Merge pull request #29 from nextstrain/hpxv

Add Monkeypox datasets

CHANGELOG.md

@@ -1,3 +1,36 @@
+## 2022-06-14
+
+### 3 Monkeypox (MPXV) datasets introduced
+
+Three MPXV datasets are added with differing zoom levels containing:
+
+- MPXV (All clades)
+- hMPXV-1 (part of clade 3, source of 2017/2018/2022 outbreaks)
+- hMPXV-1 B.1 (2022 outbreak lineage)
+
+All 3 use the coordinate system of the recently designated NCBI Monkeypox reference sequence NC_063383 (MPXV-M5312_HM12_Rivers).
+
+However, SNPs from two different ref sequences are added to the "all clades" and B.1 datasets to reduce the number of total mutations.
+
+The B.1 datset uses SNPs of ON563414.3 (MPXV_USA_2022_MA001) on top of a NC_063383 backbone.
+
+The "all clades" build uses the SNPs of a reconstructed ancestral MPXV sequence that is the inferred most recent common ancestor of clades 1, 2 and 3, rooted with a Cowpox outgroup.
+
+Only the MPXV (All clades) dataset can assign all clades 1, 2 and 3.
+The hMPXV-1 dataset can be used if all viruses are from hMPXV-1.
+The B.1 dataset is useful for 2022 outbreak sequences but will not be able to assign anything but B.1 lineages.
+
+Gene annotations follow the annotation used by NC_063383 and is of the form `OPG001` (for OrthoPox Gene 001).
+Since the alignment reference is always in NC_063383 coordinates, nucleotide and protein mutation position should usually be identical in alignments done with all three datasets.
+
+Quality control parameters are subject to change, especially since "known" frame shifts and stop codons have not been annotated. For example, clade 1 sequences will always show around 7 frame shifts, yet these do not indicate quality problems.
+
+### New dataset version (tag `2022-06-14T12:00:00Z`)
+
+#### SARS-CoV-2
+
+- Pango lineages: New lineages added up till [pango-designation release](https://github.com/cov-lineages/pango-designation/releases) v1.9 and beyond are now included, including among others `BA.5.1-BA.5.3`, `BA.2.35-BA.2.48` and `XV-XY`
+
 ## 2022-04-28
 
 ### New dataset version (tag `2022-04-28T12:00:00Z`)

data/datasets/MPXV/dataset.json

@@ -0,0 +1,7 @@
+{
+  "defaultRef": "ancestral",
+  "enabled": true,
+  "metadata": {},
+  "name": "MPXV",
+  "nameFriendly": "Monkeypox (All Clades)"
+}

data/datasets/MPXV/references/ancestral/datasetRef.json

@@ -0,0 +1,9 @@
+{
+  "enabled": true,
+  "metadata": {},
+  "reference": {
+    "source": "genbank",
+    "accession": "ancestral",
+    "strainName": "Reconstructed ancestral MPXV"
+  }
+}

data/datasets/MPXV/references/ancestral/versions/2022-06-14T12:00:00Z/files/qc.json

@@ -0,0 +1,32 @@
+{
+  "schemaVersion": "1.2.0",
+  "privateMutations": {
+    "enabled": true,
+    "typical": 50,
+    "cutoff": 300
+  },
+  "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": 2
+  },
+  "stopCodons": {
+    "enabled": true,
+    "scoreWeight": 10,
+    "ignoredStopCodons": []
+  }
+}

data/datasets/monkeypox/references/MT903344.1/versions/2022-05-20T12:00:00Z/files/tag.json → data/datasets/MPXV/references/ancestral/versions/2022-06-14T12:00:00Z/files/tag.json

@@ -1,6 +1,6 @@
 {
-  "tag": "2022-05-20T12:00:00Z",
-  "comment": "First Monkeypox dataset, experimental",
+  "tag": "2022-06-14T12:00:00Z",
+  "comment": "Monkeypox all-clades dataset",
   "compatibility": {
     "nextcladeCli": {
       "min": "1.999.0",

data/datasets/monkeypox/references/MT903344.1/versions/2022-05-20T12:00:00Z/files/virus_properties.json → data/datasets/MPXV/references/ancestral/versions/2022-06-14T12:00:00Z/files/virus_properties.json

@@ -3,10 +3,10 @@
   "nucMutLabelMap": {},
   "nucMutLabelMapReverse": {},
   "alignmentParams": {
-    "max_indel": 5000,
-    "seed_spacing": 1000,
-    "terminal_bandwidth": 100,
-    "excess_bandwidth": 3,
+    "max_indel": 20000,
+    "seed_spacing": 500,
+    "terminal_bandwidth": 500,
+    "excess_bandwidth": 20,
     "gap_alignment_side": "left"
   }
 }

data/datasets/hMPXV/dataset.json

@@ -0,0 +1,7 @@
+{
+  "defaultRef": "NC_063383.1",
+  "enabled": true,
+  "metadata": {},
+  "name": "hMPXV",
+  "nameFriendly": "Human Monkeypox (hMPXV)"
+}

data/datasets/monkeypox/references/MT903344.1/datasetRef.json → data/datasets/hMPXV/references/NC_063383.1/datasetRef.json

@@ -3,7 +3,7 @@
   "metadata": {},
   "reference": {
     "source": "genbank",
-    "accession": "MT903344.1",
-    "strainName": "MPXV-UK_P2/2018"
+    "accession": "NC_063383.1",
+    "strainName": "MPXV-M5312_HM12_Rivers"
   }
 }

data/datasets/hMPXV/references/NC_063383.1/versions/2022-06-14T12:00:00Z/files/primers.csv

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

data/datasets/hMPXV/references/NC_063383.1/versions/2022-06-14T12:00:00Z/files/tag.json

@@ -0,0 +1,25 @@
+{
+  "tag": "2022-06-14T12:00:00Z",
+  "comment": "hMPXV-1 dataset",
+  "compatibility": {
+    "nextcladeCli": {
+      "min": "1.999.0",
+      "max": null
+    },
+    "nextcladeWeb": {
+      "min": "1.999.0",
+      "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/hMPXV/references/NC_063383.1/versions/2022-06-14T12:00:00Z/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_B1/dataset.json

@@ -0,0 +1,7 @@
+{
+  "defaultRef": "pseudo_ON563414",
+  "enabled": true,
+  "metadata": {},
+  "name": "hMPXV_B1",
+  "nameFriendly": "Human Monkeypox Clade B.1"
+}

data/datasets/hMPXV_B1/references/pseudo_ON563414/datasetRef.json

@@ -0,0 +1,9 @@
+{
+  "enabled": true,
+  "metadata": {},
+  "reference": {
+    "source": "genbank",
+    "accession": "pseudo_ON563414",
+    "strainName": "MPXV_USA_2022_MA001 in NC_063383 coordinates"
+  }
+}