fixup: dataset

Applies fixes to the dataset so far 1. Gff coordinate fixup 2. Adding the example sequences 3. Set defaultCds to the E gene
nextstrain · May 30, 2024 · baf0263 · baf0263
1 parent 3bd63f6
commit baf0263
Show file tree

Hide file tree

Showing 15 changed files with 27,928 additions and 13 deletions.
diff --git a/nextclade/datasets/all/genome_annotation.gff3 b/nextclade/datasets/all/genome_annotation.gff3
@@ -2,7 +2,7 @@
 ##sequence-region NC_002640.1 1 10649
 NC_002640.1	feature	gene	102	440	.	+	.	codon_start=1;gene=C;gene_name=C;
 NC_002640.1	feature	gene	441	713	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_002640.1	feature	gene	714	938	.	+	.	codon_start=1;gene=M;gene_name=M;
+NC_002640.1	feature	gene	441	938	.	+	.	codon_start=1;gene=M;gene_name=M;
 NC_002640.1	feature	gene	939	2423	.	+	.	codon_start=1;gene=E;gene_name=E;
 NC_002640.1	feature	gene	2424	3479	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
 NC_002640.1	feature	gene	3480	4133	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;

diff --git a/nextclade/datasets/all/pathogen.json b/nextclade/datasets/all/pathogen.json
@@ -62,5 +62,6 @@
   "schemaVersion": "3.0.0",
   "version": {
     "tag": "unreleased"
-  }
+  },
+  "defaultCds": "E"
 }
diff --git a/nextclade/datasets/all/sequences.fasta b/nextclade/datasets/all/sequences.fasta
diff --git a/nextclade/datasets/denv1/genome_annotation.gff3 b/nextclade/datasets/denv1/genome_annotation.gff3
@@ -1,8 +1,8 @@
 ##gff-version 3
 ##sequence-region NC_001477.1 1 10735
-NC_001477.1	feature	gene	95	394	.	+	.	codon_start=1;gene=C;gene_name=C;
+NC_001477.1	feature	gene	95	436	.	+	.	codon_start=1;gene=C;gene_name=C;
 NC_001477.1	feature	gene	437	709	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_001477.1	feature	gene	710	934	.	+	.	codon_start=1;gene=M;gene_name=M;
+NC_001477.1	feature	gene	437	934	.	+	.	codon_start=1;gene=M;gene_name=M;
 NC_001477.1	feature	gene	935	2419	.	+	.	codon_start=1;gene=E;gene_name=E;
 NC_001477.1	feature	gene	2420	3475	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
 NC_001477.1	feature	gene	3476	4129	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;

diff --git a/nextclade/datasets/denv1/pathogen.json b/nextclade/datasets/denv1/pathogen.json
@@ -61,5 +61,6 @@
   "schemaVersion": "3.0.0",
   "version": {
     "tag": "unreleased"
-  }
+  },
+  "defaultCds": "E"
 }
diff --git a/nextclade/datasets/denv1/sequences.fasta b/nextclade/datasets/denv1/sequences.fasta
diff --git a/nextclade/datasets/denv2/genome_annotation.gff3 b/nextclade/datasets/denv2/genome_annotation.gff3
@@ -1,8 +1,8 @@
 ##gff-version 3
 ##sequence-region NC_001474.2 1 10723
-NC_001474.2	feature	gene	97	396	.	+	.	codon_start=1;gene=C;gene_name=C;
+NC_001474.2	feature	gene	97	438	.	+	.	codon_start=1;gene=C;gene_name=C;
 NC_001474.2	feature	gene	439	711	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_001474.2	feature	gene	712	936	.	+	.	codon_start=1;gene=M;gene_name=M;
+NC_001474.2	feature	gene	439	936	.	+	.	codon_start=1;gene=M;gene_name=M;
 NC_001474.2	feature	gene	937	2421	.	+	.	codon_start=1;gene=E;gene_name=E;
 NC_001474.2	feature	gene	2422	3477	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
 NC_001474.2	feature	gene	3478	4131	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;

diff --git a/nextclade/datasets/denv2/pathogen.json b/nextclade/datasets/denv2/pathogen.json
@@ -61,5 +61,6 @@
   "schemaVersion": "3.0.0",
   "version": {
     "tag": "unreleased"
-  }
+  },
+  "defaultCds": "E"
 }
diff --git a/nextclade/datasets/denv2/sequences.fasta b/nextclade/datasets/denv2/sequences.fasta
diff --git a/nextclade/datasets/denv3/genome_annotation.gff3 b/nextclade/datasets/denv3/genome_annotation.gff3
@@ -1,8 +1,8 @@
 ##gff-version 3
 ##sequence-region NC_001475.2 1 10707
-NC_001475.2	feature	gene	95	394	.	+	.	codon_start=1;gene=C;gene_name=C;
+NC_001475.2	feature	gene	95	436	.	+	.	codon_start=1;gene=C;gene_name=C;
 NC_001475.2	feature	gene	437	709	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_001475.2	feature	gene	710	934	.	+	.	codon_start=1;gene=M;gene_name=M;
+NC_001475.2	feature	gene	437	934	.	+	.	codon_start=1;gene=M;gene_name=M;
 NC_001475.2	feature	gene	935	2419	.	+	.	codon_start=1;gene=E;gene_name=E;
 NC_001475.2	feature	gene	2414	3469	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
 NC_001475.2	feature	gene	3470	4123	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;

diff --git a/nextclade/datasets/denv3/pathogen.json b/nextclade/datasets/denv3/pathogen.json
@@ -61,5 +61,6 @@
   "schemaVersion": "3.0.0",
   "version": {
     "tag": "unreleased"
-  }
+  },
+  "defaultCds": "E"
 }
diff --git a/nextclade/datasets/denv3/sequences.fasta b/nextclade/datasets/denv3/sequences.fasta
diff --git a/nextclade/datasets/denv4/genome_annotation.gff3 b/nextclade/datasets/denv4/genome_annotation.gff3
@@ -2,7 +2,7 @@
 ##sequence-region NC_002640.1 1 10649
 NC_002640.1	feature	gene	102	440	.	+	.	codon_start=1;gene=C;gene_name=C;
 NC_002640.1	feature	gene	441	713	.	+	.	codon_start=1;gene=pr;gene_name=pr;
-NC_002640.1	feature	gene	714	938	.	+	.	codon_start=1;gene=M;gene_name=M;
+NC_002640.1	feature	gene	441	938	.	+	.	codon_start=1;gene=M;gene_name=M;
 NC_002640.1	feature	gene	939	2423	.	+	.	codon_start=1;gene=E;gene_name=E;
 NC_002640.1	feature	gene	2424	3479	.	+	.	codon_start=1;gene=NS1;gene_name=NS1;
 NC_002640.1	feature	gene	3480	4133	.	+	.	codon_start=1;gene=NS2A;gene_name=NS2A;

diff --git a/nextclade/datasets/denv4/pathogen.json b/nextclade/datasets/denv4/pathogen.json
@@ -61,5 +61,6 @@
   "schemaVersion": "3.0.0",
   "version": {
     "tag": "unreleased"
-  }
+  },
+  "defaultCds": "E"
 }
diff --git a/nextclade/datasets/denv4/sequences.fasta b/nextclade/datasets/denv4/sequences.fasta