Merge pull request #46 from nextstrain/monkeypox_2022-11-03

Add monkeypox 2022-11-03 release assets

CHANGELOG.md

@@ -1,5 +1,13 @@
 # CHANGELOG
 
+## 2022-11-03
+
+### All monkeypox datasets
+
+#### New dataset version (tag `2022-11-03T00:00:00Z`)
+
+- New monkeypox lineages A.2.3, A.3, B.1.13 and B.1.14 were added to the dataset, see https://github.com/mpxv-lineages/lineage-designation/pull/28 for details on these lineages.
+
 ## 2022-10-27
 
 ### All SARS-CoV-2 datasets

data/datasets/MPXV/references/ancestral/versions/2022-11-03T12:00:00Z/files/primers.csv

@@ -0,0 +1 @@
+Country (Institute),Target,Oligonucleotide,Sequence

data/datasets/MPXV/references/ancestral/versions/2022-11-03T12:00:00Z/files/qc.json

@@ -0,0 +1,59 @@
+{
+  "schemaVersion": "1.2.0",
+  "privateMutations": {
+    "enabled": true,
+    "typical": 50,
+    "cutoff": 300,
+    "weightLabeledSubstitutions": 6,
+    "weightReversionSubstitutions": 6,
+    "weightUnlabeledSubstitutions": 1
+  },
+  "missingData": {
+    "enabled": true,
+    "missingDataThreshold": 20000,
+    "scoreBias": 1000
+  },
+  "snpClusters": {
+    "enabled": false,
+    "windowSize": 100,
+    "clusterCutOff": 10,
+    "scoreWeight": 10
+  },
+  "mixedSites": {
+    "enabled": true,
+    "mixedSitesThreshold": 40
+  },
+  "frameShifts": {
+    "enabled": true,
+    "scoreWeight": 20,
+    "ignoredFrameShifts": [
+      { "geneName": "OPG003", "codonRange": {"begin": 3, "end": 589} },
+      { "geneName": "OPG105", "codonRange": {"begin": 281, "end": 285} },
+      { "geneName": "OPG164", "codonRange": {"begin": 227, "end": 229} },
+      { "geneName": "OPG180", "codonRange": {"begin": 554, "end": 560} },
+      { "geneName": "OPG197", "codonRange": {"begin": 42, "end": 101} },
+      { "geneName": "OPG037", "codonRange": {"begin": 443, "end": 443} },
+      { "geneName": "OPG037", "codonRange": {"begin": 57, "end": 443} },
+      { "geneName": "OPG047", "codonRange": {"begin": 481, "end": 483} },
+      { "geneName": "OPG047", "codonRange": {"begin": 482, "end": 483} },
+      { "geneName": "OPG050", "codonRange": {"begin": 72, "end": 76} },
+      { "geneName": "OPG153", "codonRange": {"begin": 369, "end": 371} },
+      { "geneName": "OPG153", "codonRange": {"begin": 370, "end": 371} },
+      { "geneName": "OPG191", "codonRange": {"begin": 166, "end": 169} },
+      { "geneName": "OPG195", "codonRange": {"begin": 72, "end": 222} },
+      { "geneName": "OPG195", "codonRange": {"begin": 208, "end": 222} },
+      { "geneName": "OPG174", "codonRange": {"begin": 289, "end": 346} }
+    ]
+  },
+  "stopCodons": {
+    "enabled": true,
+    "scoreWeight": 20,
+    "ignoredStopCodons": [
+      { "geneName": "NBT03_gp175", "codon": 187 },
+      { "geneName": "OPG015", "codon": 187 },
+      { "geneName": "OPG176", "codon": 21},
+      { "geneName": "OPG187", "codon": 299},
+      { "geneName": "OPG059", "codon": 48}
+    ]
+  }
+}

data/datasets/MPXV/references/ancestral/versions/2022-11-03T12:00:00Z/files/tag.json

@@ -0,0 +1,25 @@
+{
+  "tag": "2022-11-03T12:00:00Z",
+  "comment": "",
+  "compatibility": {
+    "nextcladeCli": {
+      "min": "2.0.0-alpha.0",
+      "max": null
+    },
+    "nextcladeWeb": {
+      "min": "2.0.0-alpha.0",
+      "max": null
+    }
+  },
+  "enabled": true,
+  "files": {
+    "geneMap": "genemap.gff",
+    "primers": "primers.csv",
+    "qc": "qc.json",
+    "reference": "reference.fasta",
+    "sequences": "sequences.fasta",
+    "tree": "tree.json",
+    "virusPropertiesJson": "virus_properties.json"
+  },
+  "metadata": {}
+}

data/datasets/MPXV/references/ancestral/versions/2022-11-03T12:00:00Z/files/virus_properties.json

@@ -0,0 +1,12 @@
+{
+  "schemaVersion": "1.10.0",
+  "nucMutLabelMap": {},
+  "nucMutLabelMapReverse": {},
+  "alignmentParams": {
+    "max_indel": 20000,
+    "seed_spacing": 500,
+    "terminal_bandwidth": 500,
+    "excess_bandwidth": 20,
+    "gap_alignment_side": "left"
+  }
+}

data/datasets/hMPXV/references/NC_063383.1/versions/2022-11-03T12:00:00Z/files/primers.csv

@@ -0,0 +1 @@
+Country (Institute),Target,Oligonucleotide,Sequence

data/datasets/hMPXV/references/NC_063383.1/versions/2022-11-03T12:00:00Z/files/qc.json

@@ -0,0 +1,42 @@
+{
+  "schemaVersion": "1.2.0",
+  "privateMutations": {
+    "enabled": true,
+    "typical": 5,
+    "cutoff": 50,
+    "weightLabeledSubstitutions": 6,
+    "weightReversionSubstitutions": 6,
+    "weightUnlabeledSubstitutions": 1
+  },
+  "missingData": {
+    "enabled": true,
+    "missingDataThreshold": 20000,
+    "scoreBias": 1000
+  },
+  "snpClusters": {
+    "enabled": true,
+    "windowSize": 100,
+    "clusterCutOff": 5,
+    "scoreWeight": 20
+  },
+  "mixedSites": {
+    "enabled": true,
+    "mixedSitesThreshold": 40
+  },
+  "frameShifts": {
+    "enabled": true,
+    "scoreWeight": 20,
+    "ignoredFrameShifts": [
+      { "geneName": "OPG174", "codonRange": {"begin": 289, "end": 346} }
+    ]
+  },
+  "stopCodons": {
+    "enabled": true,
+    "scoreWeight": 40,
+    "ignoredStopCodons": [
+      { "geneName": "NBT03_gp175", "codon": 187 },
+      { "geneName": "OPG015", "codon": 187 },
+      { "geneName": "OPG176", "codon": 21}
+    ]
+  }
+}