diff test-data/gencode_ens_hav.gtf @ 9:7d67331368f3

fixing the new version upload manually
author vipints <vipin@cbio.mskcc.org>
date Thu, 23 Apr 2015 17:57:49 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gencode_ens_hav.gtf	Thu Apr 23 17:57:49 2015 -0400
@@ -0,0 +1,50 @@
+1	HAVANA	gene	69091	70008	.	+	.	gene_id "ENSG00000186092.4"; transcript_id "ENSG00000186092.4"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5"; level 2; havana_gene "OTTHUMG00000001094.1";
+1	HAVANA	transcript	69091	70008	.	+	.	gene_id "ENSG00000186092.4"; transcript_id "ENST00000335137.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS30547.1"; havana_gene "OTTHUMG00000001094.1"; havana_transcript "OTTHUMT00000003223.1";
+1	HAVANA	exon	69091	70008	.	+	.	gene_id "ENSG00000186092.4"; transcript_id "ENST00000335137.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5-001"; exon_number 1;  exon_id "ENSE00002319515.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS30547.1"; havana_gene "OTTHUMG00000001094.1"; havana_transcript "OTTHUMT00000003223.1";
+1	HAVANA	CDS	69091	70005	.	+	0	gene_id "ENSG00000186092.4"; transcript_id "ENST00000335137.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5-001"; exon_number 1;  exon_id "ENSE00002319515.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS30547.1"; havana_gene "OTTHUMG00000001094.1"; havana_transcript "OTTHUMT00000003223.1";
+1	HAVANA	start_codon	69091	69093	.	+	0	gene_id "ENSG00000186092.4"; transcript_id "ENST00000335137.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5-001"; exon_number 1;  exon_id "ENSE00002319515.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS30547.1"; havana_gene "OTTHUMG00000001094.1"; havana_transcript "OTTHUMT00000003223.1";
+1	HAVANA	stop_codon	70006	70008	.	+	0	gene_id "ENSG00000186092.4"; transcript_id "ENST00000335137.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5-001"; exon_number 1;  exon_id "ENSE00002319515.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS30547.1"; havana_gene "OTTHUMG00000001094.1"; havana_transcript "OTTHUMT00000003223.1";
+1	HAVANA	UTR	70006	70008	.	+	.	gene_id "ENSG00000186092.4"; transcript_id "ENST00000335137.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F5-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS30547.1"; havana_gene "OTTHUMG00000001094.1"; havana_transcript "OTTHUMT00000003223.1";
+1	ENSEMBL	gene	134901	139379	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENSG00000237683.5"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1"; level 3;
+1	ENSEMBL	transcript	134901	139379	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	137621	139379	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; exon_number 1;  exon_id "ENSE00002221580.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	138533	139309	.	-	0	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; exon_number 1;  exon_id "ENSE00002221580.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	stop_codon	138530	138532	.	-	0	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; exon_number 1;  exon_id "ENSE00002221580.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	134901	135802	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; exon_number 2;  exon_id "ENSE00002314092.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	UTR	137621	138532	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	UTR	139310	139379	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	UTR	134901	135802	.	-	.	gene_id "ENSG00000237683.5"; transcript_id "ENST00000423372.3"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "AL627309.1"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "AL627309.1-201"; level 3; tag "basic"; tag "appris_principal";
+1	HAVANA	gene	367640	368634	.	+	.	gene_id "ENSG00000235249.1"; transcript_id "ENSG00000235249.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29"; level 2; havana_gene "OTTHUMG00000002860.1";
+1	HAVANA	transcript	367640	368634	.	+	.	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	exon	367640	368634	.	+	.	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; exon_number 1;  exon_id "ENSE00002316283.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	CDS	367659	368594	.	+	0	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; exon_number 1;  exon_id "ENSE00002316283.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	start_codon	367659	367661	.	+	0	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; exon_number 1;  exon_id "ENSE00002316283.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	stop_codon	368595	368597	.	+	0	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; exon_number 1;  exon_id "ENSE00002316283.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	UTR	367640	367658	.	+	.	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	UTR	368595	368634	.	+	.	gene_id "ENSG00000235249.1"; transcript_id "ENST00000426406.1"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F29"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F29-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41220.1"; havana_gene "OTTHUMG00000002860.1"; havana_transcript "OTTHUMT00000007999.1";
+1	HAVANA	gene	621059	622053	.	-	.	gene_id "ENSG00000185097.2"; transcript_id "ENSG00000185097.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16"; level 2; havana_gene "OTTHUMG00000002581.1";
+1	HAVANA	transcript	621059	622053	.	-	.	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	HAVANA	exon	621059	622053	.	-	.	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; exon_number 1;  exon_id "ENSE00002324228.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	HAVANA	CDS	621099	622034	.	-	0	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; exon_number 1;  exon_id "ENSE00002324228.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	HAVANA	start_codon	622032	622034	.	-	0	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; exon_number 1;  exon_id "ENSE00002324228.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	HAVANA	stop_codon	621096	621098	.	-	0	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; exon_number 1;  exon_id "ENSE00002324228.1";  level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	HAVANA	UTR	621059	621098	.	-	.	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	HAVANA	UTR	622035	622053	.	-	.	gene_id "ENSG00000185097.2"; transcript_id "ENST00000332831.2"; gene_type "protein_coding"; gene_status "KNOWN"; gene_name "OR4F16"; transcript_type "protein_coding"; transcript_status "KNOWN"; transcript_name "OR4F16-001"; level 2; tag "basic"; tag "appris_principal"; tag "CCDS"; ccdsid "CCDS41221.1"; havana_gene "OTTHUMG00000002581.1"; havana_transcript "OTTHUMT00000007334.1";
+1	ENSEMBL	gene	738532	739137	.	-	.	gene_id "ENSG00000269831.1"; transcript_id "ENSG00000269831.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1"; level 3;
+1	ENSEMBL	transcript	738532	739137	.	-	.	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	739121	739137	.	-	.	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; exon_number 1;  exon_id "ENSE00003063549.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	739121	739137	.	-	0	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; exon_number 1;  exon_id "ENSE00003063549.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	738788	738812	.	-	.	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; exon_number 2;  exon_id "ENSE00003084653.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	738788	738812	.	-	1	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; exon_number 2;  exon_id "ENSE00003084653.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	738532	738618	.	-	.	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; exon_number 3;  exon_id "ENSE00003138540.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	738532	738618	.	-	0	gene_id "ENSG00000269831.1"; transcript_id "ENST00000599533.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL669831.1"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL669831.1-201"; exon_number 3;  exon_id "ENSE00003138540.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	gene	818043	819983	.	+	.	gene_id "ENSG00000269308.1"; transcript_id "ENSG00000269308.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2"; level 3;
+1	ENSEMBL	transcript	818043	819983	.	+	.	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	818043	818058	.	+	.	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 1;  exon_id "ENSE00003079649.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	818043	818058	.	+	0	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 1;  exon_id "ENSE00003079649.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	819496	819513	.	+	.	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 2;  exon_id "ENSE00003048391.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	819496	819513	.	+	2	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 2;  exon_id "ENSE00003048391.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	exon	819961	819983	.	+	.	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 3;  exon_id "ENSE00003055565.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	CDS	819961	819980	.	+	2	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 3;  exon_id "ENSE00003055565.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	stop_codon	819981	819983	.	+	0	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; exon_number 3;  exon_id "ENSE00003055565.1";  level 3; tag "basic"; tag "appris_principal";
+1	ENSEMBL	UTR	819981	819983	.	+	.	gene_id "ENSG00000269308.1"; transcript_id "ENST00000594233.1"; gene_type "protein_coding"; gene_status "NOVEL"; gene_name "AL645608.2"; transcript_type "protein_coding"; transcript_status "NOVEL"; transcript_name "AL645608.2-201"; level 3; tag "basic"; tag "appris_principal";