc.getGenotypes().entrySet()) {
if (samples.contains(genotypePair.getKey())) genotypes.add(genotypePair.getValue());
}
VariantContext sub = vc.subContextFromGenotypes(genotypes, vc.getAlleles());
// if we have fewer alternate alleles in the selected VC than in the original VC, we need to
// strip out the GL/PLs (because they are no longer accurate)
if (vc.getAlleles().size() != sub.getAlleles().size())
sub = VariantContext.modifyGenotypes(sub, VariantContextUtils.stripPLs(vc.getGenotypes()));
HashMap<String, Object> attributes = new HashMap<String, Object>(sub.getAttributes());
int depth = 0;
for (String sample : sub.getSampleNames()) {
Genotype g = sub.getGenotype(sample);
if (g.isNotFiltered() && g.isCalled()) {
String dp = (String) g.getAttribute("DP");
if (dp != null
&& !dp.equals(VCFConstants.MISSING_DEPTH_v3)
&& !dp.equals(VCFConstants.MISSING_VALUE_v4)) {
depth += Integer.valueOf(dp);
}
}
}
if (KEEP_ORIGINAL_CHR_COUNTS) {
if (attributes.containsKey(VCFConstants.ALLELE_COUNT_KEY))
attributes.put("AC_Orig", attributes.get(VCFConstants.ALLELE_COUNT_KEY));
if (attributes.containsKey(VCFConstants.ALLELE_FREQUENCY_KEY))
attributes.put("AF_Orig", attributes.get(VCFConstants.ALLELE_FREQUENCY_KEY));
if (attributes.containsKey(VCFConstants.ALLELE_NUMBER_KEY))
attributes.put("AN_Orig", attributes.get(VCFConstants.ALLELE_NUMBER_KEY));
}
VariantContextUtils.calculateChromosomeCounts(sub, attributes, false);
attributes.put("DP", depth);
sub = VariantContext.modifyAttributes(sub, attributes);
return sub;
}
@Test(dataProvider = "RepeatDetectorTest")
public void testRepeatDetectorTest(RepeatDetectorTest cfg) {
// test alleles are equal
Assert.assertEquals(
VariantContextUtils.isTandemRepeat(cfg.vc, cfg.ref.getBytes()), cfg.isTrueRepeat);
}
@Test(dataProvider = "mergeAlleles")
public void testMergeAlleles(MergeAllelesTest cfg) {
final List<VariantContext> inputs = new ArrayList<VariantContext>();
int i = 0;
for (final List<Allele> alleles : cfg.inputs) {
final String name = "vcf" + ++i;
inputs.add(makeVC(name, alleles));
}
final List<String> priority = vcs2priority(inputs);
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
inputs,
priority,
VariantContextUtils.FilteredRecordMergeType.KEEP_IF_ANY_UNFILTERED,
VariantContextUtils.GenotypeMergeType.PRIORITIZE,
false,
false,
"set",
false,
false);
Assert.assertEquals(merged.getAlleles(), cfg.expected);
}
@Test(dataProvider = "mergeFiltered")
public void testMergeFiltered(MergeFilteredTest cfg) {
final List<String> priority = vcs2priority(cfg.inputs);
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
cfg.inputs,
priority,
cfg.type,
VariantContextUtils.GenotypeMergeType.PRIORITIZE,
true,
false,
"set",
false,
false);
// test alleles are equal
Assert.assertEquals(merged.getAlleles(), cfg.expected.getAlleles());
// test set field
Assert.assertEquals(merged.getAttribute("set"), cfg.setExpected);
// test filter field
Assert.assertEquals(merged.getFilters(), cfg.expected.getFilters());
}
@Test
public void testAnnotationSet() {
for (final boolean annotate : Arrays.asList(true, false)) {
for (final String set : Arrays.asList("set", "combine", "x")) {
final List<String> priority = Arrays.asList("1", "2");
VariantContext vc1 = makeVC("1", Arrays.asList(Aref, T), VariantContext.PASSES_FILTERS);
VariantContext vc2 = makeVC("2", Arrays.asList(Aref, T), VariantContext.PASSES_FILTERS);
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
Arrays.asList(vc1, vc2),
priority,
VariantContextUtils.FilteredRecordMergeType.KEEP_IF_ANY_UNFILTERED,
VariantContextUtils.GenotypeMergeType.PRIORITIZE,
annotate,
false,
set,
false,
false);
if (annotate)
Assert.assertEquals(merged.getAttribute(set), VariantContextUtils.MERGE_INTERSECTION);
else Assert.assertFalse(merged.hasAttribute(set));
}
}
}
static boolean mergeIntoMNPvalidationCheck(
GenomeLocParser genomeLocParser, VariantContext vc1, VariantContext vc2) {
GenomeLoc loc1 = VariantContextUtils.getLocation(genomeLocParser, vc1);
GenomeLoc loc2 = VariantContextUtils.getLocation(genomeLocParser, vc2);
if (!loc1.onSameContig(loc2))
throw new ReviewedStingException("Can only merge vc1, vc2 if on the same chromosome");
if (!loc1.isBefore(loc2))
throw new ReviewedStingException("Can only merge if vc1 is BEFORE vc2");
if (vc1.isFiltered() || vc2.isFiltered()) return false;
if (!vc1.getSampleNames()
.equals(vc2.getSampleNames())) // vc1, vc2 refer to different sample sets
return false;
if (!allGenotypesAreUnfilteredAndCalled(vc1) || !allGenotypesAreUnfilteredAndCalled(vc2))
return false;
return true;
}
@Test(expectedExceptions = UserException.class)
public void testMergeGenotypesRequireUnique() {
final VariantContext vc1 = makeVC("1", Arrays.asList(Aref, T), makeG("s1", Aref, T, -1));
final VariantContext vc2 = makeVC("2", Arrays.asList(Aref, T), makeG("s1", Aref, T, -2));
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
Arrays.asList(vc1, vc2),
null,
VariantContextUtils.FilteredRecordMergeType.KEEP_IF_ANY_UNFILTERED,
VariantContextUtils.GenotypeMergeType.REQUIRE_UNIQUE,
false,
false,
"set",
false,
false);
}
public void update2(
VariantContext eval,
VariantContext comp,
RefMetaDataTracker tracker,
ReferenceContext ref,
AlignmentContext context) {
if (eval == null || (getWalker().ignoreAC0Sites() && eval.isMonomorphicInSamples())) return;
final Type type = getType(eval);
if (type == null) return;
TypeSampleMap titvTable = null;
// update DP, if possible
if (eval.hasAttribute(VCFConstants.DEPTH_KEY)) depthPerSample.inc(type, ALL);
// update counts
allVariantCounts.inc(type, ALL);
// type specific calculations
if (type == Type.SNP && eval.isBiallelic()) {
titvTable =
VariantContextUtils.isTransition(eval) ? transitionsPerSample : transversionsPerSample;
titvTable.inc(type, ALL);
}
// novelty calculation
if (comp != null || (type == Type.CNV && overlapsKnownCNV(eval)))
knownVariantCounts.inc(type, ALL);
// per sample metrics
for (final Genotype g : eval.getGenotypes()) {
if (!g.isNoCall() && !g.isHomRef()) {
countsPerSample.inc(type, g.getSampleName());
// update transition / transversion ratio
if (titvTable != null) titvTable.inc(type, g.getSampleName());
if (g.hasDP()) depthPerSample.inc(type, g.getSampleName());
}
}
}
@Test(dataProvider = "mergeGenotypes")
public void testMergeGenotypes(MergeGenotypesTest cfg) {
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
cfg.inputs,
cfg.priority,
VariantContextUtils.FilteredRecordMergeType.KEEP_IF_ANY_UNFILTERED,
VariantContextUtils.GenotypeMergeType.PRIORITIZE,
true,
false,
"set",
false,
false);
// test alleles are equal
Assert.assertEquals(merged.getAlleles(), cfg.expected.getAlleles());
// test genotypes
assertGenotypesAreMostlyEqual(merged.getGenotypes(), cfg.expected.getGenotypes());
}
@Test
public void testMergeGenotypesUniquify() {
final VariantContext vc1 = makeVC("1", Arrays.asList(Aref, T), makeG("s1", Aref, T, -1));
final VariantContext vc2 = makeVC("2", Arrays.asList(Aref, T), makeG("s1", Aref, T, -2));
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
Arrays.asList(vc1, vc2),
null,
VariantContextUtils.FilteredRecordMergeType.KEEP_IF_ANY_UNFILTERED,
VariantContextUtils.GenotypeMergeType.UNIQUIFY,
false,
false,
"set",
false,
false);
// test genotypes
Assert.assertEquals(
merged.getSampleNames(), new HashSet<String>(Arrays.asList("s1.1", "s1.2")));
}
/**
* Method for creating JexlVCMatchExp from input walker arguments names and exps. These two arrays
* contain the name associated with each JEXL expression. initializeMatchExps will parse each
* expression and return a list of JexlVCMatchExp, in order, that correspond to the names and
* exps. These are suitable input to match() below.
*
* @param names names
* @param exps expressions
* @return list of matches
*/
public static List<JexlVCMatchExp> initializeMatchExps(String[] names, String[] exps) {
if (names == null || exps == null)
throw new ReviewedStingException(
"BUG: neither names nor exps can be null: names "
+ Arrays.toString(names)
+ " exps="
+ Arrays.toString(exps));
if (names.length != exps.length)
throw new UserException(
"Inconsistent number of provided filter names and expressions: names="
+ Arrays.toString(names)
+ " exps="
+ Arrays.toString(exps));
Map<String, String> map = new HashMap<String, String>();
for (int i = 0; i < names.length; i++) {
map.put(names[i], exps[i]);
}
return VariantContextUtils.initializeMatchExps(map);
}
@Test(dataProvider = "simplemergersiddata")
public void testRSIDMerge(SimpleMergeRSIDTest cfg) {
VariantContext snpVC1 = makeVC("snpvc1", Arrays.asList(Aref, T));
final List<VariantContext> inputs = new ArrayList<VariantContext>();
for (final String id : cfg.inputs) {
inputs.add(new VariantContextBuilder(snpVC1).id(id).make());
}
final VariantContext merged =
VariantContextUtils.simpleMerge(
genomeLocParser,
inputs,
null,
VariantContextUtils.FilteredRecordMergeType.KEEP_IF_ANY_UNFILTERED,
VariantContextUtils.GenotypeMergeType.UNSORTED,
false,
false,
"set",
false,
false);
Assert.assertEquals(merged.getID(), cfg.expected);
}
@Test(dataProvider = "ReverseClippingPositionTestProvider")
public void testReverseClippingPositionTestProvider(ReverseClippingPositionTestProvider cfg) {
int result =
VariantContextUtils.computeReverseClipping(cfg.alleles, cfg.ref.getBytes(), 0, false);
Assert.assertEquals(result, cfg.expectedClip);
}
/** Initialize the stratifications, evaluations, evaluation contexts, and reporting object */
public void initialize() {
// Just list the modules, and exit quickly.
if (LIST) {
variantEvalUtils.listModulesAndExit();
}
// maintain the full list of comps
comps.addAll(compsProvided);
if (dbsnp.dbsnp.isBound()) {
comps.add(dbsnp.dbsnp);
knowns.add(dbsnp.dbsnp);
}
// Add a dummy comp track if none exists
if (comps.size() == 0)
comps.add(
new RodBinding<VariantContext>(VariantContext.class, "none", "UNBOUND", "", new Tags()));
// Set up set of additional knowns
for (RodBinding<VariantContext> compRod : comps) {
if (KNOWN_NAMES.contains(compRod.getName())) knowns.add(compRod);
}
// Now that we have all the rods categorized, determine the sample list from the eval rods.
Map<String, VCFHeader> vcfRods = VCFUtils.getVCFHeadersFromRods(getToolkit(), evals);
Set<String> vcfSamples =
SampleUtils.getSampleList(vcfRods, VariantContextUtils.GenotypeMergeType.REQUIRE_UNIQUE);
// Load the sample list
sampleNamesForEvaluation.addAll(
SampleUtils.getSamplesFromCommandLineInput(vcfSamples, SAMPLE_EXPRESSIONS));
numSamples = NUM_SAMPLES > 0 ? NUM_SAMPLES : sampleNamesForEvaluation.size();
if (Arrays.asList(STRATIFICATIONS_TO_USE).contains("Sample")) {
sampleNamesForStratification.addAll(sampleNamesForEvaluation);
}
sampleNamesForStratification.add(ALL_SAMPLE_NAME);
// Initialize select expressions
for (VariantContextUtils.JexlVCMatchExp jexl :
VariantContextUtils.initializeMatchExps(SELECT_NAMES, SELECT_EXPS)) {
SortableJexlVCMatchExp sjexl = new SortableJexlVCMatchExp(jexl.name, jexl.exp);
jexlExpressions.add(sjexl);
}
// Initialize the set of stratifications and evaluations to use
stratificationObjects =
variantEvalUtils.initializeStratificationObjects(
this, NO_STANDARD_STRATIFICATIONS, STRATIFICATIONS_TO_USE);
Set<Class<? extends VariantEvaluator>> evaluationObjects =
variantEvalUtils.initializeEvaluationObjects(NO_STANDARD_MODULES, MODULES_TO_USE);
for (VariantStratifier vs : getStratificationObjects()) {
if (vs.getName().equals("Filter")) byFilterIsEnabled = true;
else if (vs.getName().equals("Sample")) perSampleIsEnabled = true;
}
if (intervalsFile != null) {
boolean fail = true;
for (final VariantStratifier vs : stratificationObjects) {
if (vs.getClass().equals(IntervalStratification.class)) fail = false;
}
if (fail)
throw new UserException.BadArgumentValue(
"ST", "stratIntervals argument provided but -ST IntervalStratification not provided");
}
// Initialize the evaluation contexts
evaluationContexts =
variantEvalUtils.initializeEvaluationContexts(
stratificationObjects, evaluationObjects, null, null);
// Initialize report table
report = variantEvalUtils.initializeGATKReport(stratificationObjects, evaluationObjects);
// Load ancestral alignments
if (ancestralAlignmentsFile != null) {
try {
ancestralAlignments = new IndexedFastaSequenceFile(ancestralAlignmentsFile);
} catch (FileNotFoundException e) {
throw new ReviewedStingException(
String.format(
"The ancestral alignments file, '%s', could not be found",
ancestralAlignmentsFile.getAbsolutePath()));
}
}
// initialize CNVs
if (knownCNVsFile != null) {
knownCNVsByContig = createIntervalTreeByContig(knownCNVsFile);
}
}
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();
}
/**
* Subset VC record if necessary and emit the modified record (provided it satisfies criteria for
* printing)
*
* @param tracker the ROD tracker
* @param ref reference information
* @param context alignment info
* @return 1 if the record was printed to the output file, 0 if otherwise
*/
@Override
public Integer map(RefMetaDataTracker tracker, ReferenceContext ref, AlignmentContext context) {
if (tracker == null) return 0;
Collection<VariantContext> vcs =
tracker.getValues(variantCollection.variants, context.getLocation());
if (vcs == null || vcs.size() == 0) {
return 0;
}
for (VariantContext vc : vcs) {
if (MENDELIAN_VIOLATIONS) {
boolean foundMV = false;
for (MendelianViolation mv : mvSet) {
if (mv.isViolation(vc)) {
foundMV = true;
// System.out.println(vc.toString());
if (outMVFile != null)
outMVFileStream.format(
"MV@%s:%d. REF=%s, ALT=%s, AC=%d, momID=%s, dadID=%s, childID=%s, momG=%s, momGL=%s, dadG=%s, dadGL=%s, "
+ "childG=%s childGL=%s\n",
vc.getChr(),
vc.getStart(),
vc.getReference().getDisplayString(),
vc.getAlternateAllele(0).getDisplayString(),
vc.getChromosomeCount(vc.getAlternateAllele(0)),
mv.getSampleMom(),
mv.getSampleDad(),
mv.getSampleChild(),
vc.getGenotype(mv.getSampleMom()).toBriefString(),
vc.getGenotype(mv.getSampleMom()).getLikelihoods().getAsString(),
vc.getGenotype(mv.getSampleDad()).toBriefString(),
vc.getGenotype(mv.getSampleMom()).getLikelihoods().getAsString(),
vc.getGenotype(mv.getSampleChild()).toBriefString(),
vc.getGenotype(mv.getSampleChild()).getLikelihoods().getAsString());
}
}
if (!foundMV) break;
}
if (DISCORDANCE_ONLY) {
Collection<VariantContext> compVCs =
tracker.getValues(discordanceTrack, context.getLocation());
if (!isDiscordant(vc, compVCs)) return 0;
}
if (CONCORDANCE_ONLY) {
Collection<VariantContext> compVCs =
tracker.getValues(concordanceTrack, context.getLocation());
if (!isConcordant(vc, compVCs)) return 0;
}
if (alleleRestriction.equals(NumberAlleleRestriction.BIALLELIC) && !vc.isBiallelic())
continue;
if (alleleRestriction.equals(NumberAlleleRestriction.MULTIALLELIC) && vc.isBiallelic())
continue;
if (!selectedTypes.contains(vc.getType())) continue;
VariantContext sub = subsetRecord(vc, samples);
if ((sub.isPolymorphic() || !EXCLUDE_NON_VARIANTS)
&& (!sub.isFiltered() || !EXCLUDE_FILTERED)) {
for (VariantContextUtils.JexlVCMatchExp jexl : jexls) {
if (!VariantContextUtils.match(sub, jexl)) {
return 0;
}
}
if (SELECT_RANDOM_NUMBER) {
randomlyAddVariant(++variantNumber, sub, ref.getBase());
} else if (!SELECT_RANDOM_FRACTION
|| (GenomeAnalysisEngine.getRandomGenerator().nextDouble() < fractionRandom)) {
vcfWriter.add(sub);
}
}
}
return 1;
}
/** Set up the VCF writer, the sample expressions and regexs, and the JEXL matcher */
public void initialize() {
// Get list of samples to include in the output
List<String> rodNames = Arrays.asList(variantCollection.variants.getName());
Map<String, VCFHeader> vcfRods = VCFUtils.getVCFHeadersFromRods(getToolkit(), rodNames);
TreeSet<String> vcfSamples =
new TreeSet<String>(
SampleUtils.getSampleList(
vcfRods, VariantContextUtils.GenotypeMergeType.REQUIRE_UNIQUE));
Collection<String> samplesFromFile = SampleUtils.getSamplesFromFiles(sampleFiles);
Collection<String> samplesFromExpressions =
SampleUtils.matchSamplesExpressions(vcfSamples, sampleExpressions);
// first, add any requested samples
samples.addAll(samplesFromFile);
samples.addAll(samplesFromExpressions);
samples.addAll(sampleNames);
// if none were requested, we want all of them
if (samples.isEmpty()) {
samples.addAll(vcfSamples);
NO_SAMPLES_SPECIFIED = true;
}
// now, exclude any requested samples
Collection<String> XLsamplesFromFile = SampleUtils.getSamplesFromFiles(XLsampleFiles);
samples.removeAll(XLsamplesFromFile);
samples.removeAll(XLsampleNames);
if (samples.size() == 0 && !NO_SAMPLES_SPECIFIED)
throw new UserException(
"All samples requested to be included were also requested to be excluded.");
for (String sample : samples) logger.info("Including sample '" + sample + "'");
// if user specified types to include, add these, otherwise, add all possible variant context
// types to list of vc types to include
if (TYPES_TO_INCLUDE.isEmpty()) {
for (VariantContext.Type t : VariantContext.Type.values()) selectedTypes.add(t);
} else {
for (VariantContext.Type t : TYPES_TO_INCLUDE) selectedTypes.add(t);
}
// Initialize VCF header
Set<VCFHeaderLine> headerLines = VCFUtils.smartMergeHeaders(vcfRods.values(), logger);
headerLines.add(new VCFHeaderLine("source", "SelectVariants"));
if (KEEP_ORIGINAL_CHR_COUNTS) {
headerLines.add(
new VCFFormatHeaderLine("AC_Orig", 1, VCFHeaderLineType.Integer, "Original AC"));
headerLines.add(
new VCFFormatHeaderLine("AF_Orig", 1, VCFHeaderLineType.Float, "Original AF"));
headerLines.add(
new VCFFormatHeaderLine("AN_Orig", 1, VCFHeaderLineType.Integer, "Original AN"));
}
vcfWriter.writeHeader(new VCFHeader(headerLines, samples));
for (int i = 0; i < SELECT_EXPRESSIONS.size(); i++) {
// It's not necessary that the user supply select names for the JEXL expressions, since those
// expressions will only be needed for omitting records. Make up the select names here.
selectNames.add(String.format("select-%d", i));
}
jexls = VariantContextUtils.initializeMatchExps(selectNames, SELECT_EXPRESSIONS);
// Look at the parameters to decide which analysis to perform
DISCORDANCE_ONLY = discordanceTrack.isBound();
if (DISCORDANCE_ONLY)
logger.info(
"Selecting only variants discordant with the track: " + discordanceTrack.getName());
CONCORDANCE_ONLY = concordanceTrack.isBound();
if (CONCORDANCE_ONLY)
logger.info(
"Selecting only variants concordant with the track: " + concordanceTrack.getName());
if (MENDELIAN_VIOLATIONS) {
if (FAMILY_STRUCTURE_FILE != null) {
try {
for (final String line : new XReadLines(FAMILY_STRUCTURE_FILE)) {
MendelianViolation mv =
new MendelianViolation(line, MENDELIAN_VIOLATION_QUAL_THRESHOLD);
if (samples.contains(mv.getSampleChild())
&& samples.contains(mv.getSampleDad())
&& samples.contains(mv.getSampleMom())) mvSet.add(mv);
}
} catch (FileNotFoundException e) {
throw new UserException.CouldNotReadInputFile(FAMILY_STRUCTURE_FILE, e);
}
if (outMVFile != null)
try {
outMVFileStream = new PrintStream(outMVFile);
} catch (FileNotFoundException e) {
throw new UserException.CouldNotCreateOutputFile(
outMVFile, "Can't open output file", e);
}
} else
mvSet.add(new MendelianViolation(FAMILY_STRUCTURE, MENDELIAN_VIOLATION_QUAL_THRESHOLD));
} else if (!FAMILY_STRUCTURE.isEmpty()) {
mvSet.add(new MendelianViolation(FAMILY_STRUCTURE, MENDELIAN_VIOLATION_QUAL_THRESHOLD));
MENDELIAN_VIOLATIONS = true;
}
SELECT_RANDOM_NUMBER = numRandom > 0;
if (SELECT_RANDOM_NUMBER) {
logger.info("Selecting " + numRandom + " variants at random from the variant track");
variantArray = new RandomVariantStructure[numRandom];
}
SELECT_RANDOM_FRACTION = fractionRandom > 0;
if (SELECT_RANDOM_FRACTION)
logger.info(
"Selecting approximately "
+ 100.0 * fractionRandom
+ "% of the variants at random from the variant track");
}
public void writeBeagleOutput(
VariantContext preferredVC, VariantContext otherVC, boolean isValidationSite, double prior) {
GenomeLoc currentLoc =
VariantContextUtils.getLocation(getToolkit().getGenomeLocParser(), preferredVC);
StringBuffer beagleOut = new StringBuffer();
String marker = String.format("%s:%d ", currentLoc.getContig(), currentLoc.getStart());
beagleOut.append(marker);
if (markers != null)
markers.append(marker).append("\t").append(Integer.toString(markerCounter++)).append("\t");
for (Allele allele : preferredVC.getAlleles()) {
String bglPrintString;
if (allele.isNoCall() || allele.isNull()) bglPrintString = "-";
else bglPrintString = allele.getBaseString(); // get rid of * in case of reference allele
beagleOut.append(String.format("%s ", bglPrintString));
if (markers != null) markers.append(bglPrintString).append("\t");
}
if (markers != null) markers.append("\n");
GenotypesContext preferredGenotypes = preferredVC.getGenotypes();
GenotypesContext otherGenotypes = goodSite(otherVC) ? otherVC.getGenotypes() : null;
for (String sample : samples) {
boolean isMaleOnChrX = CHECK_IS_MALE_ON_CHR_X && getSample(sample).getGender() == Gender.MALE;
Genotype genotype;
boolean isValidation;
// use sample as key into genotypes structure
if (preferredGenotypes.containsSample(sample)) {
genotype = preferredGenotypes.get(sample);
isValidation = isValidationSite;
} else if (otherGenotypes != null && otherGenotypes.containsSample(sample)) {
genotype = otherGenotypes.get(sample);
isValidation = !isValidationSite;
} else {
// there is magically no genotype for this sample.
throw new StingException(
"Sample "
+ sample
+ " arose with no genotype in variant or validation VCF. This should never happen.");
}
/*
* Use likelihoods if: is validation, prior is negative; or: is not validation, has genotype key
*/
double[] log10Likelihoods = null;
if ((isValidation && prior < 0.0) || genotype.hasLikelihoods()) {
log10Likelihoods = genotype.getLikelihoods().getAsVector();
// see if we need to randomly mask out genotype in this position.
if (GenomeAnalysisEngine.getRandomGenerator().nextDouble() <= insertedNoCallRate) {
// we are masking out this genotype
log10Likelihoods =
isMaleOnChrX ? HAPLOID_FLAT_LOG10_LIKELIHOODS : DIPLOID_FLAT_LOG10_LIKELIHOODS;
}
if (isMaleOnChrX) {
log10Likelihoods[1] = -255; // todo -- warning this is dangerous for multi-allele case
}
}
/** otherwise, use the prior uniformly */
else if (!isValidation && genotype.isCalled() && !genotype.hasLikelihoods()) {
// hack to deal with input VCFs with no genotype likelihoods. Just assume the called
// genotype
// is confident. This is useful for Hapmap and 1KG release VCFs.
double AA = (1.0 - prior) / 2.0;
double AB = (1.0 - prior) / 2.0;
double BB = (1.0 - prior) / 2.0;
if (genotype.isHomRef()) {
AA = prior;
} else if (genotype.isHet()) {
AB = prior;
} else if (genotype.isHomVar()) {
BB = prior;
}
log10Likelihoods = MathUtils.toLog10(new double[] {AA, isMaleOnChrX ? 0.0 : AB, BB});
} else {
log10Likelihoods =
isMaleOnChrX ? HAPLOID_FLAT_LOG10_LIKELIHOODS : DIPLOID_FLAT_LOG10_LIKELIHOODS;
}
writeSampleLikelihoods(beagleOut, preferredVC, log10Likelihoods);
}
beagleWriter.println(beagleOut.toString());
}
/**
* 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));
}
