From a280a0ff0d3315811b05b2b67ddfe1e9310d9b37 Mon Sep 17 00:00:00 2001 From: delangel Date: Fri, 21 May 2010 22:25:17 +0000 Subject: [PATCH] a) Made HaplotypeScore default annotation. This changed several integration tests, whose MD5 is now updated. b) Disabled BaseQualRankSumTest, the returned p-values differ wildly from Matlab/R-provided ones, cause TBD. git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@3419 348d0f76-0448-11de-a6fe-93d51630548a --- .../annotator/BaseQualityRankSumTest.java | 4 ++-- .../walkers/annotator/HaplotypeScore.java | 2 +- .../VariantAnnotatorIntegrationTest.java | 8 +++---- .../UnifiedGenotyperIntegrationTest.java | 22 +++++++++---------- 4 files changed, 18 insertions(+), 18 deletions(-) diff --git a/java/src/org/broadinstitute/sting/gatk/walkers/annotator/BaseQualityRankSumTest.java b/java/src/org/broadinstitute/sting/gatk/walkers/annotator/BaseQualityRankSumTest.java index 7d35e207c..14bbcee3d 100755 --- a/java/src/org/broadinstitute/sting/gatk/walkers/annotator/BaseQualityRankSumTest.java +++ b/java/src/org/broadinstitute/sting/gatk/walkers/annotator/BaseQualityRankSumTest.java @@ -7,8 +7,8 @@ import org.broadinstitute.sting.utils.pileup.PileupElement; import java.util.List; -public class BaseQualityRankSumTest extends RankSumTest { - +public class BaseQualityRankSumTest /*extends RankSumTest*/ { + // todo -- seems math in this test is dubious, need to recheck and verify (p-values wildly divergent from R or MATLAB) public String getKeyName() { return "BaseQRankSum"; } public VCFInfoHeaderLine getDescription() { return new VCFInfoHeaderLine("BaseQRankSum", 1, VCFInfoHeaderLine.INFO_TYPE.Float, "Phred-scaled p-value From Wilcoxon Rank Sum Test of Het Vs. Ref Base Qualities"); } diff --git a/java/src/org/broadinstitute/sting/gatk/walkers/annotator/HaplotypeScore.java b/java/src/org/broadinstitute/sting/gatk/walkers/annotator/HaplotypeScore.java index 3ad9b12ca..cf726ed65 100755 --- a/java/src/org/broadinstitute/sting/gatk/walkers/annotator/HaplotypeScore.java +++ b/java/src/org/broadinstitute/sting/gatk/walkers/annotator/HaplotypeScore.java @@ -42,7 +42,7 @@ import java.util.*; import net.sf.samtools.SAMRecord; // todo -- rename to haplotype penalty -public class HaplotypeScore implements InfoFieldAnnotation, WorkInProgressAnnotation { +public class HaplotypeScore implements InfoFieldAnnotation, StandardAnnotation { private final static boolean DEBUG = false; private final static int MIN_CONTEXT_WING_SIZE = 10; diff --git a/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java b/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java index d1ec4e681..a0608ed38 100755 --- a/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java +++ b/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java @@ -66,7 +66,7 @@ public class VariantAnnotatorIntegrationTest extends WalkerTest { public void testHasAnnotsAsking1() { WalkerTestSpec spec = new WalkerTestSpec( baseTestString() + " -G \"Standard\" -B variant,VCF," + validationDataLocation + "vcfexample2.vcf -I " + validationDataLocation + "low_coverage_CEU.chr1.10k-11k.bam -L 1:10,020,000-10,021,000", 1, - Arrays.asList("fb1180d956d92080c43058fd6a562385")); + Arrays.asList("08fa964f33cdf934af8cb46a9cc03ff2")); executeTest("test file has annotations, asking for annotations, #1", spec); } @@ -74,7 +74,7 @@ public class VariantAnnotatorIntegrationTest extends WalkerTest { public void testHasAnnotsAsking2() { WalkerTestSpec spec = new WalkerTestSpec( baseTestString() + " -G \"Standard\" -B variant,VCF," + validationDataLocation + "vcfexample3.vcf -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -L 1:10,000,000-10,050,000", 1, - Arrays.asList("1ff5f1d3fc1a938a2763e2b9ded5db3f")); + Arrays.asList("8d57463554486cf077faf190b5af5f2d")); executeTest("test file has annotations, asking for annotations, #2", spec); } @@ -98,7 +98,7 @@ public class VariantAnnotatorIntegrationTest extends WalkerTest { public void testNoAnnotsAsking1() { WalkerTestSpec spec = new WalkerTestSpec( baseTestString() + " -G \"Standard\" -B variant,VCF," + validationDataLocation + "vcfexample2empty.vcf -I " + validationDataLocation + "low_coverage_CEU.chr1.10k-11k.bam -L 1:10,020,000-10,021,000", 1, - Arrays.asList("fb32a176d4e6df563d5d4d3ad1237baf")); + Arrays.asList("fc240f58f073071a6edf4d11b74fb493")); executeTest("test file doesn't have annotations, asking for annotations, #1", spec); } @@ -106,7 +106,7 @@ public class VariantAnnotatorIntegrationTest extends WalkerTest { public void testNoAnnotsAsking2() { WalkerTestSpec spec = new WalkerTestSpec( baseTestString() + " -G \"Standard\" -B variant,VCF," + validationDataLocation + "vcfexample3empty.vcf -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -L 1:10,000,000-10,050,000", 1, - Arrays.asList("88edec2c057b5074e4e1ffc1ca0c2332")); + Arrays.asList("9d8b72384e90c5f8f278da9558ac2419")); executeTest("test file doesn't have annotations, asking for annotations, #2", spec); } diff --git a/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java b/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java index d812a60af..918ff0f39 100755 --- a/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java +++ b/java/test/org/broadinstitute/sting/gatk/walkers/genotyper/UnifiedGenotyperIntegrationTest.java @@ -35,7 +35,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { public void testMultiSamplePilot1Joint() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + oneKGLocation + "reference/human_b36_both.fasta -I " + validationDataLocation + "low_coverage_CEU.chr1.10k-11k.bam -varout %s -L 1:10,022,000-10,025,000", 1, - Arrays.asList("d50ebc40d935ece7e57aafc7355bec77")); + Arrays.asList("3f919977584b2c15273cb7de948dd1ac")); executeTest("testMultiSamplePilot1 - Joint Estimate", spec); } @@ -43,7 +43,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { public void testMultiSamplePilot2Joint() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + oneKGLocation + "reference/human_b36_both.fasta -I " + validationDataLocation + "pilot2_daughters.chr20.10k-11k.bam -varout %s -L 20:10,000,000-10,050,000", 1, - Arrays.asList("2f113c2b1cd0d36522fc24e7784a2b7d")); + Arrays.asList("d45934ae6537a84bb123db2288ad235e")); executeTest("testMultiSamplePilot2 - Joint Estimate", spec); } @@ -51,7 +51,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { public void testSingleSamplePilot2Joint() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + oneKGLocation + "reference/human_b36_both.fasta -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -varout %s -L 1:10,000,000-10,100,000", 1, - Arrays.asList("4f08c27ada3ad1a33d12d106bc80dab6")); + Arrays.asList("96245f0842534527b66a9daad53134bd")); executeTest("testSingleSamplePilot2 - Joint Estimate", spec); } @@ -64,7 +64,7 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { public void testParallelization() { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + oneKGLocation + "reference/human_b36_both.fasta -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -varout %s -L 1:10,000,000-10,400,000 -nt 4", 1, - Arrays.asList("d643e60343c05817dcb4fafb7870804d")); + Arrays.asList("60bf51595eda646f5ccf0b0bf5db95d8")); executeTest("test parallelization", spec); } @@ -77,11 +77,11 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { @Test public void testParameter() { HashMap e = new HashMap(); - e.put( "-genotype", "03e228232eeb0a32ea3791daec29248c" ); - e.put( "-all_bases", "fe894f335e048d89fccd7a7b39a105a1" ); - e.put( "--min_base_quality_score 26", "a1142c69f1951a05d5a33215c69133af" ); - e.put( "--min_mapping_quality_score 26", "796d1ea790481a1a257609279f8076bb" ); - e.put( "--max_mismatches_in_40bp_window 5", "379bd56d4402e974127e0677ff51d040" ); + e.put( "-genotype", "d301500f0cd5ef1929a1adce7e857f9c" ); + e.put( "-all_bases", "70e94c6671a3e5122cb9ad04c0ad138e" ); + e.put( "--min_base_quality_score 26", "c508728f9d26cc3a8b73f3a5ee4275f2" ); + e.put( "--min_mapping_quality_score 26", "34634ea8f196eaf40dac6e069ebcf09a" ); + e.put( "--max_mismatches_in_40bp_window 5", "92903b97b43145c24f19a899ce127aa3" ); for ( Map.Entry entry : e.entrySet() ) { WalkerTest.WalkerTestSpec spec = new WalkerTest.WalkerTestSpec( @@ -95,12 +95,12 @@ public class UnifiedGenotyperIntegrationTest extends WalkerTest { public void testConfidence() { WalkerTest.WalkerTestSpec spec1 = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + oneKGLocation + "reference/human_b36_both.fasta -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -varout %s -L 1:10,000,000-10,010,000 -stand_call_conf 10 ", 1, - Arrays.asList("7b41dc669e8a0abde089d7aeedab2941")); + Arrays.asList("cdcc3977ce78e15d7c8153eaf5f9a2df")); executeTest("testConfidence1", spec1); WalkerTest.WalkerTestSpec spec2 = new WalkerTest.WalkerTestSpec( "-T UnifiedGenotyper -R " + oneKGLocation + "reference/human_b36_both.fasta -I " + validationDataLocation + "NA12878.1kg.p2.chr1_10mb_11_mb.SLX.bam -varout %s -L 1:10,000,000-10,010,000 -stand_emit_conf 10 ", 1, - Arrays.asList("258617b8de0e6468bf6a0c740b51676b")); + Arrays.asList("2413aafdcfd3d8ac1169662f72524035")); executeTest("testConfidence2", spec2); }