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

Merge pull request #1454 from broadinstitute/rrhl_rm_stand_emit_conf 

Remove -stand_emit_conf argument
This commit is contained in:
Ron Levine 2016-08-27 08:57:09 -04:00 committed by GitHub
parent cb0dedeb49 a883905101
commit 814ad21006
9 changed files with 26 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/engine/arguments/GenotypeCalculationArgumentCollection.java
View File

@ -110,12 +110,6 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
@Argument(fullName = "standard_min_confidence_threshold_for_calling", shortName = "stand_call_conf", doc = "The minimum phred-scaled confidence threshold at which variants should be called", required = false)
public double STANDARD_CONFIDENCE_FOR_CALLING = 30.0;
/**
* This argument allows you to emit low quality calls as filtered records.
*/
@Argument(fullName = "standard_min_confidence_threshold_for_emitting", shortName = "stand_emit_conf", doc = "The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold)", required = false)
public double STANDARD_CONFIDENCE_FOR_EMITTING = 30.0;
/**
* If there are more than this number of alternate alleles presented to the genotyper (either through discovery or GENOTYPE_GIVEN_ALLELES),
* then only this many alleles will be used. Note that genotyping sites with many alternate alleles is both CPU and memory intensive and it

12
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/genotyper/GenotypingEngine.java
View File

@ -68,6 +68,7 @@ import org.broadinstitute.gatk.utils.contexts.AlignmentContext;
import org.broadinstitute.gatk.utils.contexts.AlignmentContextUtils;
import org.broadinstitute.gatk.utils.contexts.ReferenceContext;
import org.broadinstitute.gatk.utils.exceptions.UserException;
import org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap;
import org.broadinstitute.gatk.utils.genotyper.SampleList;
import org.broadinstitute.gatk.utils.gga.GenotypingGivenAllelesUtils;
import org.broadinstitute.gatk.utils.pileup.ReadBackedPileup;
@ -218,7 +219,7 @@ public abstract class GenotypingEngine<Config extends StandardCallerArgumentColl
final AlignmentContext rawContext, Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc, final GenotypeLikelihoodsCalculationModel.Model model,
final boolean inheritAttributesFromInputVC,
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final boolean doAlleleSpecificCalcs) {
final boolean limitedContext = tracker == null || refContext == null || rawContext == null || stratifiedContexts == null;
@ -362,7 +363,7 @@ public abstract class GenotypingEngine<Config extends StandardCallerArgumentColl
// we want to keep the NON_REF symbolic allele but only in the absence of a non-symbolic allele, e.g.
// if we combined a ref / NON_REF gVCF with a ref / alt gVCF
final boolean isNonRefWhichIsLoneAltAllele = alternativeAlleleCount == 1 && allele.equals(GATKVCFConstants.NON_REF_SYMBOLIC_ALLELE);
final boolean isPlausible = afcr.isPolymorphicPhredScaledQual(allele, configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_EMITTING);
final boolean isPlausible = afcr.isPolymorphicPhredScaledQual(allele, configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING/3);
siteIsMonomorphic &= !isPlausible;
boolean toOutput = (isPlausible || forceKeepAllele(allele) || isNonRefWhichIsLoneAltAllele);
@ -671,8 +672,7 @@ public abstract class GenotypingEngine<Config extends StandardCallerArgumentColl
protected final boolean passesEmitThreshold(double conf, boolean bestGuessIsRef) {
return (configuration.outputMode == OutputMode.EMIT_ALL_CONFIDENT_SITES || !bestGuessIsRef) &&
conf >= Math.min(configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING,
configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_EMITTING);
conf >= configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING;
}
protected final boolean passesCallThreshold(double conf) {
@ -682,7 +682,7 @@ public abstract class GenotypingEngine<Config extends StandardCallerArgumentColl
protected Map<String,Object> composeCallAttributes(final boolean inheritAttributesFromInputVC, final VariantContext vc,
final AlignmentContext rawContext, final Map<String, AlignmentContext> stratifiedContexts, final RefMetaDataTracker tracker, final ReferenceContext refContext, final List<Integer> alleleCountsofMLE, final boolean bestGuessIsRef,
final AFCalculationResult AFresult, final List<Allele> allAllelesToUse, final GenotypesContext genotypes,
final GenotypeLikelihoodsCalculationModel.Model model, final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final GenotypeLikelihoodsCalculationModel.Model model, final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final boolean doAlleleSpecificCalcs) {
final HashMap<String, Object> attributes = new HashMap<>();
@ -778,7 +778,7 @@ public abstract class GenotypingEngine<Config extends StandardCallerArgumentColl
final double normalizedLog10ACeq0Posterior = log10ACeq0Posterior - log10PosteriorNormalizationConstant;
// This is another condition to return a 0.0 also present in AFCalculator code as well.
if (normalizedLog10ACeq0Posterior >= QualityUtils.qualToErrorProbLog10(configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_EMITTING))
if (normalizedLog10ACeq0Posterior >= QualityUtils.qualToErrorProbLog10(configuration.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING/3))
return 0.0;
return 1.0 - Math.pow(10.0, normalizedLog10ACeq0Posterior);

1
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/genotyper/UnifiedGenotyper.java
View File

@ -116,7 +116,6 @@ import java.util.*;
* --dbsnp dbSNP.vcf \
* -o snps.raw.vcf \
* -stand_call_conf [50.0] \
* -stand_emit_conf 10.0 \
* [-L targets.interval_list]
* </pre>
*

14
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/genotyper/UnifiedGenotypingEngine.java
View File

@ -203,7 +203,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
final List<GenotypeLikelihoodsCalculationModel.Model> models = getGLModelsToUse(tracker, rawContext);
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap = new HashMap<>();
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap = new HashMap<>();
final VariantCallContext defaultResult = configuration.outputMode == OutputMode.EMIT_ALL_SITES
&& configuration.genotypingOutputMode == GenotypingOutputMode.GENOTYPE_GIVEN_ALLELES
@ -267,7 +267,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
public VariantContext calculateLikelihoods(final RefMetaDataTracker tracker,
final ReferenceContext refContext,
final AlignmentContext rawContext,
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap) {
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap) {
final List<GenotypeLikelihoodsCalculationModel.Model> models = getGLModelsToUse(tracker, rawContext);
if ( models.isEmpty() ) {
return null;
@ -345,7 +345,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
final List<Allele> alternateAllelesToUse,
final boolean useBAQedPileup,
final GenotypeLikelihoodsCalculationModel.Model model,
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap) {
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap) {
return glcm.get().get(model.name()).getLikelihoods(tracker, refContext, stratifiedContexts, type, alternateAllelesToUse, useBAQedPileup && BAQEnabledOnCMDLine,
genomeLocParser != null || refContext == null ? genomeLocParser : refContext.getGenomeLocParser(), perReadAlleleLikelihoodMap);
@ -360,7 +360,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
final AlignmentContext rawContext, Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc, final GenotypeLikelihoodsCalculationModel.Model model,
final boolean inheritAttributesFromInputVC,
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap) {
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap) {
return calculateGenotypes(tracker, refContext, rawContext, stratifiedContexts, vc, model, inheritAttributesFromInputVC, perReadAlleleLikelihoodMap, false);
}
@ -370,7 +370,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
final Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc,
final GenotypeLikelihoodsCalculationModel.Model model,
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final boolean useAlleleSpecificCalcs) {
return calculateGenotypes(tracker, refContext, rawContext, stratifiedContexts, vc, model, false, perReadAlleleLikelihoodMap, useAlleleSpecificCalcs);
}
@ -386,7 +386,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
final AlignmentContext rawContext, Map<String, AlignmentContext> stratifiedContexts,
final VariantContext vc, final GenotypeLikelihoodsCalculationModel.Model model,
final boolean inheritAttributesFromInputVC,
final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final boolean useAlleleSpecificCalcs) {
boolean limitedContext = tracker == null || refContext == null || rawContext == null || stratifiedContexts == null;
final VariantCallContext result = super.calculateGenotypes(tracker,refContext,rawContext,stratifiedContexts,vc,model,inheritAttributesFromInputVC,perReadAlleleLikelihoodMap, useAlleleSpecificCalcs);
@ -410,7 +410,7 @@ public class UnifiedGenotypingEngine extends GenotypingEngine<UnifiedArgumentCol
protected Map<String,Object> composeCallAttributes(final boolean inheritAttributesFromInputVC, final VariantContext vc,
final AlignmentContext rawContext, final Map<String, AlignmentContext> stratifiedContexts, final RefMetaDataTracker tracker, final ReferenceContext refContext, final List<Integer> alleleCountsofMLE, final boolean bestGuessIsRef,
final AFCalculationResult AFresult, final List<Allele> allAllelesToUse, final GenotypesContext genotypes,
final GenotypeLikelihoodsCalculationModel.Model model, final Map<String, org.broadinstitute.gatk.utils.genotyper.PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final GenotypeLikelihoodsCalculationModel.Model model, final Map<String, PerReadAlleleLikelihoodMap> perReadAlleleLikelihoodMap,
final boolean useAlleleSpecificCalcs) {
final Map<String,Object> result = super.composeCallAttributes(inheritAttributesFromInputVC, vc,rawContext,stratifiedContexts,tracker,refContext,alleleCountsofMLE,bestGuessIsRef,
AFresult,allAllelesToUse,genotypes,model,perReadAlleleLikelihoodMap, useAlleleSpecificCalcs);

4
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/haplotypecaller/HaplotypeCaller.java
View File

@ -211,7 +211,6 @@ import java.util.*;
* -I sample1.bam [-I sample2.bam ...] \
* [--dbsnp dbSNP.vcf] \
* [-stand_call_conf 30] \
* [-stand_emit_conf 10] \
* [-L targets.interval_list] \
* -o output.raw.snps.indels.vcf
* </pre>
@ -224,7 +223,6 @@ import java.util.*;
* -I sample1.bam \
* [--dbsnp dbSNP.vcf] \
* -stand_call_conf 20 \
* -stand_emit_conf 20 \
* -o output.raw.snps.indels.vcf
* </pre>
*
@ -590,7 +588,6 @@ public class HaplotypeCaller extends ActiveRegionWalker<List<VariantContext>, In
if (HCAC.genotypingOutputMode == GenotypingOutputMode.GENOTYPE_GIVEN_ALLELES)
throw new UserException.BadArgumentValue("ERC/gt_mode","you cannot request reference confidence output and GENOTYPE_GIVEN_ALLELES at the same time");
HCAC.genotypeArgs.STANDARD_CONFIDENCE_FOR_EMITTING = -0.0;
HCAC.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING = -0.0;
// also, we don't need to output several of the annotations
@ -632,7 +629,6 @@ public class HaplotypeCaller extends ActiveRegionWalker<List<VariantContext>, In
simpleUAC.outputMode = OutputMode.EMIT_VARIANTS_ONLY;
simpleUAC.genotypingOutputMode = GenotypingOutputMode.DISCOVERY;
simpleUAC.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING = Math.min(MAXMIN_CONFIDENCE_FOR_CONSIDERING_A_SITE_AS_POSSIBLE_VARIANT_IN_ACTIVE_REGION_DISCOVERY, HCAC.genotypeArgs.STANDARD_CONFIDENCE_FOR_CALLING ); // low values used for isActive determination only, default/user-specified values used for actual calling
simpleUAC.genotypeArgs.STANDARD_CONFIDENCE_FOR_EMITTING = Math.min(MAXMIN_CONFIDENCE_FOR_CONSIDERING_A_SITE_AS_POSSIBLE_VARIANT_IN_ACTIVE_REGION_DISCOVERY, HCAC.genotypeArgs.STANDARD_CONFIDENCE_FOR_EMITTING ); // low values used for isActive determination only, default/user-specified values used for actual calling
simpleUAC.CONTAMINATION_FRACTION = 0.0;
simpleUAC.CONTAMINATION_FRACTION_FILE = null;
simpleUAC.exactCallsLog = null;

2
protected/gatk-tools-protected/src/test/java/org/broadinstitute/gatk/tools/walkers/genotyper/UnifiedGenotyperIntegrationTest.java
View File

@ -310,7 +310,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest {
baseCommand + " -I " + validationDataLocation + "low_coverage_CEU.chr1.10k-11k.bam -o %s -L 1:10,022,000-10,025,000 " +
"-A SnpEff",
1,
Arrays.asList("65641c92469ab80513b04144d0eae900"));
Arrays.asList("2a1eced23dd605d1b0a3efde3f04e23f"));
executeTest("testSnpEffAnnotationRequestedWithoutRodBinding", spec);
}

4
protected/gatk-tools-protected/src/test/java/org/broadinstitute/gatk/tools/walkers/genotyper/UnifiedGenotyperNormalCallingIntegrationTest.java
View File

@ -70,7 +70,7 @@ public class UnifiedGenotyperNormalCallingIntegrationTest extends WalkerTest{
public void testMultiSamplePilot1() {
WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
baseCommand + " -I " + validationDataLocation + "low_coverage_CEU.chr1.10k-11k.bam -o %s -L 1:10,022,000-10,025,000", 1,
Arrays.asList("e7f216d2f9857a579ef3e211076b37a4"));
Arrays.asList("f03e4ef62d6614c9b1b0a600f7e9f16d"));
executeTest("test MultiSample Pilot1", spec);
}
@ -102,7 +102,7 @@ public class UnifiedGenotyperNormalCallingIntegrationTest extends WalkerTest{
public void testMultipleSNPAlleles() {
WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec(
"-T UnifiedGenotyper --contamination_fraction_to_filter 0.05 --disableDithering -R " + b37KGReference + " --no_cmdline_in_header -glm BOTH --dbsnp " + b37dbSNP129 + " -I " + privateTestDir + "multiallelic.snps.bam -o %s -L " + privateTestDir + "multiallelic.snps.intervals", 1,
Arrays.asList("25b710f830749448cd056c9b2e7798ff"));
Arrays.asList("fca6cacfb523114a3fb93772569deb08"));
executeTest("test Multiple SNP alleles", spec);
}

6
protected/gatk-tools-protected/src/test/java/org/broadinstitute/gatk/tools/walkers/haplotypecaller/HaplotypeCallerIntegrationTest.java
View File

@ -107,7 +107,7 @@ public class HaplotypeCallerIntegrationTest extends WalkerTest {
@Test
public void testHaplotypeBAMOutFlags() throws IOException {
HCTestWithBAMOut(NA12878_BAM, " -L 20:10000000-10100000 ", "56086abc3bd5e3f7d111f452b7cc4fa1", "6a81bbefa6c4ed7a6b8d2c3e0e5a4756");
HCTestWithBAMOut(NA12878_BAM, " -L 20:10000000-10100000 ", "729ebefdce0d5ea6f535c354c329e6b9", "d38aab5bf8ef0bc7c18e8c909819da84");
}
@Test
@ -264,7 +264,7 @@ public class HaplotypeCallerIntegrationTest extends WalkerTest {
@Test
public void HCTestDoesNotFailOnBadRefBase() {
// don't care about the output - just want to make sure it doesn't fail
final String base = String.format("-T HaplotypeCaller --disableDithering -pairHMMSub %s %s -R %s -I %s", HMM_SUB_IMPLEMENTATION, ALWAYS_LOAD_VECTOR_HMM, REF, privateTestDir + "NA12878.readsOverBadBase.chr3.bam") + " --no_cmdline_in_header -o /dev/null -L 3:60830000-60840000 --minPruning 3 -stand_call_conf 2 -stand_emit_conf 2";
final String base = String.format("-T HaplotypeCaller --disableDithering -pairHMMSub %s %s -R %s -I %s", HMM_SUB_IMPLEMENTATION, ALWAYS_LOAD_VECTOR_HMM, REF, privateTestDir + "NA12878.readsOverBadBase.chr3.bam") + " --no_cmdline_in_header -o /dev/null -L 3:60830000-60840000 --minPruning 3 -stand_call_conf 2";
final WalkerTestSpec spec = new WalkerTestSpec(base, Collections.<String>emptyList());
executeTest("HCTestDoesNotFailOnBadRefBase: ", spec);
}
@ -421,7 +421,7 @@ public class HaplotypeCallerIntegrationTest extends WalkerTest {
final String DBSNP = b37dbSNP138;
final String commandLineWithoutInterval = String.format("-T HaplotypeCaller -pairHMMSub %s %s -I %s -R %s -D %s "
+ "-variant_index_type LINEAR -variant_index_parameter 128000 --no_cmdline_in_header "
+ "-stand_call_conf 10.0 -stand_emit_conf 10.0", HMM_SUB_IMPLEMENTATION, ALWAYS_LOAD_VECTOR_HMM, TEST_BAM, REFERENCE, DBSNP);
+ "-stand_call_conf 10.0", HMM_SUB_IMPLEMENTATION, ALWAYS_LOAD_VECTOR_HMM, TEST_BAM, REFERENCE, DBSNP);
final String commandLineShortInterval = commandLineWithoutInterval + " -L " + SHORT_INTERVAL;
final String commandLineLongInterval = commandLineWithoutInterval + " -L " + LONG_INTERVAL;

14
protected/gatk-tools-protected/src/test/java/org/broadinstitute/gatk/tools/walkers/variantutils/GenotypeGVCFsIntegrationTest.java
View File

@ -108,7 +108,7 @@ public class GenotypeGVCFsIntegrationTest extends WalkerTest {
" -V:sample3 " + privateTestDir + "combine.single.sample.pipeline.3.vcf" +
" -L 20:10,000,000-11,000,000", b37KGReference),
1,
Collections.singletonList("c9edd4ca8c2801c4681322087d82e781"));
Collections.singletonList("61dd2aaabf94a8f5b87d5069a75d84d7"));
executeTest("combineSingleSamplePipelineGVCF", spec);
}
@ -170,7 +170,7 @@ public class GenotypeGVCFsIntegrationTest extends WalkerTest {
" -V:sample3 " + privateTestDir + "combine.single.sample.pipeline.3.vcf" +
" -L 20:10,000,000-20,000,000", b37KGReference),
1,
Collections.singletonList("f48114bc6348cdc9dc4f0960f5dcf5f8"));
Collections.singletonList("3943e70eed48618040469e157509868e"));
executeTest("combineSingleSamplePipelineGVCFHierarchical", spec);
}
@ -182,7 +182,7 @@ public class GenotypeGVCFsIntegrationTest extends WalkerTest {
" -V:sample3 " + privateTestDir + "combine.single.sample.pipeline.3.vcf" +
" -L 20:10,000,000-11,000,000 --dbsnp " + b37dbSNP132, b37KGReference),
1,
Collections.singletonList("f88841deb5c2ce4f3bbea1e914a13898"));
Collections.singletonList("51d498327342bd3b0b092845b437aad5"));
executeTest("combineSingleSamplePipelineGVCF_addDbsnp", spec);
}
@ -257,9 +257,9 @@ public class GenotypeGVCFsIntegrationTest extends WalkerTest {
@Test
public void testStandardConf() {
final WalkerTestSpec spec = new WalkerTestSpec(
baseBPResolutionString("-stand_call_conf 300 -stand_emit_conf 100"),
baseBPResolutionString("-stand_call_conf 300"),
1,
Collections.singletonList("0283e784ed49bc2dce32a26137c43409"));
Collections.singletonList("30903101c5459f602d7004934bc85ca9"));
executeTest("testStandardConf", spec);
}
@ -299,7 +299,7 @@ public class GenotypeGVCFsIntegrationTest extends WalkerTest {
" -V:combined2 " + privateTestDir + "combine.single.sample.pipeline.combined.vcf" +
" --uniquifySamples", b37KGReference),
1,
Collections.singletonList("16d7374502fa3cf99863d15d31b5ef86"));
Collections.singletonList("c23b1e3f9a960e022038768998a8df82"));
executeTest("testUniquifiedSamples", spec);
}
@ -666,7 +666,7 @@ public class GenotypeGVCFsIntegrationTest extends WalkerTest {
public void testGenotypingSpanningDeletionAcrossLines() {
final WalkerTestSpec spec = new WalkerTestSpec(
baseTestString(" -V " + privateTestDir + "input-1_2256566.vcf", b37KGReference),
Collections.singletonList("1f914189326cdd17d0a8753f13cb221f"));
Collections.singletonList("24ac243e77e679508c6554194923317b"));
spec.disableShadowBCF();
executeTest("testGenotypingSpanningDeletionAcrossLines", spec);
}