Merge pull request #454 from nextstrain/bdbv-update

bdbv: update tree and qc params

Author: rneher

data/nextstrain/orthoebolavirus/bdbv/CHANGELOG.md

@@ -1,3 +1,9 @@
+## Unreleased
+
+- adjust QC param settings to reudce private mutation threshold (outbreak genomes should be very similar)
+- add SNP cluster QC rule to trigger on stretches of high private mutation density
+- update tree
+
 ## 2026-05-18T20:09:34Z
 
 - Add outbreak annotation

data/nextstrain/orthoebolavirus/bdbv/pathogen.json

@@ -33,7 +33,7 @@
     "frameShifts": {
       "enabled": true,
       "ignoredFrameShifts": [],
-      "scoreWeight": 20
+      "scoreWeight": 50
     },
     "missingData": {
       "enabled": true,
@@ -42,21 +42,21 @@
     },
     "mixedSites": {
       "enabled": true,
-      "mixedSitesThreshold": 40
+      "mixedSitesThreshold": 20
     },
     "privateMutations": {
-      "cutoff": 300,
+      "cutoff": 10,
       "enabled": true,
-      "typical": 50,
-      "weightLabeledSubstitutions": 6,
-      "weightReversionSubstitutions": 6,
+      "typical": 3,
+      "weightLabeledSubstitutions": 3,
+      "weightReversionSubstitutions": 3,
       "weightUnlabeledSubstitutions": 1
     },
     "snpClusters": {
-      "clusterCutOff": 10,
-      "enabled": false,
-      "scoreWeight": 10,
-      "windowSize": 100
+      "clusterCutOff": 3,
+      "enabled": true,
+      "scoreWeight": 50,
+      "windowSize": 50
     },
     "stopCodons": {
       "enabled": true,
@@ -67,13 +67,5 @@
   "schemaVersion": "3.0.0",
   "shortcuts": [
     "nextstrain/ebola/bdbv"
-  ],
-  "version": {
-    "updatedAt": "2026-04-14T11:55:23Z",
-    "tag": "2026-04-14--11-55-23Z",
-    "compatibility": {
-      "cli": "3.0.0-alpha.0",
-      "web": "3.0.0-alpha.0"
-    }
-  }
+  ]
 }

data/nextstrain/orthoebolavirus/bdbv/tree.json

@@ -2343,10 +2343,18 @@
               "missingData",
               "mixedSites",
               "privateMutations",
+              "snpClusters",
               "stopCodons"
             ]
           },
           "versions": [
+            {
+              "tag": "unreleased",
+              "compatibility": {
+                "cli": "3.0.0-alpha.0",
+                "web": "3.0.0-alpha.0"
+              }
+            },
             {
               "updatedAt": "2026-05-18T20:09:34Z",
               "tag": "2026-05-18--20-09-34Z",
@@ -2365,8 +2373,7 @@
             }
           ],
           "version": {
-            "updatedAt": "2026-05-18T20:09:34Z",
-            "tag": "2026-05-18--20-09-34Z",
+            "tag": "unreleased",
             "compatibility": {
               "cli": "3.0.0-alpha.0",
               "web": "3.0.0-alpha.0"

data_output/index.json

@@ -0,0 +1,16 @@
+## Unreleased
+
+- adjust QC param settings to reudce private mutation threshold (outbreak genomes should be very similar)
+- add SNP cluster QC rule to trigger on stretches of high private mutation density
+- update tree
+
+## 2026-05-18T20:09:34Z
+
+- Add outbreak annotation
+- add GP_003:367 to known stop codons
+- Include 2026 genomes
+
+
+## 2026-05-15T16:16:45Z
+
+Initial release of this dataset.

data_output/nextstrain/orthoebolavirus/bdbv/unreleased/CHANGELOG.md

@@ -0,0 +1,15 @@
+# Nextclade dataset for Bundibugyo virus (Orthoebolavirus bundibugyoense)
+
+| Key                    | Value                                                                           |
+| ---------------------- | ------------------------------------------------------------------------------- |
+| authors                | [Richard Neher](https://neherlab.org) |
+| data source            | Genbank                                             |
+| nextclade dataset path | nextstrain/orthoebolavirus/bdbv                     |
+| annotation             | [NC_014373.1](https://www.ncbi.nlm.nih.gov/nuccore/NC_014373.1)                   |
+
+This Nextclade dataset for Bundibugyo virus [(Orthoebolavirus bundibugyoense)](https://ictv.global/report/chapter/filoviridae/filoviridae/orthoebolavirus) aligns to the reference sequence [NC_014373.1](https://www.ncbi.nlm.nih.gov/nuccore/NC_014373) and translates major CDS. It scores the sequence with respect to unexpected frameshifts or stop codons, missing sequence (in form of `NNN`s) and mixed bases.
+
+Data from the 2026 outbreak were generously shared by the groups of Prof. Placide Mbala-Kingebeni (INRB, DRC) and Dr Isaac Ssewanyana (CPHL, Uganda) to facilitate the public health response and containment of the virus. These data are described in a post on [Virological.org](https://virological.org/t/initial-genomes-from-may-2026-bundibugyo-virus-disease-outbreak-in-the-democratic-republic-of-the-congo-and-uganda/1032) and were deposited in Pathoplexus under [Restricted Data-Use terms](https://pathoplexus.org/about/terms-of-use/restricted-data). Please consult the authors and the [data-use terms](https://pathoplexus.org/about/terms-of-use/restricted-data) before using these sequences.
+
+
+