Merge remote-tracking branch 'origin/master' into yellow-fever-dataset

data/nextstrain/collection.json

@@ -38,6 +38,7 @@
     "nextstrain/rsv/a/EPI_ISL_412866",
     "nextstrain/rsv/b/EPI_ISL_1653999",
     "nextstrain/mpox/all-clades",
+    "nextstrain/mpox/clade-i",
     "nextstrain/mpox/clade-iib",
     "nextstrain/mpox/lineage-b.1",
     "nextstrain/flu/h3n2/pb1",

data/nextstrain/mpox/clade-i/CHANGELOG.md

@@ -0,0 +1,3 @@
+## 2024-08-01T22:31:31Z
+
+Initial release of this dataset.

data/nextstrain/mpox/clade-i/README.md

@@ -0,0 +1,28 @@
+# Nextclade dataset for "Mpox virus (Clade I)"
+
+| Key                    | Value                                                                                                                                                                                  |
+| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| authors                | [Cornelius Roemer](https://neherlab.org), [Richard Neher](https://neherlab.org), [Nextstrain](https://nextstrain.org)                                                                  |
+| data source            | Genbank                                                                                                                                                                                |
+| workflow               | [github.com/nextstrain/mpox/nextclade](https://github.com/nextstrain/mpox/nextclade)                                                                                                   |
+| nextclade dataset path | nextstrain/mpox/clade-i                                                                                                                                                                |
+| reference              | [DQ011155.1](https://www.ncbi.nlm.nih.gov/nuccore/DQ011155.1), isolate `Zaire_1979-005`, an early complete clade I sequence                                                            |
+| annotation             | based on [DQ011155.1](https://www.ncbi.nlm.nih.gov/nuccore/DQ011155.1), but with genes called by modern names (OPGXXX)                                                                 |
+| clade definitions      | [github.com/mpxv-lineages/lineage-designation](https://github.com/mpxv-lineages/lineage-designation)                                                                                   |
+| related datasets       | Mpox virus (All clades): `nextstrain/mpox/all-clades`<br>Mpox virus (clade IIb) `nextstrain/mpox/clade-iib`<br>Mpox virus (Lineage B.1 within clade IIb) `nextstrain/mpox/lineage-b.1` |
+
+## Scope of this dataset
+
+This dataset is for Mpox viruses of clade I (Ia and Ib). A broader dataset for all clades I, IIa and IIb is available under `nextstrain/mpox/all-clades`.
+
+## Reference sequence and reference tree
+
+The reference used in this dataset is [DQ011155.1](https://www.ncbi.nlm.nih.gov/nuccore/DQ011155.1), an early complete clade I sequence (Isolate `Zaire_1979-005`).
+
+This is in contrast to the reference used in the other Nextclade mpox datasets, which use a clade IIb reference sequence.
+
+The reference tree consists of all good quality clade I sequences available within Genbank at the time of dataset creation (with identical sequences deduplicated to 1), as well as 3 outgroup genomes (a reconstructed ancestor of all clades, and one sequence for each of clade IIa and clade IIb).
+
+## Further reading
+
+Read more about Nextclade datasets in the Nextclade documentation: https://docs.nextstrain.org/projects/nextclade/en/stable/user/datasets.html

data/nextstrain/mpox/clade-i/pathogen.json

@@ -0,0 +1,75 @@
+{
+  "alignmentParams": {
+    "excessBandwidth": 100,
+    "terminalBandwidth": 300,
+    "allowedMismatches": 8,
+    "windowSize": 40,
+    "minSeedCover": 0.1,
+    "gapAlignmentSide": "left"
+  },
+  "attributes": {
+    "name": "Mpox virus (Clade I)",
+    "reference accession": "DQ011155.1",
+    "reference name": "Zaire_1979-005"
+  },
+  "compatibility": {
+    "cli": "3.0.0-alpha.0",
+    "web": "3.0.0-alpha.0"
+  },
+  "deprecated": false,
+  "enabled": true,
+  "experimental": false,
+  "files": {
+    "changelog": "CHANGELOG.md",
+    "examples": "sequences.fasta",
+    "genomeAnnotation": "genome_annotation.gff3",
+    "pathogenJson": "pathogen.json",
+    "readme": "README.md",
+    "reference": "reference.fasta",
+    "treeJson": "tree.json"
+  },
+  "official": true,
+  "qc": {
+    "frameShifts": {
+      "enabled": true,
+      "ignoredFrameShifts": [
+      ],
+      "scoreWeight": 20
+    },
+    "missingData": {
+      "enabled": true,
+      "missingDataThreshold": 20000,
+      "scoreBias": 1000
+    },
+    "mixedSites": {
+      "enabled": true,
+      "mixedSitesThreshold": 40
+    },
+    "privateMutations": {
+      "cutoff": 50,
+      "enabled": true,
+      "typical": 5,
+      "weightLabeledSubstitutions": 6,
+      "weightReversionSubstitutions": 6,
+      "weightUnlabeledSubstitutions": 1
+    },
+    "snpClusters": {
+      "clusterCutOff": 5,
+      "enabled": true,
+      "scoreWeight": 10,
+      "windowSize": 1000
+    },
+    "stopCodons": {
+      "enabled": true,
+      "ignoredStopCodons": [
+      ],
+      "scoreWeight": 40
+    }
+  },
+  "schemaVersion": "3.0.0",
+  "shortcuts": [
+  ],
+  "version": {
+    "tag": "unreleased"
+  }
+}

data/nextstrain/rsv/a/EPI_ISL_412866/CHANGELOG.md

@@ -1,3 +1,10 @@
+## 2024-08-01T22:31:31Z
+
+ - add subclades A.D.1.4-8
+ - add subclades A.D.3.2-6, add representatives to A.D.3.1
+ - add subclade A.D.5.4, adjust definition of A.D.5.3 to make it a clear sibling
+
+
 ## 2024-01-29T10:29:43Z
 
  - fix definitions of G_clades (legacy) for RSV-A and RSV-B

data/nextstrain/rsv/a/EPI_ISL_412866/README.md

@@ -4,7 +4,7 @@
 | ---------------------- | --------------------------------------------------------------------------------------------------------------------|
 | authors                | [Richard Neher](https://neherlab.org), Laura Urbanska, [Nextstrain](https://nextstrain.org)                         |
 | data source            | Genbank + authorized other sequences                                                                                |
-| workflow               | [github.com/nextstrain/rsv/nextclade](https://github.com/nextstrain/rsv/nextclade)                                  |
+| workflow               | [github.com/nextstrain/rsv](https://github.com/nextstrain/rsv)                                                      |
 | nextclade dataset path | nextstrain/rsv/a/EPI_ISL_412866                                                                                     |
 | reference              | EPI_ISL_412866                                                                                                      |
 | clade definitions      | [github.com/rsv-lineages/lineage-designation-A](https://github.com/rsv-lineages/lineage-designation-A)              |

data/nextstrain/rsv/a/EPI_ISL_412866/pathogen.json

@@ -50,7 +50,12 @@
     },
     "stopCodons": {
       "enabled": true,
-      "ignoredStopCodons": []
+      "ignoredStopCodons": [
+        {
+          "codon": 320,
+          "cdsName": "G"
+        }
+      ]
     }
   },
   "cdsOrderPreference": [
@@ -88,5 +93,10 @@
     "name": "RSV-A",
     "reference accession": "EPI_ISL_412866",
     "reference name": "hRSV/A/England/397/2017"
-  }
+  },
+  "geneOrderPreference": [
+    "F",
+    "G",
+    "L"
+  ]
 }