Add files to Nextclade Dataset

nextstrain · May 22, 2024 · bba4969 · bba4969
1 parent 751cb5c
commit bba4969
Show file tree

Hide file tree

Showing 4 changed files with 1,332 additions and 13 deletions.
diff --git a/nextclade_dataset/CHANGELOG.md b/nextclade_dataset/CHANGELOG.md
@@ -0,0 +1,3 @@
+## Unreleased
+
+Initial release.
diff --git a/nextclade_dataset/README.md b/nextclade_dataset/README.md
@@ -0,0 +1,29 @@
+# Measles dataset
+
+| Key               | Value                                                                                                                                                            |
+| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| authors           | [Nextstrain](https://nextstrain.org)                                            |
+| reference         | NC_001498.1                                                                                                                        |
+| workflow          | https://github.com/nextstrain/measles/tree/main/nextclade                                                                                     |
+| path              | `nextstrain/measles`                                                                                                                                  |
+
+
+## Scope of this dataset
+
+This dataset assigns genotypes to measles samples based on [criteria outlined by the WHO](https://www.who.int/publications/i/item/WER8709). 
+
+The WHO has defined 24 measles genotypes based on N gene and H gene sequences from 28 reference strains. For new measles samples, genotypes can be assigned based on genetic similarity to the reference strains at the "N450" region (a 450 bp region of the N gene). 
+
+The tree used in this dataset includes N450 sequences for the 28 reference strains, along with other representative strains for each genotype. 
+
+## Features
+
+This dataset supports:
+
+- Assignment of genotypes
+- Minimal sequence QC
+- Phylogenetic placement
+
+## What are Nextclade datasets
+
+Read more about Nextclade datasets in the Nextclade documentation: https://docs.nextstrain.org/projects/nextclade/en/stable/user/datasets.html
diff --git a/nextclade_dataset/pathogen.json b/nextclade_dataset/pathogen.json
@@ -1,15 +1,52 @@
 {
-	"files": {
-	  "reference": "measles_reference_N450.fasta",
-	  "pathogenJson": "pathogen.json",
-	  "genomeAnnotation": "measles_reference_N450.gff3",
-	  "treeJson": "measles_nextclade.json"
-	},
-	"attributes": {
-	  "name": "Measles"
-	},
-	"schemaVersion": "3.0.0",
-	"version": {
-	  "tag": "unreleased"
-	}
+  "files": {
+    "reference": "measles_reference_N450.fasta",
+    "pathogenJson": "pathogen.json",
+    "genomeAnnotation": "measles_reference_N450.gff3",
+    "treeJson": "measles_nextclade.json",
+    "examples": "sequences.fasta",
+    "readme": "README.md",
+    "changelog": "CHANGELOG.md"
+  },
+  "attributes": {
+    "name": "Measles (N450)",
+    "reference name": "Ichinose-B95a",
+    "reference accession": "NC_001498.1"
+  },
+  "schemaVersion": "1.0.0",
+  "alignmentParams": {
+      "minSeedCover": 0.01,
+      "minLength": 400
+  },
+  "qc": {
+    "missingData": {
+      "enabled": true,
+      "missingDataThreshold": 20,
+      "scoreBias": 4
+    },
+    "mixedSites": {
+      "enabled": true,
+      "mixedSitesThreshold": 4
+    },
+    "frameShifts": {
+      "enabled": true
+    },
+    "stopCodons": {
+      "enabled": true
+    },
+    "privateMutations": {
+      "enabled": true,
+      "cutoff": 8,
+      "typical": 2,
+      "weightLabeledSubstitutions": 2,
+      "weightReversionSubstitutions": 1,
+      "weightUnlabeledSubstitutions": 1
+    },
+    "snpClusters": {
+      "enabled": true,
+      "clusterCutOff": 3,
+      "scoreWeight": 50,
+      "windowSize": 50
+    }
   }
+}