add germline to structural variant table and model

core/src/main/java/org/mskcc/cbio/portal/dao/DaoStructuralVariant.java

@@ -80,7 +80,8 @@ public static void addStructuralVariantToBulkLoader(StructuralVariant structural
                                             "CLASS",
                                             "LENGTH",
                                             "COMMENTS",
-                                            "EXTERNAL_ANNOTATION"
+                                            "EXTERNAL_ANNOTATION",
+                                            "IS_GERMLINE",
                                             };
         bl.setFieldNames(fieldNames);
 
@@ -121,7 +122,9 @@ public static void addStructuralVariantToBulkLoader(StructuralVariant structural
            structuralVariant.getVariantClass(),
            Integer.toString(structuralVariant.getLength()),
            structuralVariant.getComments(),
-           structuralVariant.getExternalAnnotation());
+           structuralVariant.getExternalAnnotation(),
+           Integer.toString(structuralVariant.getIsGermline()?1:0));
+//TODO: fix this ... the value must be converted to an integer
 
         if ((structuralVariant.getDriverFilter() != null
             && !structuralVariant.getDriverFilter().isEmpty()
@@ -237,6 +240,7 @@ 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"));
         return structuralVariant;
     }
 }

core/src/main/java/org/mskcc/cbio/portal/model/StructuralVariant.java

@@ -69,14 +69,14 @@ public class StructuralVariant {
     private String driverFilterAnn;
     private String driverTiersFilter;
     private String driverTiersFilterAnn;
+    private Boolean isGermline;
 
     public long getInternalId() {
         return internalId;
     }
     public void setInternalId(long internalId) {
         this.internalId = internalId;
     }
-
     public int getGeneticProfileId() {
         return geneticProfileId;
     }
@@ -335,4 +335,10 @@ public String getDriverTiersFilterAnn() {
     public void setDriverTiersFilterAnn(String driverTiersFilterAnn) {
         this.driverTiersFilterAnn = driverTiersFilterAnn;
     }
+    public Boolean getIsGermline() {
+        return isGermline;
+    }
+    public void setIsGermline(Boolean isGermline) {
+        this.isGermline = isGermline;
+    }
 }

core/src/main/java/org/mskcc/cbio/portal/util/StructuralVariantUtil.java

@@ -83,6 +83,7 @@ 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 StructuralVariantUtil(){}
 
@@ -139,6 +140,7 @@ 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);
         return structuralVariant;
     }
 

core/src/main/scripts/importer/validateData.py

@@ -3105,6 +3105,8 @@ def checkNCBIbuild(ncbi_build):
                                           extra={'line_number': self.line_number,
                                                  'cause': '%s and %s' % (self.ncbi_build, ncbi_build)})
 
+# TODO: discuss what that actual requirement are for different categories of structural variants. We now allow records which are germline cnv events referencing only a single gene for instance. Is that a third category or not?
+
         def checkFusionValues(self, data):
             """Check if all values are present for a fusion event"""
 
@@ -3163,11 +3165,6 @@ def checkExonPresence(self, exon, column_name):
         site1_entrez_gene_id = checkPresenceValue('Site1_Entrez_Gene_Id', self, data)
         self.checkGeneIdentification(site1_hugo_symbol, site1_entrez_gene_id)
 
-        # Parse Hugo Symbol and Entrez Gene Id and check them for Site 2
-        site2_hugo_symbol = checkPresenceValue('Site2_Hugo_Symbol', self, data)
-        site2_entrez_gene_id = checkPresenceValue('Site2_Entrez_Gene_Id', self, data)
-        self.checkGeneIdentification(site2_hugo_symbol, site2_entrez_gene_id)
-
         # Validate fusion events if Event_Info is 'Fusion'
         if data[self.cols.index('Event_Info')] == 'Fusion':
             checkFusionValues(self, data)

core/src/test/java/org/mskcc/cbio/portal/util/TestStructuralVariantUtil.java

@@ -10,6 +10,7 @@
 public class TestStructuralVariantUtil {
     private StructuralVariantUtil structuralVariantUtil = new StructuralVariantUtil();
 
+//TODO: the set of required fields has shrunk to just [Site1EntrezGeneId or <<Site1HugoSymbol>>] ... but also, sampleId is needed??
     @Test
     public void testValidStructuralVariantRecordWithCompleteGeneTranscriptInfo() {
         // confirm that record meets minimum requirements for import

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
-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
-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
+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

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
-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
-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
-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
-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
-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
-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
-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
+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

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
-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
-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
-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
-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
-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
-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
-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
+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