zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

a) Hidden, experimental argument to UnifiedGenotyper that makes code, when in GenotypeGivenAlleles mode, ignore SNP alleles mixed in with indels in complex records - theory is that SNP sites behave statistically differently when doing VQSR so those alleles/sites should be treated separately. 

b) Bug fix: multiallelic indel records where not being treated properly by VQSR because vc.isIndel() returns false with them. Correct general treatment for now is to do (vc.isIndel()||vc.isMixed()).



git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@5973 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
delangel 2011-06-09 19:19:23 +00:00
parent 17e17d3c3c
commit f8ffda6835
4 changed files with 24 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
java/src/org/broadinstitute/sting/gatk/walkers/genotyper/IndelGenotypeLikelihoodsCalculationModel.java
View File

@ -58,6 +58,8 @@ public class IndelGenotypeLikelihoodsCalculationModel extends GenotypeLikelihood
private boolean DEBUG = false;
private boolean ignoreSNPAllelesWhenGenotypingIndels = false;
private PairHMMIndelErrorModel pairModel;
private static ThreadLocal<HashMap<PileupElement,LinkedHashMap<Allele,Double>>> indelLikelihoodMap =
@ -111,7 +113,7 @@ public class IndelGenotypeLikelihoodsCalculationModel extends GenotypeLikelihood
DEBUG = UAC.OUTPUT_DEBUG_INDEL_INFO;
haplotypeMap = new LinkedHashMap<Allele,Haplotype>();
ignoreSNPAllelesWhenGenotypingIndels = UAC.IGNORE_SNP_ALLELES;
}
@ -333,8 +335,19 @@ public class IndelGenotypeLikelihoodsCalculationModel extends GenotypeLikelihood
return null;
alleleList.clear();
for (Allele a : vc.getAlleles())
alleleList.add(a);
if (ignoreSNPAllelesWhenGenotypingIndels) {
// if there's an allele that has same length as the reference (i.e. a SNP or MNP), ignore it and don't genotype it
for (Allele a : vc.getAlleles())
if (a.isNonReference() && a.getBases().length == vc.getReference().getBases().length)
continue;
else
alleleList.add(a);
}
else {
for (Allele a : vc.getAlleles())
alleleList.add(a);
}
}
else {

6
java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedArgumentCollection.java
View File

@ -124,6 +124,11 @@ public class UnifiedArgumentCollection {
@Argument(fullName = "exactCalculation", shortName = "exactCalculation", doc = "expt", required = false)
public ExactAFCalculationModel.ExactCalculation EXACT_CALCULATION_TYPE = ExactAFCalculationModel.ExactCalculation.LINEAR_EXPERIMENTAL;
@Hidden
@Argument(fullName = "ignoreSNPAlleles", shortName = "ignoreSNPAlleles", doc = "expt", required = false)
public boolean IGNORE_SNP_ALLELES = false;
@Deprecated
@Argument(fullName="output_all_callable_bases", shortName="all_bases", doc="Please use --output_mode EMIT_ALL_SITES instead" ,required=false)
private Boolean ALL_BASES_DEPRECATED = false;
@ -165,6 +170,7 @@ public class UnifiedArgumentCollection {
uac.COVERAGE_AT_WHICH_TO_ABORT = COVERAGE_AT_WHICH_TO_ABORT;
uac.dovit = dovit;
uac.GSA_PRODUCTION_ONLY = GSA_PRODUCTION_ONLY;
uac.IGNORE_SNP_ALLELES = IGNORE_SNP_ALLELES;
return uac;
}

2
java/src/org/broadinstitute/sting/gatk/walkers/variantrecalibration/VariantDataManager.java
View File

@ -240,7 +240,7 @@ public class VariantDataManager {
datum.consensusCount = 0;
for( final TrainingSet trainingSet : trainingSets ) {
for( final VariantContext trainVC : tracker.getVariantContexts( ref, trainingSet.name, null, context.getLocation(), false, false ) ) {
if( trainVC != null && trainVC.isNotFiltered() && trainVC.isVariant() && ((evalVC.isSNP() && trainVC.isSNP()) || (evalVC.isIndel() && trainVC.isIndel())) && (TRUST_ALL_POLYMORPHIC || !trainVC.hasGenotypes() || trainVC.isPolymorphic()) ) {
if( trainVC != null && trainVC.isNotFiltered() && trainVC.isVariant() && ((evalVC.isSNP() && trainVC.isSNP())) || ((evalVC.isIndel()||evalVC.isMixed()) && (trainVC.isIndel()||trainVC.isMixed())) && (TRUST_ALL_POLYMORPHIC || !trainVC.hasGenotypes() || trainVC.isPolymorphic()) ) {
datum.isKnown = datum.isKnown || trainingSet.isKnown;
datum.atTruthSite = datum.atTruthSite || trainingSet.isTruth;
datum.atTrainingSite = datum.atTrainingSite || trainingSet.isTraining;

2
java/src/org/broadinstitute/sting/gatk/walkers/variantrecalibration/VariantRecalibrator.java
View File

@ -194,7 +194,7 @@ public class VariantRecalibrator extends RodWalker<ExpandingArrayList<VariantDat
public static boolean checkRecalibrationMode( final VariantContext vc, final VariantRecalibratorArgumentCollection.Mode mode ) {
return mode == VariantRecalibratorArgumentCollection.Mode.BOTH ||
(mode == VariantRecalibratorArgumentCollection.Mode.SNP && vc.isSNP()) ||
(mode == VariantRecalibratorArgumentCollection.Mode.INDEL && vc.isIndel());
(mode == VariantRecalibratorArgumentCollection.Mode.INDEL && (vc.isIndel() || vc.isMixed()));
}
//---------------------------------------------------------------------------------------------------------------