Added a check to ensure previous caching information doesn't affect r…

…eferenceConfidenceCalls (#5911)

* Added a defensive check to calculateReferenceConfidence() to ensure the Indel cache has been cleared from underlying reads

* Added a proper test of cache clearing behavior

Resolves #5908

src/main/java/org/broadinstitute/hellbender/tools/walkers/haplotypecaller/ReferenceConfidenceModel.java

@@ -217,6 +217,13 @@ public List<VariantContext> calculateRefConfidence(final Haplotype refHaplotype,
             }
         }
 
+        // Ensuring that we remove any indel informativeness data we may have attached to the underlying reads for caching purposes
+        // This is important as if multiple reference blocks are computed for a low complexity active region some reads may incorrectly
+        // be using caching values computed for a different reference block.
+        if (USE_CACHED_READ_INDEL_INFORMATIVENESS_VALUES) {
+            readLikelihoods.sampleReads(0).forEach(r -> r.clearTransientAttribute(INDEL_INFORMATIVE_BASES_CACHE_ATTRIBUTE_NAME));
+        }
+
         return results;
     }
 

src/test/java/org/broadinstitute/hellbender/tools/walkers/haplotypecaller/ReferenceConfidenceModelUnitTest.java

@@ -508,6 +508,10 @@ public void testRefConfidenceBasic(final int nReads, final int extension) {
         final IndependentSampleGenotypesModel genotypingModel = new IndependentSampleGenotypesModel();
         final List<Integer> expectedDPs = Collections.nCopies(data.getActiveRegion().getSpan().size(), nReads);
         final List<VariantContext> contexts = model.calculateRefConfidence(data.getRefHap(), haplotypes, data.getPaddedRefLoc(), data.getActiveRegion(), likelihoods, ploidyModel, calls, false, Collections.emptyList());
+        // Asserting that none of the reads after calculateRefConfidence have indel informativeness caching values attached.
+        for (GATKRead read : data.getActiveRegion().getReads()) {
+            Assert.assertNull(read.getTransientAttribute(ReferenceConfidenceModel.INDEL_INFORMATIVE_BASES_CACHE_ATTRIBUTE_NAME));
+        }
         checkReferenceModelResult(data, contexts, expectedDPs, calls);
     }
 
@@ -529,6 +533,10 @@ public void testRefConfidencePartialReads() {
                 final List<Integer> expectedDPs = new ArrayList<>(Collections.nCopies(data.getActiveRegion().getSpan().size(), 0));
                 for ( int i = start; i < readLen + start; i++ ) expectedDPs.set(i, 1);
                 final List<VariantContext> contexts = model.calculateRefConfidence(data.getRefHap(), haplotypes, data.getPaddedRefLoc(), data.getActiveRegion(), likelihoods, ploidyModel, calls);
+                // Asserting that none of the reads after calculateRefConfidence have indel informativeness caching values attached.
+                for (GATKRead read : data.getActiveRegion().getReads()) {
+                    Assert.assertNull(read.getTransientAttribute(ReferenceConfidenceModel.INDEL_INFORMATIVE_BASES_CACHE_ATTRIBUTE_NAME));
+                }
                 checkReferenceModelResult(data, contexts, expectedDPs, calls);
             }
         }
@@ -565,6 +573,10 @@ public void testRefConfidenceWithCalls() {
 
                     final List<Integer> expectedDPs = Collections.nCopies(data.getActiveRegion().getSpan().size(), nReads);
                     final List<VariantContext> contexts = model.calculateRefConfidence(data.getRefHap(), haplotypes, data.getPaddedRefLoc(), data.getActiveRegion(), likelihoods, ploidyModel, calls);
+                    // Asserting that none of the reads after calculateRefConfidence have indel informativeness caching values attached.
+                    for (GATKRead read : data.getActiveRegion().getReads()) {
+                        Assert.assertNull(read.getTransientAttribute(ReferenceConfidenceModel.INDEL_INFORMATIVE_BASES_CACHE_ATTRIBUTE_NAME));
+                    }
                     checkReferenceModelResult(data, contexts, expectedDPs, calls);
                 }
             }