From 4fe21b3afb233c033f6dd7d1ee7242dc3ed7d1ae Mon Sep 17 00:00:00 2001 From: Manda Wilson <1458628+mandawilson@users.noreply.github.com> Date: Tue, 8 Feb 2022 10:21:03 -0500 Subject: [PATCH] changed IS_GERMLINE to SV_STATUS --- .../cbio/portal/dao/DaoStructuralVariant.java | 11 +-- .../cbio/portal/model/StructuralVariant.java | 10 +- .../scripts/ImportStructuralVariantData.java | 23 ++--- .../portal/util/StructuralVariantUtil.java | 14 +-- .../resources/data_structural_variants.txt | 6 +- ...ctural_variants_exon_not_in_transcript.txt | 16 ++-- ...ta_structural_variants_missing_columns.txt | 16 ++-- ...ata_structural_variants_missing_values.txt | 16 ++-- ...ariants_transcript_not_in_genome_nexus.txt | 16 ++-- .../study_es_0/data_structural_variants.txt | 92 +++++++++---------- db-scripts/src/main/resources/cgds.sql | 6 +- db-scripts/src/main/resources/migration.sql | 3 +- docs/File-Formats.md | 2 +- .../cbioportal/model/StructuralVariant.java | 10 +- .../mybatis/StructuralVariantMapper.xml | 2 +- ...tructuralVariantMyBatisRepositoryTest.java | 4 +- .../src/test/resources/testSql.sql | 28 +++--- .../web/StructuralVariantControllerTest.java | 8 +- 18 files changed, 143 insertions(+), 140 deletions(-) diff --git a/core/src/main/java/org/mskcc/cbio/portal/dao/DaoStructuralVariant.java b/core/src/main/java/org/mskcc/cbio/portal/dao/DaoStructuralVariant.java index 1e8c3ddc240..7943d1b0c52 100644 --- a/core/src/main/java/org/mskcc/cbio/portal/dao/DaoStructuralVariant.java +++ b/core/src/main/java/org/mskcc/cbio/portal/dao/DaoStructuralVariant.java @@ -81,7 +81,7 @@ public static void addStructuralVariantToBulkLoader(StructuralVariant structural "LENGTH", "COMMENTS", "EXTERNAL_ANNOTATION", - "IS_GERMLINE", + "SV_STATUS", }; bl.setFieldNames(fieldNames); @@ -90,13 +90,13 @@ public static void addStructuralVariantToBulkLoader(StructuralVariant structural Long.toString(structuralVariant.getInternalId()), Integer.toString(structuralVariant.getGeneticProfileId()), Integer.toString(structuralVariant.getSampleIdInternal()), - Long.toString(structuralVariant.getSite1EntrezGeneId()), + structuralVariant.getSite1EntrezGeneId() == null ? null : Long.toString(structuralVariant.getSite1EntrezGeneId()), structuralVariant.getSite1EnsemblTranscriptId(), Integer.toString(structuralVariant.getSite1Exon()), structuralVariant.getSite1Chromosome(), Integer.toString(structuralVariant.getSite1Position()), structuralVariant.getSite1Description(), - Long.toString(structuralVariant.getSite2EntrezGeneId()), + structuralVariant.getSite2EntrezGeneId() == null ? null : Long.toString(structuralVariant.getSite2EntrezGeneId()), structuralVariant.getSite2EnsemblTranscriptId(), Integer.toString(structuralVariant.getSite2Exon()), structuralVariant.getSite2Chromosome(), @@ -123,8 +123,7 @@ public static void addStructuralVariantToBulkLoader(StructuralVariant structural Integer.toString(structuralVariant.getLength()), structuralVariant.getComments(), structuralVariant.getExternalAnnotation(), - Integer.toString(structuralVariant.getIsGermline()?1:0)); -//TODO: fix this ... the value must be converted to an integer + structuralVariant.getSvStatus()); if ((structuralVariant.getDriverFilter() != null && !structuralVariant.getDriverFilter().isEmpty() @@ -240,7 +239,7 @@ private static StructuralVariant extractStructuralVariant(ResultSet rs) throws S structuralVariant.setDriverFilterAnn(rs.getString("DRIVER_FILTER_ANNOTATION")); structuralVariant.setDriverTiersFilter(rs.getString("DRIVER_TIERS_FILTER")); structuralVariant.setDriverTiersFilterAnn(rs.getString("DRIVER_TIERS_FILTER_ANNOTATION")); - structuralVariant.setIsGermline(rs.getBoolean("IS_GERMLINE")); + structuralVariant.setSvStatus(rs.getString("SV_STATUS")); return structuralVariant; } } diff --git a/core/src/main/java/org/mskcc/cbio/portal/model/StructuralVariant.java b/core/src/main/java/org/mskcc/cbio/portal/model/StructuralVariant.java index 69a4b0ee654..a06345708c2 100644 --- a/core/src/main/java/org/mskcc/cbio/portal/model/StructuralVariant.java +++ b/core/src/main/java/org/mskcc/cbio/portal/model/StructuralVariant.java @@ -69,7 +69,7 @@ public class StructuralVariant { private String driverFilterAnn; private String driverTiersFilter; private String driverTiersFilterAnn; - private Boolean isGermline; + private String svStatus; public long getInternalId() { return internalId; @@ -335,10 +335,10 @@ public String getDriverTiersFilterAnn() { public void setDriverTiersFilterAnn(String driverTiersFilterAnn) { this.driverTiersFilterAnn = driverTiersFilterAnn; } - public Boolean getIsGermline() { - return isGermline; + public String getSvStatus() { + return svStatus; } - public void setIsGermline(Boolean isGermline) { - this.isGermline = isGermline; + public void setSvStatus(String svStatus) { + this.svStatus = svStatus; } } diff --git a/core/src/main/java/org/mskcc/cbio/portal/scripts/ImportStructuralVariantData.java b/core/src/main/java/org/mskcc/cbio/portal/scripts/ImportStructuralVariantData.java index ef6bd127e51..54cb7f63bb9 100644 --- a/core/src/main/java/org/mskcc/cbio/portal/scripts/ImportStructuralVariantData.java +++ b/core/src/main/java/org/mskcc/cbio/portal/scripts/ImportStructuralVariantData.java @@ -111,22 +111,23 @@ public void importData() throws IOException, DaoException { CanonicalGene site2CanonicalGene = setCanonicalGene(site2EntrezGeneId, site2HugoSymbol, daoGene); // If neither of the genes is recognized, skip the line - if(site1CanonicalGene == null) { - ProgressMonitor.logWarning("Gene not found: " + site1HugoSymbol + " [" - + site1EntrezGeneId + "]. Ignoring it " - + "and all fusion data associated with it!"); - } else if (site2CanonicalGene == null) { - ProgressMonitor.logWarning("Gene not found: " + site2HugoSymbol + " [" + if(site1CanonicalGene == null && site2CanonicalGene == null) { + ProgressMonitor.logWarning("Could not find gene 1: " + site1HugoSymbol + " [" + site1EntrezGeneId + + "] or gene 2: " + site2HugoSymbol + " [" + site2EntrezGeneId + "]. Ignoring it " - + "and all fusion data associated with it!"); - // If both genes are recognized, continue + + "and all SV data associated with it!"); + // If at least one gene is recognized, continue } else { // Save the Entrez Gene Id if it was not saved before - if (site1EntrezGeneId == TabDelimitedFileUtil.NA_LONG) { + if (site1EntrezGeneId == TabDelimitedFileUtil.NA_LONG && site1CanonicalGene != null) { structuralVariant.setSite1EntrezGeneId(site1CanonicalGene.getEntrezGeneId()); + } else if (site1EntrezGeneId == TabDelimitedFileUtil.NA_LONG) { + structuralVariant.setSite1EntrezGeneId(null); // we want this to be null in the database, not NA_LONG } - if (site2EntrezGeneId == TabDelimitedFileUtil.NA_LONG) { + if (site2EntrezGeneId == TabDelimitedFileUtil.NA_LONG && site2CanonicalGene != null) { structuralVariant.setSite2EntrezGeneId(site2CanonicalGene.getEntrezGeneId()); + } else if (site2EntrezGeneId == TabDelimitedFileUtil.NA_LONG) { + structuralVariant.setSite2EntrezGeneId(null); // we want this to be null in the database, not NA_LONG } // Add structural variant DaoStructuralVariant.addStructuralVariantToBulkLoader(structuralVariant); @@ -160,7 +161,7 @@ private CanonicalGene setCanonicalGene(long siteEntrezGeneId, String siteHugoSym } // If no gene can be found based on Entrez Gene ID, try Symbol. - if (siteCanonicalGene == null) { + if (siteCanonicalGene == null && !TabDelimitedFileUtil.NA_STRING.equals(siteHugoSymbol)) { siteCanonicalGene = daoGene.getNonAmbiguousGene(siteHugoSymbol, true); } diff --git a/core/src/main/java/org/mskcc/cbio/portal/util/StructuralVariantUtil.java b/core/src/main/java/org/mskcc/cbio/portal/util/StructuralVariantUtil.java index 3bf6636fb16..80cde707f6d 100644 --- a/core/src/main/java/org/mskcc/cbio/portal/util/StructuralVariantUtil.java +++ b/core/src/main/java/org/mskcc/cbio/portal/util/StructuralVariantUtil.java @@ -83,8 +83,8 @@ public class StructuralVariantUtil { public static final String DRIVER_FILTER_ANNOTATION = "cbp_driver_annotation"; public static final String DRIVER_TIERS_FILTER = "cbp_driver_tiers"; public static final String DRIVER_TIERS_FILTER_ANNOTATION = "cbp_driver_tiers_annotation"; - public static final String IS_GERMLINE = "is_germline"; - + public static final String SV_STATUS = "Sv_Status"; + public StructuralVariantUtil(){} public StructuralVariantUtil(String line) { @@ -140,7 +140,10 @@ public StructuralVariant parseStructuralVariantRecord(String[] parts) { structuralVariant.setDriverFilterAnn(TabDelimitedFileUtil.getPartString(getColumnIndex(StructuralVariantUtil.DRIVER_FILTER_ANNOTATION), parts)); structuralVariant.setDriverTiersFilter(TabDelimitedFileUtil.getPartString(getColumnIndex(StructuralVariantUtil.DRIVER_TIERS_FILTER), parts)); structuralVariant.setDriverTiersFilterAnn(TabDelimitedFileUtil.getPartString(getColumnIndex(StructuralVariantUtil.DRIVER_TIERS_FILTER_ANNOTATION), parts)); - structuralVariant.setIsGermline(TabDelimitedFileUtil.getPartInt(getColumnIndex(StructuralVariantUtil.IS_GERMLINE), parts) != 0); + structuralVariant.setSvStatus(TabDelimitedFileUtil.getPartString(getColumnIndex(StructuralVariantUtil.SV_STATUS), parts)); + if (TabDelimitedFileUtil.NA_STRING.equals(structuralVariant.getSvStatus())) { + structuralVariant.setSvStatus(null); // we want to use the database default + } return structuralVariant; } @@ -162,7 +165,7 @@ public int getColumnIndex(String colName) { * If a structural variant record has a mix of defined and missing values for Site 1 or Site 2 * Ensembl transcript IDs and/or exons then the structural variant record will not be imported. * - * Example (assuming that site 1 and site 2 hugo symbol and/or entrez id are present): + * Example (assuming that site 1 or site 2 hugo symbol and/or entrez id are present): * * Valid Record: * Site 1 Transcript: EST0000024958 @@ -195,8 +198,7 @@ public Boolean hasRequiredStructuralVariantFields(StructuralVariant record) { record.getSite1Exon() != -1 && record.getSite2Exon() != -1); return ( hasNoEnsemblExonValues || hasAllEnsemblExonValues ) && - (record.getSite1EntrezGeneId() != Long.MIN_VALUE || !record.getSite1HugoSymbol().equalsIgnoreCase(TabDelimitedFileUtil.NA_STRING)) && - (record.getSite2EntrezGeneId() != Long.MIN_VALUE || !record.getSite2HugoSymbol().equalsIgnoreCase(TabDelimitedFileUtil.NA_STRING)); + (record.getSite1EntrezGeneId() != Long.MIN_VALUE || !record.getSite1HugoSymbol().equalsIgnoreCase(TabDelimitedFileUtil.NA_STRING) || record.getSite2EntrezGeneId() != Long.MIN_VALUE || !record.getSite2HugoSymbol().equalsIgnoreCase(TabDelimitedFileUtil.NA_STRING)); } } diff --git a/core/src/test/resources/data_structural_variants.txt b/core/src/test/resources/data_structural_variants.txt index 765bfa7ff11..7e0d6659376 100644 --- a/core/src/test/resources/data_structural_variants.txt +++ b/core/src/test/resources/data_structural_variants.txt @@ -1,3 +1,3 @@ -Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation is_germline -TCGA-A1-A0SB-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA 0 -TCGA-A1-A0SD-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA 0 +Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation Sv_Status +TCGA-A1-A0SB-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA SOMATIC +TCGA-A1-A0SD-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA SOMATIC diff --git a/core/src/test/scripts/test_data/data_structural_variants_exon_not_in_transcript.txt b/core/src/test/scripts/test_data/data_structural_variants_exon_not_in_transcript.txt index a270e306a89..2ebb348a1a4 100644 --- a/core/src/test/scripts/test_data/data_structural_variants_exon_not_in_transcript.txt +++ b/core/src/test/scripts/test_data/data_structural_variants_exon_not_in_transcript.txt @@ -1,8 +1,8 @@ -Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation is_germline -TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 1500 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA 0 -TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA EML4 ENST00000318522 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 2000 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA 0 -TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA 0 -TCGA-A2-A04P-01 NA EGFR ENST00000275493 1 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA 0 +Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation Sv_Status +TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 1500 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EML4 ENST00000318522 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 2000 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EGFR ENST00000275493 1 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA SOMATIC diff --git a/core/src/test/scripts/test_data/data_structural_variants_missing_columns.txt b/core/src/test/scripts/test_data/data_structural_variants_missing_columns.txt index 183bc09756b..184096397fb 100644 --- a/core/src/test/scripts/test_data/data_structural_variants_missing_columns.txt +++ b/core/src/test/scripts/test_data/data_structural_variants_missing_columns.txt @@ -1,8 +1,8 @@ -Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation is_germline -TCGA-A2-A04P-01 NA KIAA1549 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA 0 -TCGA-A2-A04P-01 NA NCOA4 10 51582939 NCOA4-RET.N7R12_1 NA RET 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA EML4 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA 0 -TCGA-A2-A04P-01 NA TMPRSS2 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA 0 -TCGA-A2-A04P-01 NA EGFR 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA ALK 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A1-A0SB-01 NA EML4 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA 0 +Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation Sv_Status +TCGA-A2-A04P-01 NA KIAA1549 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA NCOA4 10 51582939 NCOA4-RET.N7R12_1 NA RET 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EML4 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA TMPRSS2 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EGFR 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA ALK 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A1-A0SB-01 NA EML4 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA SOMATIC diff --git a/core/src/test/scripts/test_data/data_structural_variants_missing_values.txt b/core/src/test/scripts/test_data/data_structural_variants_missing_values.txt index 7d0da42e470..dadbb4131a7 100644 --- a/core/src/test/scripts/test_data/data_structural_variants_missing_values.txt +++ b/core/src/test/scripts/test_data/data_structural_variants_missing_values.txt @@ -1,8 +1,8 @@ -Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation is_germline -TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA 0 -TCGA-A2-A04P-01 NA NCOA4 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA EML4 ENST00000318522 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 20 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA 0 -TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA 0 -TCGA-A2-A04P-01 NA EGFR ENST00000275493 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA 0 +Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation Sv_Status +TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA NCOA4 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EML4 ENST00000318522 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 20 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EGFR ENST00000275493 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA SOMATIC diff --git a/core/src/test/scripts/test_data/data_structural_variants_transcript_not_in_genome_nexus.txt b/core/src/test/scripts/test_data/data_structural_variants_transcript_not_in_genome_nexus.txt index 51701dae0c2..a02f5fdb260 100644 --- a/core/src/test/scripts/test_data/data_structural_variants_transcript_not_in_genome_nexus.txt +++ b/core/src/test/scripts/test_data/data_structural_variants_transcript_not_in_genome_nexus.txt @@ -1,8 +1,8 @@ -Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation is_germline -TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA 0 -TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA EML4 TEST_TRANSCRIPT 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 20 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA 0 -TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA 0 -TCGA-A2-A04P-01 NA EGFR ENST00000275493 1 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA 0 +Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation Sv_Status +TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EML4 TEST_TRANSCRIPT 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 20 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EGFR ENST00000275493 1 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA SOMATIC diff --git a/core/src/test/scripts/test_data/study_es_0/data_structural_variants.txt b/core/src/test/scripts/test_data/study_es_0/data_structural_variants.txt index 4c87d171bc7..167a5da065b 100644 --- a/core/src/test/scripts/test_data/study_es_0/data_structural_variants.txt +++ b/core/src/test/scripts/test_data/study_es_0/data_structural_variants.txt @@ -1,46 +1,46 @@ -Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation is_germline -TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA 0 -TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA EML4 ENST00000318522 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 20 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA 0 -TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA 0 -TCGA-A2-A04P-01 NA EGFR ENST00000275493 1 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA 0 -TCGA-A1-A0SB-01 NA TMPRSS2 ENST00000455813 1 21 42870045 TMPRSS2-ETV1.T1bE4_1 NA ETV1 ENST00000405358 4 7 14017105 TMPRSS2-ETV1.T1bE4_2 NA GRCh37 no yes NA 1007 NA 200 NA NA NA NA TMPRSS2-ETV1.T1bE4 NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-TTN.CUSTOMHYVE_1 NA TTN ENST00000589042 2 1 111111111 NCOA4-TTN.CUSTOMHYVE_2 NA GRCh37 no yes NA 1008 NA 100 NA NA NA NA NCOA4-TTN.CUSTOMHYVE NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A2-A04P-01 NA TTN ENST00000589042 28 1 222222222 TTN_ALK.CUSTOMHYVE_1 NA ALK ENST00000389048 20 2 29446394 TTN_ALK.CUSTOMHYVE_2 NA GRCh37 no yes NA 1008 NA 100 NA NA NA NA TTN-ALK.CUSTOMHYVE NA NA NA Fusion NA NA NA NA NA NA NA NA 0 -TCGA-A1-A0SK-01 NA PJA2 ENST00000361189 7 1 10000000 PJA2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PJA2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PJA2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0CM-01 NA GIPC2 ENST00000370759 3 1 10000000 GIPC2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 GIPC2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA GIPC2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-AR-A1AR-01 NA OSBPL9 ENST00000428468 11 1 10000000 OSBPL9_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 OSBPL9_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA OSBPL9_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-B6-A0WX-01 NA RBM33 ENST00000401878 3 1 10000000 RBM33_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 RBM33_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA RBM33_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A1F0-01 NA CDK5RAP2 ENST00000349780 13 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA CDK5RAP2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-B6-A0I6-01 NA CDK5RAP2 ENST00000349780 12 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA CDK5RAP2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A18V-01 NA SCRIB ENST00000320476 20 1 10000000 SCRIB_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SCRIB_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SCRIB_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A18Q-01 NA PRKAR2B ENST00000265717 1 1 10000000 PRKAR2B_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PRKAR2B_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PRKAR2B_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A18K-01 NA PRKAR1B ENST00000265717 10 1 10000000 PRKAR1B_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PRKAR1B_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PRKAR1B_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A0HL-01 NA PHTF2 ENST00000248550 19 1 10000000 PHTF2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PHTF2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PHTF2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A0E0-01 NA ZNF207 ENST00000321233 3 1 10000000 ZNF207_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 ZNF207_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA ZNF207_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A0RX-01 NA TLK2 ENST00000326270 2 1 10000000 TLK2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 TLK2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA TLK2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A7-A13D-01 NA TNS3 ENST00000311160 18 1 10000000 TNS3_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 TNS3_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA TNS3_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A0E6-01 NA HERPUD1 ENST00000439977 6 1 10000000 HERPUD1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 HERPUD1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA HERPUD1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-AO-A0J4-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A7-A0CE-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A7-A13E-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A7-A0DA-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-D8-A142-01 NA FAM131B ENST00000409222 3 1 10000000 FAM131B_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 FAM131B_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA FAM131B_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-D8-A143-01 NA AGAP3 ENST00000397238 10 1 10000000 AGAP3_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGAP3_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGAP3_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-AQ-A04J-01 NA AGAP3 ENST00000397238 9 1 10000000 AGAP3_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGAP3_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGAP3_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A0HN-01 NA CUL1 ENST00000325222 7 1 10000000 CUL1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 CUL1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA CUL1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0T0-01 NA SND1 ENST00000354725 20 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0YE-01 NA SND1 ENST00000354725 18 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0YJ-01 NA SND1 ENST00000354725 15 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0D0-01 NA SND1 ENST00000354725 15 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04U-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-AO-A0J6-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0YM-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0D2-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-BH-A0B3-01 NA SND1 ENST00000354725 10 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A04Q-01 NA SND1 ENST00000354725 10 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-A2-A0SX-01 NA MKRN1 ENST00000255977 4 1 10000000 MKRN1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 MKRN1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA MKRN1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-AO-A0JL-01 NA MKRN1 ENST00000255977 4 1 10000000 MKRN1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 MKRN1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA MKRN1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 -TCGA-AO-A0JL-01 NA BRAF ENST00000288602 6 1 10000000 BRAF_TTN_CUSTOMHYVE_1 NA TTN ENST00000589042 2 1 111111111 BRAF_TTN_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA BRAF_TTN_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA 0 +Sample_ID Site1_Entrez_Gene_Id Site1_Hugo_Symbol Site1_Ensembl_Transcript_Id Site1_Exon Site1_Chromosome Site1_Position Site1_Description Site2_Entrez_Gene_Id Site2_Hugo_Symbol Site2_Ensembl_Transcript_Id Site2_Exon Site2_Chromosome Site2_Position Site2_Description Site2_Effect_On_Frame NCBI_Build DNA_Support RNA_Support Normal_Read_Count Tumor_Read_Count Normal_Variant_Count Tumor_Variant_Count Normal_Paired_End_Read_Count Tumor_Paired_End_Read_Count Normal_Split_Read_Count Tumor_Split_Read_Count Annotation Breakpoint_Type Center Connection_Type Event_Info Class Length Comments External_Annotation cbp_driver cbp_driver_annotation cbp_driver_tiers cbp_driver_tiers_annotation Sv_Status +TCGA-A2-A04P-01 NA KIAA1549 ENST00000242365 15 7 138536968 KIAA1549-BRAF.K16B10.COSF509_1 NA BRAF ENST00000288602 10 7 140482957 KIAA1549-BRAF.K16B10.COSF509_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA KIAA1549-BRAF.K16B10.COSF509 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF509 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-RET.N7R12_1 NA RET ENST00000340058 12 10 43612031 NCOA4-RET.N7R12_2 NA GRCh37 no yes NA 1001 NA 800 NA NA NA NA NCOA4-RET.N7R1 NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EML4 ENST00000318522 6 2 42492091 EML4-ALK.E6bA20.AB374362_1 NA ALK ENST00000389048 20 2 29446394 EML4-ALK.E6bA20.AB374362_2 NA GRCh37 no yes NA 1002 NA 700 NA NA NA NA EML4-ALK.E6bA20.AB374362 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB374362 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA TMPRSS2 ENST00000332149 1 21 42880007 TMPRSS2-ERG.T1E2.COSF23.1_1 NA ERG ENST00000442448 2 21 39956869 TMPRSS2-ERG.T1E2.COSF23.1_2 NA GRCh37 no yes NA 1003 NA 600 NA NA NA NA TMPRSS2-ERG.T1E2.COSF23.1 NA NA NA Fusion NA NA Gain-of-Function COSMIC:COSF23 NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA EGFR ENST00000275493 1 7 55087058 EGFR-EGFR.E1E8.DelPositive.1_1 NA EGFR ENST00000275493 8 7 55223522 EGFR-EGFR.E1E8.DelPositive.1_2 NA GRCh37 no yes NA 1004 NA 500 NA NA NA NA EGFR-EGFR.E1E8.DelPositive NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA ALK ENST00000389048 11 2 29497964 ALK-PTPN3.A11P3_1 NA PTPN3 ENST00000374541 3 9 112219679 ALK-PTPN3.A11P3_2 NA GRCh37 no yes NA 1005 NA 400 NA NA NA NA ALK-PTPN3.A11P3 NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A1-A0SB-01 NA EML4 ENST00000318522 13 2 42522656 EML4-ALK.E13A20.AB462411_1 NA ALK ENST00000389048 20 2 29446335 EML4-ALK.E13A20.AB462411_2 NA GRCh37 no yes NA 1006 NA 300 NA NA NA NA EML4-ALK.E13A20 NA NA NA Fusion NA NA Gain-of-Function GENBANK:AB462411 NA NA NA NA SOMATIC +TCGA-A1-A0SB-01 NA TMPRSS2 ENST00000455813 1 21 42870045 TMPRSS2-ETV1.T1bE4_1 NA ETV1 ENST00000405358 4 7 14017105 TMPRSS2-ETV1.T1bE4_2 NA GRCh37 no yes NA 1007 NA 200 NA NA NA NA TMPRSS2-ETV1.T1bE4 NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA NCOA4 ENST00000344348 7 10 51582939 NCOA4-TTN.CUSTOMHYVE_1 NA TTN ENST00000589042 2 1 111111111 NCOA4-TTN.CUSTOMHYVE_2 NA GRCh37 no yes NA 1008 NA 100 NA NA NA NA NCOA4-TTN.CUSTOMHYVE NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A2-A04P-01 NA TTN ENST00000589042 28 1 222222222 TTN_ALK.CUSTOMHYVE_1 NA ALK ENST00000389048 20 2 29446394 TTN_ALK.CUSTOMHYVE_2 NA GRCh37 no yes NA 1008 NA 100 NA NA NA NA TTN-ALK.CUSTOMHYVE NA NA NA Fusion NA NA NA NA NA NA NA NA SOMATIC +TCGA-A1-A0SK-01 NA PJA2 ENST00000361189 7 1 10000000 PJA2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PJA2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PJA2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0CM-01 NA GIPC2 ENST00000370759 3 1 10000000 GIPC2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 GIPC2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA GIPC2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-AR-A1AR-01 NA OSBPL9 ENST00000428468 11 1 10000000 OSBPL9_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 OSBPL9_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA OSBPL9_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-B6-A0WX-01 NA RBM33 ENST00000401878 3 1 10000000 RBM33_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 RBM33_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA RBM33_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A1F0-01 NA CDK5RAP2 ENST00000349780 13 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA CDK5RAP2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-B6-A0I6-01 NA CDK5RAP2 ENST00000349780 12 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 CDK5RAP2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA CDK5RAP2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A18V-01 NA SCRIB ENST00000320476 20 1 10000000 SCRIB_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SCRIB_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SCRIB_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A18Q-01 NA PRKAR2B ENST00000265717 1 1 10000000 PRKAR2B_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PRKAR2B_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PRKAR2B_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A18K-01 NA PRKAR1B ENST00000265717 10 1 10000000 PRKAR1B_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PRKAR1B_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PRKAR1B_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A0HL-01 NA PHTF2 ENST00000248550 19 1 10000000 PHTF2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 PHTF2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA PHTF2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A0E0-01 NA ZNF207 ENST00000321233 3 1 10000000 ZNF207_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 ZNF207_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA ZNF207_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A0RX-01 NA TLK2 ENST00000326270 2 1 10000000 TLK2_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 TLK2_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA TLK2_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A7-A13D-01 NA TNS3 ENST00000311160 18 1 10000000 TNS3_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 TNS3_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA TNS3_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A0E6-01 NA HERPUD1 ENST00000439977 6 1 10000000 HERPUD1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 HERPUD1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA HERPUD1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-AO-A0J4-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A7-A0CE-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A7-A13E-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A7-A0DA-01 NA AGK ENST00000355413 2 1 10000000 AGK_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGK_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGK_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-D8-A142-01 NA FAM131B ENST00000409222 3 1 10000000 FAM131B_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 FAM131B_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA FAM131B_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-D8-A143-01 NA AGAP3 ENST00000397238 10 1 10000000 AGAP3_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGAP3_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGAP3_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-AQ-A04J-01 NA AGAP3 ENST00000397238 9 1 10000000 AGAP3_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 AGAP3_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA AGAP3_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A0HN-01 NA CUL1 ENST00000325222 7 1 10000000 CUL1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 CUL1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA CUL1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0T0-01 NA SND1 ENST00000354725 20 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0YE-01 NA SND1 ENST00000354725 18 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0YJ-01 NA SND1 ENST00000354725 15 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0D0-01 NA SND1 ENST00000354725 15 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04U-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-AO-A0J6-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0YM-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0D2-01 NA SND1 ENST00000354725 12 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-BH-A0B3-01 NA SND1 ENST00000354725 10 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A04Q-01 NA SND1 ENST00000354725 10 1 10000000 SND1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 SND1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA SND1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-A2-A0SX-01 NA MKRN1 ENST00000255977 4 1 10000000 MKRN1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 MKRN1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA MKRN1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-AO-A0JL-01 NA MKRN1 ENST00000255977 4 1 10000000 MKRN1_BRAF_CUSTOMHYVE_1 NA BRAF ENST00000288602 11 1 10000000 MKRN1_BRAF_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA MKRN1_BRAF_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC +TCGA-AO-A0JL-01 NA BRAF ENST00000288602 6 1 10000000 BRAF_TTN_CUSTOMHYVE_1 NA TTN ENST00000589042 2 1 111111111 BRAF_TTN_CUSTOMHYVE_2 NA GRCh37 no yes NA 1000 NA 900 NA NA NA NA BRAF_TTN_CUSTOMHYVE NA NA NA Fusion NA NA Gain-of-Function NA NA NA NA NA SOMATIC diff --git a/db-scripts/src/main/resources/cgds.sql b/db-scripts/src/main/resources/cgds.sql index 3da4e353327..f864b9e9b0d 100644 --- a/db-scripts/src/main/resources/cgds.sql +++ b/db-scripts/src/main/resources/cgds.sql @@ -387,7 +387,7 @@ CREATE TABLE `structural_variant` ( `INTERNAL_ID` int(11) NOT NULL auto_increment, `GENETIC_PROFILE_ID` int(11) NOT NULL, `SAMPLE_ID` int(11) NOT NULL, - `SITE1_ENTREZ_GENE_ID` int(11) NOT NULL, + `SITE1_ENTREZ_GENE_ID` int(11), `SITE1_ENSEMBL_TRANSCRIPT_ID` varchar(25), `SITE1_EXON` int(4), `SITE1_CHROMOSOME` varchar(5), @@ -420,7 +420,7 @@ CREATE TABLE `structural_variant` ( `LENGTH` int(11), `COMMENTS` varchar(255), `EXTERNAL_ANNOTATION` varchar(80), - `IS_GERMLINE` tinyint(1) NOT NULL, + `SV_STATUS` varchar(25) NOT NULL DEFAULT 'SOMATIC' COMMENT 'GERMLINE or SOMATIC.', PRIMARY KEY (`INTERNAL_ID`), FOREIGN KEY (`SAMPLE_ID`) REFERENCES `sample` (`INTERNAL_ID`) ON DELETE CASCADE, FOREIGN KEY (`SITE1_ENTREZ_GENE_ID`) REFERENCES `gene` (`ENTREZ_GENE_ID`) ON DELETE CASCADE, @@ -920,4 +920,4 @@ CREATE TABLE `resource_study` ( ); -- THIS MUST BE KEPT IN SYNC WITH db.version PROPERTY IN pom.xml -INSERT INTO info VALUES ('2.12.10', NULL); +INSERT INTO info VALUES ('2.12.11', NULL); diff --git a/db-scripts/src/main/resources/migration.sql b/db-scripts/src/main/resources/migration.sql index 7f4d72d4af0..89352ce6d19 100644 --- a/db-scripts/src/main/resources/migration.sql +++ b/db-scripts/src/main/resources/migration.sql @@ -955,5 +955,6 @@ ALTER TABLE `genetic_profile` ADD COLUMN `PATIENT_LEVEL` boolean DEFAULT 0; UPDATE `info` SET `DB_SCHEMA_VERSION`="2.12.10"; ##version: 2.12.11 -ALTER TABLE `structural_variant` ADD COLUMN `IS_GERMLINE` tinyint(1) DEFAULT 0; +ALTER TABLE `structural_variant` ADD COLUMN `SV_STATUS` varchar(25) NOT NULL DEFAULT 'SOMATIC'; +ALTER TABLE `structural_variant` MODIFY COLUMN `SITE1_ENTREZ_GENE_ID` int(11); UPDATE `info` SET `DB_SCHEMA_VERSION`="2.12.11"; diff --git a/docs/File-Formats.md b/docs/File-Formats.md index 9818da09ad9..74b3e6af87e 100644 --- a/docs/File-Formats.md +++ b/docs/File-Formats.md @@ -20,7 +20,7 @@ * [Gene Set Data](#gene-set-data) * [Study Tags file](#study-tags-file) * [Generic Assay](#generic-assay) - * [Arm Level CNA Data](#arm-level-cna-data) + * [Arm Level CNA Data](#arm-level-cna-data) * [Resource Data](#resource-data) # Introduction diff --git a/model/src/main/java/org/cbioportal/model/StructuralVariant.java b/model/src/main/java/org/cbioportal/model/StructuralVariant.java index ae33d5e77da..824f8bab4bc 100644 --- a/model/src/main/java/org/cbioportal/model/StructuralVariant.java +++ b/model/src/main/java/org/cbioportal/model/StructuralVariant.java @@ -72,7 +72,7 @@ public class StructuralVariant extends UniqueKeyBase implements Serializable { private String driverFilterAnn; private String driverTiersFilter; private String driverTiersFilterAnn; - private Boolean isGermline; + private String svStatus; public String getMolecularProfileId() { return molecularProfileId; @@ -418,11 +418,11 @@ public void setDriverTiersFilterAnn(String driverTiersFilterAnn) { this.driverTiersFilterAnn = driverTiersFilterAnn; } - public Boolean getIsGermline() { - return isGermline; + public String getSvStatus() { + return svStatus; } - public void setIsGermline(Boolean isGermline) { - this.isGermline = isGermline; + public void setSvStatus(String svStatus) { + this.svStatus = svStatus; } } diff --git a/persistence/persistence-mybatis/src/main/resources/org/cbioportal/persistence/mybatis/StructuralVariantMapper.xml b/persistence/persistence-mybatis/src/main/resources/org/cbioportal/persistence/mybatis/StructuralVariantMapper.xml index 1cb55de90ee..ab47a37a840 100644 --- a/persistence/persistence-mybatis/src/main/resources/org/cbioportal/persistence/mybatis/StructuralVariantMapper.xml +++ b/persistence/persistence-mybatis/src/main/resources/org/cbioportal/persistence/mybatis/StructuralVariantMapper.xml @@ -43,7 +43,7 @@ structural_variant.LENGTH AS "${prefix}length", structural_variant.COMMENTS AS "${prefix}comments", structural_variant.EXTERNAL_ANNOTATION AS "${prefix}externalAnnotation", - structural_variant.IS_GERMLINE AS "${prefix}isGermline", + structural_variant.SV_STATUS AS "${prefix}svStatus", alteration_driver_annotation.DRIVER_FILTER AS "${prefix}driverFilter", alteration_driver_annotation.DRIVER_FILTER_ANNOTATION AS "${prefix}driverFilterAnn", alteration_driver_annotation.DRIVER_TIERS_FILTER AS "${prefix}driverTiersFilter", diff --git a/persistence/persistence-mybatis/src/test/java/org/cbioportal/persistence/mybatis/StructuralVariantMyBatisRepositoryTest.java b/persistence/persistence-mybatis/src/test/java/org/cbioportal/persistence/mybatis/StructuralVariantMyBatisRepositoryTest.java index b2ae1bddd5d..4bc4756f80f 100644 --- a/persistence/persistence-mybatis/src/test/java/org/cbioportal/persistence/mybatis/StructuralVariantMyBatisRepositoryTest.java +++ b/persistence/persistence-mybatis/src/test/java/org/cbioportal/persistence/mybatis/StructuralVariantMyBatisRepositoryTest.java @@ -147,7 +147,7 @@ public void fetchStructuralVariantsNoSampleIdentifiers() throws Exception { Assert.assertEquals("Tier 1", structuralVariantFirstResult.getDriverTiersFilter()); Assert.assertEquals("Potentially Actionable", structuralVariantFirstResult.getDriverTiersFilterAnn()); Assert.assertEquals("Potentially Actionable", structuralVariantFirstResult.getDriverTiersFilterAnn()); - Assert.assertEquals(false, structuralVariantFirstResult.getIsGermline()); + Assert.assertEquals("SOMATIC", structuralVariantFirstResult.getSvStatus()); StructuralVariant structuralVariantSecondResult = result.get(1); Assert.assertEquals("study_tcga_pub_sv", structuralVariantSecondResult.getMolecularProfileId()); Assert.assertEquals((String) "TCGA-A1-A0SD-01", structuralVariantSecondResult.getSampleId()); @@ -192,7 +192,7 @@ public void fetchStructuralVariantsNoSampleIdentifiers() throws Exception { Assert.assertEquals(null, structuralVariantSecondResult.getDriverFilterAnn()); Assert.assertEquals(null, structuralVariantSecondResult.getDriverTiersFilter()); Assert.assertEquals(null, structuralVariantSecondResult.getDriverTiersFilterAnn()); - Assert.assertEquals(false, structuralVariantSecondResult.getIsGermline()); + Assert.assertEquals("SOMATIC", structuralVariantSecondResult.getSvStatus()); } diff --git a/persistence/persistence-mybatis/src/test/resources/testSql.sql b/persistence/persistence-mybatis/src/test/resources/testSql.sql index 3bee69b56cd..40f64966564 100644 --- a/persistence/persistence-mybatis/src/test/resources/testSql.sql +++ b/persistence/persistence-mybatis/src/test/resources/testSql.sql @@ -395,20 +395,20 @@ INSERT INTO gene (ENTREZ_GENE_ID,HUGO_GENE_SYMBOL,GENETIC_ENTITY_ID,TYPE) VALUES INSERT INTO gene (ENTREZ_GENE_ID,HUGO_GENE_SYMBOL,GENETIC_ENTITY_ID,TYPE) VALUES(7113,'TMPRSS2',26,'protein-coding'); INSERT INTO gene (ENTREZ_GENE_ID,HUGO_GENE_SYMBOL,GENETIC_ENTITY_ID,TYPE) VALUES(2078,'ERG',27,'protein-coding'); -INSERT INTO structural_variant (INTERNAL_ID,GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(1,7,1,57670,'ENST00000242365',15,'7',138536968,'KIAA1549-BRAF.K16B10.COSF509_1',673,'ENST00000288602',10,'7' ,140482957,'KIAA1549-BRAF.K16B10.COSF509_2','GRCh37','no','yes',100000,90000,'KIAA1549-BRAF.K16B10.COSF509','Fusion','Gain-of-Function','COSMIC:COSF509',0); -INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(7,1,8031,'ENST00000344348',7,'10',51582939,'NCOA4-RET.N7R12_1',5979,'ENST00000340058',12,'10',43612031,'NCOA4-RET.N7R12_2','GRCh37','no','yes',100001,80000,'NCOA4-RET.N7R1','Fusion','Gain-of-Function',NULL,0); -INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(7,1,27436,'ENST00000318522',6,'2',42492091,'EML4-ALK.E6bA20.AB374362_1',238,'ENST00000389048',20,'2',29446394,'EML4-ALK.E6bA20.AB374362_2','GRCh37','no','yes',100002,70000,'EML4-ALK.E6bA20.AB374362','Fusion','Gain-of-Function','GENBANK:AB374362',0); -INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(7,1,7113,'ENST00000332149',1,'21',42880007,'TMPRSS2-ERG.T1E2.COSF23.1_1',2078,'ENST00000442448',2,'21',39956869,'TMPRSS2-ERG.T1E2.COSF23.1_2','GRCh37','no','yes',100003,60000,'TMPRSS2-ERG.T1E2.COSF23.1','Fusion','Gain-of-Function','COSMIC:COSF23',0); -INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(7,2,57670,'ENST00000242365',15,'7',138536968,'KIAA1549-BRAF.K16B10.COSF509_1',673,'ENST00000288602',10,'7' ,140482957,'KIAA1549-BRAF.K16B10.COSF509_2','GRCh37','no','yes',100000,90000,'KIAA1549-BRAF.K16B10.COSF509','Fusion','Gain-of-Function','COSMIC:COSF509',0); -INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(8,15,57670,'ENST00000242365',15,'7',138536968,'KIAA1549-BRAF.K16B10.COSF509_1',673,'ENST00000288602',10,'7' ,140482957,'KIAA1549-BRAF.K16B10.COSF509_2','GRCh37','no','yes',100000,90000,'KIAA1549-BRAF.K16B10.COSF509','Fusion','Gain-of-Function','COSMIC:COSF509',0); -INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,IS_GERMLINE) - VALUES(8,15,8031,'ENST00000344348',7,'10',51582939,'NCOA4-RET.N7R12_1',5979,'ENST00000340058',12,'10',43612031,'NCOA4-RET.N7R12_2','GRCh37','no','yes',100001,80000,'NCOA4-RET.N7R1','Fusion','Gain-of-Function',NULL,0); +INSERT INTO structural_variant (INTERNAL_ID,GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(1,7,1,57670,'ENST00000242365',15,'7',138536968,'KIAA1549-BRAF.K16B10.COSF509_1',673,'ENST00000288602',10,'7' ,140482957,'KIAA1549-BRAF.K16B10.COSF509_2','GRCh37','no','yes',100000,90000,'KIAA1549-BRAF.K16B10.COSF509','Fusion','Gain-of-Function','COSMIC:COSF509','SOMATIC'); +INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(7,1,8031,'ENST00000344348',7,'10',51582939,'NCOA4-RET.N7R12_1',5979,'ENST00000340058',12,'10',43612031,'NCOA4-RET.N7R12_2','GRCh37','no','yes',100001,80000,'NCOA4-RET.N7R1','Fusion','Gain-of-Function',NULL,'SOMATIC'); +INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(7,1,27436,'ENST00000318522',6,'2',42492091,'EML4-ALK.E6bA20.AB374362_1',238,'ENST00000389048',20,'2',29446394,'EML4-ALK.E6bA20.AB374362_2','GRCh37','no','yes',100002,70000,'EML4-ALK.E6bA20.AB374362','Fusion','Gain-of-Function','GENBANK:AB374362','SOMATIC'); +INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(7,1,7113,'ENST00000332149',1,'21',42880007,'TMPRSS2-ERG.T1E2.COSF23.1_1',2078,'ENST00000442448',2,'21',39956869,'TMPRSS2-ERG.T1E2.COSF23.1_2','GRCh37','no','yes',100003,60000,'TMPRSS2-ERG.T1E2.COSF23.1','Fusion','Gain-of-Function','COSMIC:COSF23','SOMATIC'); +INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(7,2,57670,'ENST00000242365',15,'7',138536968,'KIAA1549-BRAF.K16B10.COSF509_1',673,'ENST00000288602',10,'7' ,140482957,'KIAA1549-BRAF.K16B10.COSF509_2','GRCh37','no','yes',100000,90000,'KIAA1549-BRAF.K16B10.COSF509','Fusion','Gain-of-Function','COSMIC:COSF509','SOMATIC'); +INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(8,15,57670,'ENST00000242365',15,'7',138536968,'KIAA1549-BRAF.K16B10.COSF509_1',673,'ENST00000288602',10,'7' ,140482957,'KIAA1549-BRAF.K16B10.COSF509_2','GRCh37','no','yes',100000,90000,'KIAA1549-BRAF.K16B10.COSF509','Fusion','Gain-of-Function','COSMIC:COSF509','SOMATIC'); +INSERT INTO structural_variant (GENETIC_PROFILE_ID,SAMPLE_ID,SITE1_ENTREZ_GENE_ID,SITE1_ENSEMBL_TRANSCRIPT_ID,SITE1_EXON,SITE1_CHROMOSOME,SITE1_POSITION,SITE1_DESCRIPTION,SITE2_ENTREZ_GENE_ID,SITE2_ENSEMBL_TRANSCRIPT_ID,SITE2_EXON,SITE2_CHROMOSOME,SITE2_POSITION,SITE2_DESCRIPTION,NCBI_BUILD,DNA_SUPPORT,RNA_SUPPORT,TUMOR_READ_COUNT,TUMOR_VARIANT_COUNT,ANNOTATION,EVENT_INFO,COMMENTS,EXTERNAL_ANNOTATION,SV_STATUS) + VALUES(8,15,8031,'ENST00000344348',7,'10',51582939,'NCOA4-RET.N7R12_1',5979,'ENST00000340058',12,'10',43612031,'NCOA4-RET.N7R12_2','GRCh37','no','yes',100001,80000,'NCOA4-RET.N7R1','Fusion','Gain-of-Function',NULL,'SOMATIC'); INSERT INTO alteration_driver_annotation (ALTERATION_EVENT_ID,GENETIC_PROFILE_ID,SAMPLE_ID, DRIVER_FILTER, DRIVER_FILTER_ANNOTATION, DRIVER_TIERS_FILTER, DRIVER_TIERS_FILTER_ANNOTATION) VALUES (1,7,1, 'Putative_Passenger', 'Pathogenic', 'Tier 1', 'Potentially Actionable'); diff --git a/web/src/test/java/org/cbioportal/web/StructuralVariantControllerTest.java b/web/src/test/java/org/cbioportal/web/StructuralVariantControllerTest.java index ff0d3c29a82..368399e5f16 100644 --- a/web/src/test/java/org/cbioportal/web/StructuralVariantControllerTest.java +++ b/web/src/test/java/org/cbioportal/web/StructuralVariantControllerTest.java @@ -104,7 +104,7 @@ public class StructuralVariantControllerTest { private static final String TEST_DRIVER_FILTER_ANN_1 = "test_driver_filter_ann_1"; private static final String TEST_DRIVER_TIERS_FILTER_1 = "test_driver_tiers_filter_1"; private static final String TEST_DRIVER_TIERS_FILTER_ANN_1 = "test_driver_tiers_filter_ann_1"; - private static final Boolean TEST_IS_GERMLINE = false; + private static final String TEST_SV_STATUS = "SOMATIC"; @Autowired private WebApplicationContext wac; @@ -189,7 +189,7 @@ public void fetchStructuralVariantsMolecularProfileId() throws Exception { .andExpect(MockMvcResultMatchers.jsonPath("$[0].driverFilterAnn").value(TEST_DRIVER_FILTER_ANN_1)) .andExpect(MockMvcResultMatchers.jsonPath("$[0].driverTiersFilter").value(TEST_DRIVER_TIERS_FILTER_1)) .andExpect(MockMvcResultMatchers.jsonPath("$[0].driverTiersFilterAnn").value(TEST_DRIVER_TIERS_FILTER_ANN_1)) - .andExpect(MockMvcResultMatchers.jsonPath("$[0].isGermline").value(TEST_IS_GERMLINE)); + .andExpect(MockMvcResultMatchers.jsonPath("$[0].svStatus").value(TEST_SV_STATUS)); } @Test @@ -254,7 +254,7 @@ public void fetchStructuralVariantsSampleMolecularIdentifier() throws Exception .andExpect(MockMvcResultMatchers.jsonPath("$[0].driverFilterAnn").value(TEST_DRIVER_FILTER_ANN_1)) .andExpect(MockMvcResultMatchers.jsonPath("$[0].driverTiersFilter").value(TEST_DRIVER_TIERS_FILTER_1)) .andExpect(MockMvcResultMatchers.jsonPath("$[0].driverTiersFilterAnn").value(TEST_DRIVER_TIERS_FILTER_ANN_1)) - .andExpect(MockMvcResultMatchers.jsonPath("$[0].isGermline").value(TEST_IS_GERMLINE)); + .andExpect(MockMvcResultMatchers.jsonPath("$[0].svStatus").value(TEST_SV_STATUS)); } @Test @@ -325,7 +325,7 @@ private List createExampleStructuralVariant() { structuralVariant1.setDriverFilterAnn(TEST_DRIVER_FILTER_ANN_1); structuralVariant1.setDriverTiersFilter(TEST_DRIVER_TIERS_FILTER_1); structuralVariant1.setDriverTiersFilterAnn(TEST_DRIVER_TIERS_FILTER_ANN_1); - structuralVariant1.setIsGermline(false); + structuralVariant1.setSvStatus(TEST_SV_STATUS); structuralVariantList.add(structuralVariant1); return structuralVariantList; }