From d78e00e5b2cd5e8a1b1aa75209100b039e521442 Mon Sep 17 00:00:00 2001 From: David Roazen Date: Thu, 15 Sep 2011 16:09:07 -0400 Subject: [PATCH] Renaming VariantAnnotator SnpEff keys This is to head off potential confusion with the output from the SnpEff tool itself, which also uses a key named EFF. --- .../sting/gatk/walkers/annotator/SnpEff.java | 90 ++++++++++--------- .../stratifications/FunctionalClass.java | 4 +- .../VariantAnnotatorIntegrationTest.java | 2 +- .../VariantEvalIntegrationTest.java | 2 +- 4 files changed, 53 insertions(+), 45 deletions(-) diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/SnpEff.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/SnpEff.java index bb3685fb5..4ead77506 100644 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/SnpEff.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/SnpEff.java @@ -68,23 +68,31 @@ public class SnpEff extends InfoFieldAnnotation implements ExperimentalAnnotatio // Key names for the INFO field annotations we will add to each record, along // with parsing-related information: public enum InfoFieldKey { - EFF (-1), - EFF_IMPACT (0), - EFF_CODON_CHANGE (1), - EFF_AMINO_ACID_CHANGE (2), - EFF_GENE_NAME (3), - EFF_GENE_BIOTYPE (4), - EFF_TRANSCRIPT_ID (6), - EFF_EXON_ID (7); + EFFECT_KEY ("SNPEFF_EFFECT", -1), + IMPACT_KEY ("SNPEFF_IMPACT", 0), + CODON_CHANGE_KEY ("SNPEFF_CODON_CHANGE", 1), + AMINO_ACID_CHANGE_KEY ("SNPEFF_AMINO_ACID_CHANGE", 2), + GENE_NAME_KEY ("SNPEFF_GENE_NAME", 3), + GENE_BIOTYPE_KEY ("SNPEFF_GENE_BIOTYPE", 4), + TRANSCRIPT_ID_KEY ("SNPEFF_TRANSCRIPT_ID", 6), + EXON_ID_KEY ("SNPEFF_EXON_ID", 7); + + // Actual text of the key + private final String keyName; // Index within the effect metadata subfields from the SnpEff EFF annotation // where each key's associated value can be found during parsing. private final int fieldIndex; - InfoFieldKey ( int fieldIndex ) { + InfoFieldKey ( String keyName, int fieldIndex ) { + this.keyName = keyName; this.fieldIndex = fieldIndex; } + public String getKeyName() { + return keyName; + } + public int getFieldIndex() { return fieldIndex; } @@ -292,27 +300,27 @@ public class SnpEff extends InfoFieldAnnotation implements ExperimentalAnnotatio } public List getKeyNames() { - return Arrays.asList( InfoFieldKey.EFF.toString(), - InfoFieldKey.EFF_IMPACT.toString(), - InfoFieldKey.EFF_CODON_CHANGE.toString(), - InfoFieldKey.EFF_AMINO_ACID_CHANGE.toString(), - InfoFieldKey.EFF_GENE_NAME.toString(), - InfoFieldKey.EFF_GENE_BIOTYPE.toString(), - InfoFieldKey.EFF_TRANSCRIPT_ID.toString(), - InfoFieldKey.EFF_EXON_ID.toString() + return Arrays.asList( InfoFieldKey.EFFECT_KEY.getKeyName(), + InfoFieldKey.IMPACT_KEY.getKeyName(), + InfoFieldKey.CODON_CHANGE_KEY.getKeyName(), + InfoFieldKey.AMINO_ACID_CHANGE_KEY.getKeyName(), + InfoFieldKey.GENE_NAME_KEY.getKeyName(), + InfoFieldKey.GENE_BIOTYPE_KEY.getKeyName(), + InfoFieldKey.TRANSCRIPT_ID_KEY.getKeyName(), + InfoFieldKey.EXON_ID_KEY.getKeyName() ); } public List getDescriptions() { return Arrays.asList( - new VCFInfoHeaderLine(InfoFieldKey.EFF.toString(), 1, VCFHeaderLineType.String, "The highest-impact effect resulting from the current variant (or one of the highest-impact effects, if there is a tie)"), - new VCFInfoHeaderLine(InfoFieldKey.EFF_IMPACT.toString(), 1, VCFHeaderLineType.String, "Impact of the highest-impact effect resulting from the current variant " + Arrays.toString(EffectImpact.values())), - new VCFInfoHeaderLine(InfoFieldKey.EFF_CODON_CHANGE.toString(), 1, VCFHeaderLineType.String, "Old/New codon for the highest-impact effect resulting from the current variant"), - new VCFInfoHeaderLine(InfoFieldKey.EFF_AMINO_ACID_CHANGE.toString(), 1, VCFHeaderLineType.String, "Old/New amino acid for the highest-impact effect resulting from the current variant"), - new VCFInfoHeaderLine(InfoFieldKey.EFF_GENE_NAME.toString(), 1, VCFHeaderLineType.String, "Gene name for the highest-impact effect resulting from the current variant"), - new VCFInfoHeaderLine(InfoFieldKey.EFF_GENE_BIOTYPE.toString(), 1, VCFHeaderLineType.String, "Gene biotype for the highest-impact effect resulting from the current variant"), - new VCFInfoHeaderLine(InfoFieldKey.EFF_TRANSCRIPT_ID.toString(), 1, VCFHeaderLineType.String, "Transcript ID for the highest-impact effect resulting from the current variant"), - new VCFInfoHeaderLine(InfoFieldKey.EFF_EXON_ID.toString(), 1, VCFHeaderLineType.String, "Exon ID for the highest-impact effect resulting from the current variant") + new VCFInfoHeaderLine(InfoFieldKey.EFFECT_KEY.getKeyName(), 1, VCFHeaderLineType.String, "The highest-impact effect resulting from the current variant (or one of the highest-impact effects, if there is a tie)"), + new VCFInfoHeaderLine(InfoFieldKey.IMPACT_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Impact of the highest-impact effect resulting from the current variant " + Arrays.toString(EffectImpact.values())), + new VCFInfoHeaderLine(InfoFieldKey.CODON_CHANGE_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Old/New codon for the highest-impact effect resulting from the current variant"), + new VCFInfoHeaderLine(InfoFieldKey.AMINO_ACID_CHANGE_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Old/New amino acid for the highest-impact effect resulting from the current variant"), + new VCFInfoHeaderLine(InfoFieldKey.GENE_NAME_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Gene name for the highest-impact effect resulting from the current variant"), + new VCFInfoHeaderLine(InfoFieldKey.GENE_BIOTYPE_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Gene biotype for the highest-impact effect resulting from the current variant"), + new VCFInfoHeaderLine(InfoFieldKey.TRANSCRIPT_ID_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Transcript ID for the highest-impact effect resulting from the current variant"), + new VCFInfoHeaderLine(InfoFieldKey.EXON_ID_KEY.getKeyName(), 1, VCFHeaderLineType.String, "Exon ID for the highest-impact effect resulting from the current variant") ); } @@ -375,16 +383,16 @@ public class SnpEff extends InfoFieldAnnotation implements ExperimentalAnnotatio } try { - impact = EffectImpact.valueOf(effectMetadata[InfoFieldKey.EFF_IMPACT.getFieldIndex()]); + impact = EffectImpact.valueOf(effectMetadata[InfoFieldKey.IMPACT_KEY.getFieldIndex()]); } catch ( IllegalArgumentException e ) { - parseError(String.format("Unrecognized value for effect impact: %s", effectMetadata[InfoFieldKey.EFF_IMPACT.getFieldIndex()])); + parseError(String.format("Unrecognized value for effect impact: %s", effectMetadata[InfoFieldKey.IMPACT_KEY.getFieldIndex()])); } - codonChange = effectMetadata[InfoFieldKey.EFF_CODON_CHANGE.getFieldIndex()]; - aminoAcidChange = effectMetadata[InfoFieldKey.EFF_AMINO_ACID_CHANGE.getFieldIndex()]; - geneName = effectMetadata[InfoFieldKey.EFF_GENE_NAME.getFieldIndex()]; - geneBiotype = effectMetadata[InfoFieldKey.EFF_GENE_BIOTYPE.getFieldIndex()]; + codonChange = effectMetadata[InfoFieldKey.CODON_CHANGE_KEY.getFieldIndex()]; + aminoAcidChange = effectMetadata[InfoFieldKey.AMINO_ACID_CHANGE_KEY.getFieldIndex()]; + geneName = effectMetadata[InfoFieldKey.GENE_NAME_KEY.getFieldIndex()]; + geneBiotype = effectMetadata[InfoFieldKey.GENE_BIOTYPE_KEY.getFieldIndex()]; if ( effectMetadata[SNPEFF_CODING_FIELD_INDEX].trim().length() > 0 ) { try { @@ -398,8 +406,8 @@ public class SnpEff extends InfoFieldAnnotation implements ExperimentalAnnotatio coding = EffectCoding.UNKNOWN; } - transcriptID = effectMetadata[InfoFieldKey.EFF_TRANSCRIPT_ID.getFieldIndex()]; - exonID = effectMetadata[InfoFieldKey.EFF_EXON_ID.getFieldIndex()]; + transcriptID = effectMetadata[InfoFieldKey.TRANSCRIPT_ID_KEY.getFieldIndex()]; + exonID = effectMetadata[InfoFieldKey.EXON_ID_KEY.getFieldIndex()]; } private void parseError ( String message ) { @@ -443,14 +451,14 @@ public class SnpEff extends InfoFieldAnnotation implements ExperimentalAnnotatio public Map getAnnotations() { Map annotations = new LinkedHashMap(Utils.optimumHashSize(InfoFieldKey.values().length)); - addAnnotation(annotations, InfoFieldKey.EFF.toString(), effect.toString()); - addAnnotation(annotations, InfoFieldKey.EFF_IMPACT.toString(), impact.toString()); - addAnnotation(annotations, InfoFieldKey.EFF_CODON_CHANGE.toString(), codonChange); - addAnnotation(annotations, InfoFieldKey.EFF_AMINO_ACID_CHANGE.toString(), aminoAcidChange); - addAnnotation(annotations, InfoFieldKey.EFF_GENE_NAME.toString(), geneName); - addAnnotation(annotations, InfoFieldKey.EFF_GENE_BIOTYPE.toString(), geneBiotype); - addAnnotation(annotations, InfoFieldKey.EFF_TRANSCRIPT_ID.toString(), transcriptID); - addAnnotation(annotations, InfoFieldKey.EFF_EXON_ID.toString(), exonID); + addAnnotation(annotations, InfoFieldKey.EFFECT_KEY.getKeyName(), effect.toString()); + addAnnotation(annotations, InfoFieldKey.IMPACT_KEY.getKeyName(), impact.toString()); + addAnnotation(annotations, InfoFieldKey.CODON_CHANGE_KEY.getKeyName(), codonChange); + addAnnotation(annotations, InfoFieldKey.AMINO_ACID_CHANGE_KEY.getKeyName(), aminoAcidChange); + addAnnotation(annotations, InfoFieldKey.GENE_NAME_KEY.getKeyName(), geneName); + addAnnotation(annotations, InfoFieldKey.GENE_BIOTYPE_KEY.getKeyName(), geneBiotype); + addAnnotation(annotations, InfoFieldKey.TRANSCRIPT_ID_KEY.getKeyName(), transcriptID); + addAnnotation(annotations, InfoFieldKey.EXON_ID_KEY.getKeyName(), exonID); return annotations; } diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/varianteval/stratifications/FunctionalClass.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/varianteval/stratifications/FunctionalClass.java index a32857ffc..88ffcaaeb 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/varianteval/stratifications/FunctionalClass.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/varianteval/stratifications/FunctionalClass.java @@ -62,8 +62,8 @@ public class FunctionalClass extends VariantStratifier { annotationId++; } while (eval.hasAttribute(key)); - } else if ( eval.hasAttribute(SnpEff.InfoFieldKey.EFF.name() ) ) { - SnpEff.EffectType snpEffType = SnpEff.EffectType.valueOf(eval.getAttribute(SnpEff.InfoFieldKey.EFF.name()).toString()); + } else if ( eval.hasAttribute(SnpEff.InfoFieldKey.EFFECT_KEY.getKeyName() ) ) { + SnpEff.EffectType snpEffType = SnpEff.EffectType.valueOf(eval.getAttribute(SnpEff.InfoFieldKey.EFFECT_KEY.getKeyName()).toString()); if ( snpEffType == SnpEff.EffectType.STOP_GAINED ) type = FunctionalType.nonsense; else if ( snpEffType == SnpEff.EffectType.NON_SYNONYMOUS_CODING ) diff --git a/public/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java b/public/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java index f902ce276..08baae7a7 100755 --- a/public/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java +++ b/public/java/test/org/broadinstitute/sting/gatk/walkers/annotator/VariantAnnotatorIntegrationTest.java @@ -134,7 +134,7 @@ public class VariantAnnotatorIntegrationTest extends WalkerTest { validationDataLocation + "1kg_exomes_unfiltered.AFR.unfiltered.vcf --snpEffFile " + validationDataLocation + "snpEff.AFR.unfiltered.vcf -L 1:1-1,500,000", 1, - Arrays.asList("a1c3ba9efc28ee0606339604095076ea") + Arrays.asList("486fc6a5ca1819f5ab180d5d72b1ebc9") ); executeTest("Testing SnpEff annotations", spec); } diff --git a/public/java/test/org/broadinstitute/sting/gatk/walkers/varianteval/VariantEvalIntegrationTest.java b/public/java/test/org/broadinstitute/sting/gatk/walkers/varianteval/VariantEvalIntegrationTest.java index 99622cbf6..b90e6d0ff 100755 --- a/public/java/test/org/broadinstitute/sting/gatk/walkers/varianteval/VariantEvalIntegrationTest.java +++ b/public/java/test/org/broadinstitute/sting/gatk/walkers/varianteval/VariantEvalIntegrationTest.java @@ -32,7 +32,7 @@ public class VariantEvalIntegrationTest extends WalkerTest { 1, Arrays.asList("f5f811ceb973d7fd6c1b2b734f1b2b12") ); - executeTest("testStratifySamplesAndExcludeMonomorphicSites", spec); + executeTest("testFunctionClassWithSnpeff", spec); } @Test