From e93ff3ea6ea864984e0a132239a7b34534b11629 Mon Sep 17 00:00:00 2001 From: Eric Banks Date: Thu, 25 Oct 2012 12:45:23 -0400 Subject: [PATCH] Let's go back to having the SB/SLOD NOT computed by default. If you recall, it was only enabled by default because we thought we were going to use it when we made VQSR use random forests. But since we decided not to change VQSR, there's no reason to triple the computation for every variant site anymore. --- .../genotyper/UnifiedArgumentCollection.java | 6 +++--- .../walkers/genotyper/UnifiedGenotyper.java | 2 +- .../genotyper/UnifiedGenotyperEngine.java | 2 +- .../walkers/variantutils/SelectVariants.java | 1 - .../UnifiedGenotyperIntegrationTest.java | 18 +++++++++--------- 5 files changed, 14 insertions(+), 15 deletions(-) diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedArgumentCollection.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedArgumentCollection.java index e50f25fe8..5f6ddf0f1 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedArgumentCollection.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedArgumentCollection.java @@ -47,8 +47,8 @@ public class UnifiedArgumentCollection extends StandardCallerArgumentCollection /** * Note that calculating the SLOD increases the runtime by an appreciable amount. */ - @Argument(fullName = "noSLOD", shortName = "nosl", doc = "If provided, we will not calculate the SLOD", required = false) - public boolean NO_SLOD = false; + @Argument(fullName = "computeSLOD", shortName = "slod", doc = "If provided, we will calculate the SLOD (SB annotation)", required = false) + public boolean COMPUTE_SLOD = false; /** * Depending on the value of the --max_alternate_alleles argument, we may genotype only a fraction of the alleles being sent on for genotyping. @@ -204,7 +204,7 @@ public class UnifiedArgumentCollection extends StandardCallerArgumentCollection this.GLmodel = uac.GLmodel; this.AFmodel = uac.AFmodel; this.PCR_error = uac.PCR_error; - this.NO_SLOD = uac.NO_SLOD; + this.COMPUTE_SLOD = uac.COMPUTE_SLOD; this.ANNOTATE_NUMBER_OF_ALLELES_DISCOVERED = uac.ANNOTATE_NUMBER_OF_ALLELES_DISCOVERED; this.MIN_BASE_QUALTY_SCORE = uac.MIN_BASE_QUALTY_SCORE; this.MAX_DELETION_FRACTION = uac.MAX_DELETION_FRACTION; diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyper.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyper.java index a17c2aa1a..ef56eaa6d 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyper.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyper.java @@ -290,7 +290,7 @@ public class UnifiedGenotyper extends LocusWalker, Unif headerInfo.addAll(annotationEngine.getVCFAnnotationDescriptions()); // annotation (INFO) fields from UnifiedGenotyper - if ( !UAC.NO_SLOD ) + if ( UAC.COMPUTE_SLOD ) VCFStandardHeaderLines.addStandardInfoLines(headerInfo, true, VCFConstants.STRAND_BIAS_KEY); if ( UAC.ANNOTATE_NUMBER_OF_ALLELES_DISCOVERED ) diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperEngine.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperEngine.java index 3c4a97ec1..97254c478 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperEngine.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperEngine.java @@ -451,7 +451,7 @@ public class UnifiedGenotyperEngine { attributes.put(VCFConstants.MLE_ALLELE_FREQUENCY_KEY, MLEfrequencies); } - if ( !UAC.NO_SLOD && !limitedContext && !bestGuessIsRef ) { + if ( UAC.COMPUTE_SLOD && !limitedContext && !bestGuessIsRef ) { //final boolean DEBUG_SLOD = false; // the overall lod diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/variantutils/SelectVariants.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/variantutils/SelectVariants.java index c7b1d0fc7..d1b7cb96f 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/variantutils/SelectVariants.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/variantutils/SelectVariants.java @@ -459,7 +459,6 @@ public class SelectVariants extends RodWalker implements TreeR UAC.GLmodel = GenotypeLikelihoodsCalculationModel.Model.BOTH; UAC.OutputMode = UnifiedGenotyperEngine.OUTPUT_MODE.EMIT_ALL_SITES; UAC.GenotypingMode = GenotypeLikelihoodsCalculationModel.GENOTYPING_MODE.GENOTYPE_GIVEN_ALLELES; - UAC.NO_SLOD = true; UG_engine = new UnifiedGenotyperEngine(getToolkit(), UAC, logger, null, null, samples, VariantContextUtils.DEFAULT_PLOIDY); headerLines.addAll(UnifiedGenotyper.getHeaderInfo(UAC, null, null)); } diff --git a/public/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java b/public/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java index 8eb1c4657..446f8cbe8 100755 --- a/public/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java +++ b/public/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java @@ -16,9 +16,9 @@ import java.util.List; public class UnifiedGenotyperIntegrationTest extends WalkerTest { - private final static String baseCommand = "-T UnifiedGenotyper -R " + b36KGReference + " -nosl --no_cmdline_in_header -glm BOTH -minIndelFrac 0.0 --dbsnp " + b36dbSNP129; - private final static String baseCommandIndels = "-T UnifiedGenotyper -R " + b36KGReference + " -nosl --no_cmdline_in_header -glm INDEL -mbq 20 -minIndelFrac 0.0 --dbsnp " + b36dbSNP129; - private final static String baseCommandIndelsb37 = "-T UnifiedGenotyper -R " + b37KGReference + " -nosl --no_cmdline_in_header -glm INDEL -mbq 20 --dbsnp " + b37dbSNP132; + private final static String baseCommand = "-T UnifiedGenotyper -R " + b36KGReference + " --no_cmdline_in_header -glm BOTH -minIndelFrac 0.0 --dbsnp " + b36dbSNP129; + private final static String baseCommandIndels = "-T UnifiedGenotyper -R " + b36KGReference + " --no_cmdline_in_header -glm INDEL -mbq 20 -minIndelFrac 0.0 --dbsnp " + b36dbSNP129; + private final static String baseCommandIndelsb37 = "-T UnifiedGenotyper -R " + b37KGReference + " --no_cmdline_in_header -glm INDEL -mbq 20 --dbsnp " + b37dbSNP132; private final static String baseCommandNoCmdLineHeaderStdout = "-T UnifiedGenotyper -R " + b37KGReference + " --no_cmdline_in_header -I " + privateTestDir + "bamExample.ReducedRead.ADAnnotation.bam"; // -------------------------------------------------------------------------------------------------------------- @@ -61,7 +61,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { @Test public void testMultipleSNPAlleles() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( - "-T UnifiedGenotyper -R " + b37KGReference + " -nosl --no_cmdline_in_header -glm BOTH --dbsnp " + b37dbSNP129 + " -I " + privateTestDir + "multiallelic.snps.bam -o %s -L " + privateTestDir + "multiallelic.snps.intervals", 1, + "-T UnifiedGenotyper -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("543f68e42034bf44cfb24da8c9204320")); executeTest("test Multiple SNP alleles", spec); } @@ -69,7 +69,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { @Test public void testBadRead() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( - "-T UnifiedGenotyper -R " + b37KGReference + " -nosl --no_cmdline_in_header -glm BOTH -I " + privateTestDir + "badRead.test.bam -o %s -L 1:22753424-22753464", 1, + "-T UnifiedGenotyper -R " + b37KGReference + " --no_cmdline_in_header -glm BOTH -I " + privateTestDir + "badRead.test.bam -o %s -L 1:22753424-22753464", 1, Arrays.asList("d915535c1458733f09f82670092fcab6")); executeTest("test bad read", spec); } @@ -77,7 +77,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { @Test public void testReverseTrim() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( - "-T UnifiedGenotyper -R " + b37KGReference + " -nosl --no_cmdline_in_header -glm INDEL -I " + validationDataLocation + "CEUTrio.HiSeq.b37.chr20.10_11mb.bam -o %s -L 20:10289124 -L 20:10090289", 1, + "-T UnifiedGenotyper -R " + b37KGReference + " --no_cmdline_in_header -glm INDEL -I " + validationDataLocation + "CEUTrio.HiSeq.b37.chr20.10_11mb.bam -o %s -L 20:10289124 -L 20:10090289", 1, Arrays.asList("5ce03dd9ca2d9324c1d4a9d64389beb5")); executeTest("test reverse trim", spec); } @@ -85,7 +85,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { @Test public void testMismatchedPLs() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( - "-T UnifiedGenotyper -R " + b37KGReference + " -nosl --no_cmdline_in_header -glm INDEL -I " + privateTestDir + "mismatchedPLs.bam -o %s -L 1:24020341", 1, + "-T UnifiedGenotyper -R " + b37KGReference + " --no_cmdline_in_header -glm INDEL -I " + privateTestDir + "mismatchedPLs.bam -o %s -L 1:24020341", 1, Arrays.asList("3c006b06b17bbe8e787d64eff6a63a19")); executeTest("test mismatched PLs", spec); } @@ -156,7 +156,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { @Test public void testSLOD() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( - "-T UnifiedGenotyper -R " + b36KGReference + " --no_cmdline_in_header -glm BOTH --dbsnp " + b36dbSNP129 + " -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -o %s -L 1:10,000,000-10,010,000", 1, + "-T UnifiedGenotyper -R " + b36KGReference + " --computeSLOD --no_cmdline_in_header -glm BOTH --dbsnp " + b36dbSNP129 + " -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -o %s -L 1:10,000,000-10,010,000", 1, Arrays.asList("c7429e670ba477bf9a6bbee2fb41c5a9")); executeTest("test SLOD", spec); } @@ -173,7 +173,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { public void testCompTrack() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + b36KGReference + " --no_cmdline_in_header -glm BOTH -comp:FOO " + b36dbSNP129 + " -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -o %s -L 1:10,000,000-10,010,000", 1, - Arrays.asList("8a9b424e00cdbe6b5e73d517335b2186")); + Arrays.asList("a6de72c5197f152be98a6f9029091a9e")); executeTest("test using comp track", spec); }