Skip to content

Commit 47bc093

Browse files
rneherrneher
authored
Merge pull request #450 from nextstrain/bdbv
bdbv: first stab at bdbv dataset
2 parents 244b5bf + 3c037ac commit 47bc093

18 files changed

Lines changed: 20302 additions & 10465 deletions

File tree

‎data/nextstrain/collection.json‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -100,6 +100,7 @@
100100
"nextstrain/flu/h2n2/ha",
101101
"nextstrain/flu/h2n2/na",
102102
"nextstrain/flu/h2n2/mp",
103-
"nextstrain/flu/h2n2/ns"
103+
"nextstrain/flu/h2n2/ns",
104+
"nextstrain/orthoebolavirus/bdbv"
104105
]
105106
}

‎data/nextstrain/orthoebolavirus/bdbv/CHANGELOG.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
## Unreleased
2+

‎data/nextstrain/orthoebolavirus/bdbv/README.md‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
# Nextclade dataset for Bundibugyo virus (Orthoebolavirus bundibugyoense)
2+
3+
| Key | Value |
4+
| ---------------------- | ------------------------------------------------------------------------------- |
5+
| authors | [Richard Neher](https://neherlab.org) |
6+
| data source | Genbank |
7+
| nextclade dataset path | nextstrain/orthoebolavirus/bdbv |
8+
| annotation | [NC_014373.1](https://www.ncbi.nlm.nih.gov/nuccore/NC_014373.1) |
9+
10+
Bundibugyo virus [(Orthoebolavirus bundibugyoense)](https://ictv.global/report/chapter/filoviridae/filoviridae/orthoebolavirus).
11+

‎data/nextstrain/orthoebolavirus/bdbv/examples.fasta‎

Lines changed: 2894 additions & 0 deletions
Large diffs are not rendered by default.

‎data/nextstrain/orthoebolavirus/bdbv/genome_annotation.gff3‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
##gff-version 3
2+
#!gff-spec-version 1.21
3+
#!processor NCBI annotwriter
4+
##sequence-region NC_014373.1 1 18940
5+
##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=565995
6+
NC_014373.1 RefSeq region 1 18940 . + . ID=NC_014373.1:1..18940;Dbxref=taxon:565995;collection-date=Nov-2007;country=Uganda;gbkey=Src;genome=genomic;isolate=Bundibugyo virus/H.sapiens-tc/UGA/2007/Butalya-811250;isolation-source=blood;mol_type=viral cRNA;nat-host=Homo sapiens;old-name=Bundibugyo ebolavirus
7+
NC_014373.1 RefSeq CDS 458 2677 . + 0 Name=NP;gene=NP;gbkey=CDS;locus_tag=BDBVp1;product=nucleoprotein;protein_id=YP_003815432.1;ID=cds-YP_003815432.1;Note=encapsidation of genomic RNA;Dbxref=GenBank:YP_003815432.1,GeneID:9487269
8+
NC_014373.1 RefSeq CDS 3108 4133 . + 0 Name=VP35;gbkey=CDS;gene=VP35;locus_tag=BDBVp2;protein_id=YP_003815433.1;ID=cds-YP_003815433.1;product=polymerase complex protein;Note=putative type-1 IFN antagonist;Dbxref=GenBank:YP_003815433.1,GeneID:9487263
9+
NC_014373.1 RefSeq CDS 4461 5441 . + 0 Name=VP40;gbkey=CDS;gene=VP40;locus_tag=BDBVp3;product=matrix protein;protein_id=YP_003815434.1;ID=cds-YP_003815434.1;Dbxref=GenBank:YP_003815434.1,GeneID:9487264
10+
NC_014373.1 RefSeq CDS 6021 6905 . + 0 Name=GP;gene=GP;gbkey=CDS;locus_tag=BDBVp4;exception=RNA editing;protein_id=YP_003815435.1;ID=cds-YP_003815435.1;product=spike glycoprotein;Dbxref=GenBank:YP_003815435.1,GeneID:9487265;Note=GP1%2C2%3B structural glycoprotein%3B cleaved by furin into subunits GP1 and GP2 to yield a heterodimer linked by a disulfide bond
11+
NC_014373.1 RefSeq CDS 6905 8050 . + 0 Name=GP;gene=GP;gbkey=CDS;locus_tag=BDBVp4;exception=RNA editing;protein_id=YP_003815435.1;ID=cds-YP_003815435.1;product=spike glycoprotein;Dbxref=GenBank:YP_003815435.1,GeneID:9487265;Note=GP1%2C2%3B structural glycoprotein%3B cleaved by furin into subunits GP1 and GP2 to yield a heterodimer linked by a disulfide bond
12+
NC_014373.1 RefSeq CDS 6021 7142 . + 0 Name=GP_003;gene=GP;gbkey=CDS;locus_tag=BDBVp4;protein_id=YP_003815436.1;ID=cds-YP_003815436.1;product=small secreted glycoprotein;Dbxref=GenBank:YP_003815436.1,GeneID:9487265;Note=solulbe secreted glycoprotein%3B small non-structural secreted glycoprotein%3B sGP
13+
NC_014373.1 RefSeq CDS 8496 9365 . + 0 Name=VP30;gbkey=CDS;gene=VP30;locus_tag=BDBVp5;protein_id=YP_003815438.1;ID=cds-YP_003815438.1;product=minor nucleoprotein;Note=polymerase complex protein;Dbxref=GenBank:YP_003815438.1,GeneID:9487266
14+
NC_014373.1 RefSeq CDS 10335 11090 . + 0 Name=VP24;gbkey=CDS;gene=VP24;locus_tag=BDBVp6;protein_id=YP_003815439.1;ID=cds-YP_003815439.1;product=membrane-associated protein;Dbxref=GenBank:YP_003815439.1,GeneID:9487267
15+
NC_014373.1 RefSeq CDS 11567 18199 . + 0 Name=L;gene=L;gbkey=CDS;locus_tag=BDBVp7;protein_id=YP_003815440.1;ID=cds-YP_003815440.1;product=RNA-dependent RNA polymerase;Dbxref=GenBank:YP_003815440.1,GeneID:9487268;Note=synthesis of viral RNAs%3B transcriptional RNA editing

‎data/nextstrain/orthoebolavirus/bdbv/pathogen.json‎

Lines changed: 78 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,78 @@
1+
{
2+
"$schema": "https://raw.githubusercontent.com/nextstrain/nextclade/refs/heads/release/packages/nextclade-schemas/input-pathogen-json.schema.json",
3+
"alignmentParams": {
4+
"excessBandwidth": 100,
5+
"terminalBandwidth": 300,
6+
"allowedMismatches": 10,
7+
"windowSize": 40,
8+
"minSeedCover": 0.03,
9+
"gapAlignmentSide": "left"
10+
},
11+
"attributes": {
12+
"name": "Bundibugyo ebolavirus",
13+
"reference accession": "NC_014373.1",
14+
"reference name": "UGA/2007/Butalya-811250",
15+
"experimental": true
16+
},
17+
"compatibility": {
18+
"cli": "3.0.0-alpha.0",
19+
"web": "3.0.0-alpha.0"
20+
},
21+
"files": {
22+
"treeJson": "tree.json",
23+
"changelog": "CHANGELOG.md",
24+
"examples": "examples.fasta",
25+
"genomeAnnotation": "genome_annotation.gff3",
26+
"pathogenJson": "pathogen.json",
27+
"readme": "README.md",
28+
"reference": "reference.fasta"
29+
},
30+
"defaultCds": "GP",
31+
"qc": {
32+
"frameShifts": {
33+
"enabled": true,
34+
"ignoredFrameShifts": [],
35+
"scoreWeight": 20
36+
},
37+
"missingData": {
38+
"enabled": true,
39+
"missingDataThreshold": 3000,
40+
"scoreBias": 500
41+
},
42+
"mixedSites": {
43+
"enabled": true,
44+
"mixedSitesThreshold": 40
45+
},
46+
"privateMutations": {
47+
"cutoff": 300,
48+
"enabled": true,
49+
"typical": 50,
50+
"weightLabeledSubstitutions": 6,
51+
"weightReversionSubstitutions": 6,
52+
"weightUnlabeledSubstitutions": 1
53+
},
54+
"snpClusters": {
55+
"clusterCutOff": 10,
56+
"enabled": false,
57+
"scoreWeight": 10,
58+
"windowSize": 100
59+
},
60+
"stopCodons": {
61+
"enabled": true,
62+
"ignoredStopCodons": [],
63+
"scoreWeight": 20
64+
}
65+
},
66+
"schemaVersion": "3.0.0",
67+
"shortcuts": [
68+
"nextstrain/ebola/bebov"
69+
],
70+
"version": {
71+
"updatedAt": "2026-04-14T11:55:23Z",
72+
"tag": "2026-04-14--11-55-23Z",
73+
"compatibility": {
74+
"cli": "3.0.0-alpha.0",
75+
"web": "3.0.0-alpha.0"
76+
}
77+
}
78+
}

0 commit comments

Comments
 (0)