Merge pull request #45 from nextstrain/nextclade

Nextclade

nextclade/config/auspice_config.json

@@ -0,0 +1,69 @@
+{
+  "title": "Nextclade dataset for RSV",
+  "build_url": "https://github.com/neherlab/nextclade_data_workflows",
+  "maintainers": [
+    { "name": "Cornelius Roemer", "url": "https://neherlab.org" },
+    { "name": "Richard Neher", "url": "https://neherlab.org" }
+  ],
+  "data_provenance": [
+    {
+      "name": "Genbank"
+    }
+  ],
+  "colorings": [
+    {
+      "key": "country",
+      "title": "Country",
+      "type": "categorical"
+    },
+    {
+      "key": "region",
+      "title": "Region",
+      "type": "categorical"
+    },
+    {
+      "key": "G_clade",
+      "title": "G Clades (Goya et al)",
+      "type": "categorical"
+    },
+    {
+      "key": "genome_clade",
+      "title": "Genome Clades (Ramaekers et al)",
+      "type": "categorical"
+    },
+    {
+      "key": "date",
+      "title": "Sample Date",
+      "type": "ordinal"
+    },
+    {
+      "key": "EPI_ISL",
+      "title": "EPI_ISL",
+      "type": "categorical"
+    }
+  ],
+  "filters": [
+    "region",
+    "country",
+    "clade_membership",
+    "G_clade"
+  ],
+  "display_defaults": {
+    "color_by": "clade_membership",
+    "distance_measure": "div",
+    "branch_label": "clade"
+  },
+  "panels": ["tree","entropy"],
+  "extensions": {
+    "nextclade": {
+      "clade_node_attrs": [
+        {
+          "name": "G_clade",
+          "displayName": "G_clade (Goya et al)",
+          "description": "Clades based on the G gene by Goya et al, IRV, 2019.",
+          "hideInWeb": false
+        }
+      ]
+    }
+  }
+}

nextclade/config/config_dict.yaml

@@ -0,0 +1,35 @@
+strain_id_field: accession
+CDS: ["NS1", "NS2", "N", "P", "M", "SH", "G", "F", "M2-1", "M2-2", "L"]
+auspice_config: "config/auspice_config.json"
+color_schemes: "../config/color_schemes.tsv"
+
+builds:
+  a:
+    refs:
+      EPI_ISL_412866:
+        filter: "--min-date 1965 --probabilistic-sampling --group-by year --subsample-max-sequences 1500 --query 'genome_coverage>0.95'"
+        exclude_url: https://raw.githubusercontent.com/nextstrain/rsv/master/config/outliers.txt
+        reference_strain: hRSV/A/England/397/2017
+        reference_accession: EPI_ISL_412866
+    clade_systems:
+      consortium:
+        url: "https://raw.githubusercontent.com/rsv-lineages/lineage-designation-A/main/.auto-generated/lineage.tsv"
+      G:
+        url: "https://raw.githubusercontent.com/nextstrain/rsv/master/config/clades_G_a.tsv"
+        key: G_clade
+        label_key: G_clade
+
+  b:
+    refs:
+      EPI_ISL_1653999:
+        filter: "--min-date 1965 --probabilistic-sampling --group-by year --subsample-max-sequences 1500 --query 'genome_coverage>0.95'"
+        exclude_url: https://raw.githubusercontent.com/nextstrain/rsv/master/config/outliers.txt
+        reference_strain: hRSV/B/Australia/VIC-RCH056/2019
+        reference_accession: EPI_ISL_1653999
+    clade_systems:
+      consortium:
+        url: https://raw.githubusercontent.com/rsv-lineages/lineage-designation-B/main/.auto-generated/lineage.tsv
+      G:
+        key: G_clade
+        label_key: G_clade
+        url: "https://raw.githubusercontent.com/nextstrain/rsv/master/config/clades_G_b.tsv"

nextclade/config/pathogen.json

@@ -0,0 +1,82 @@
+{
+  "schemaVersion": "3.0.0",
+  "alignmentParams": {
+    "excessBandwidth": 9,
+    "terminalBandwidth": 100,
+    "allowedMismatches": 4,
+    "gapAlignmentSide": "left",
+    "minSeedCover": 0.1
+  },
+  "compatibility": {
+    "cli": "3.0.0-alpha.0",
+    "web": "3.0.0-alpha.0"
+  },
+  "defaultGene": "F",
+  "files": {
+    "changelog": "CHANGELOG.md",
+    "examples": "sequences.fasta",
+    "genomeAnnotation": "genome_annotation.gff3",
+    "pathogenJson": "pathogen.json",
+    "readme": "README.md",
+    "reference": "reference.fasta",
+    "treeJson": "tree.json"
+  },
+  "qc": {
+    "privateMutations": {
+      "enabled": true,
+      "typical": 50,
+      "cutoff": 150,
+      "weightLabeledSubstitutions": 2,
+      "weightReversionSubstitutions": 1,
+      "weightUnlabeledSubstitutions": 1
+    },
+    "missingData": {
+      "enabled": false,
+      "missingDataThreshold": 2000,
+      "scoreBias": 500
+    },
+    "snpClusters": {
+      "enabled": false,
+      "windowSize": 100,
+      "clusterCutOff": 10,
+      "scoreWeight": 50
+    },
+    "mixedSites": {
+      "enabled": true,
+      "mixedSitesThreshold": 8
+    },
+    "frameShifts": {
+      "enabled": true
+    },
+    "stopCodons": {
+      "enabled": true,
+      "ignoredStopCodons": []
+    }
+  },
+  "geneOrderPreference": [
+    "F",
+    "G",
+    "L"
+  ],
+  "maintenance": {
+    "website": [
+      "https://nextstrain.org",
+      "https://clades.nextstrain.org"
+    ],
+    "documentation": [
+      "https://github.com/nextstrain/rsv"
+    ],
+    "source code": [
+      "https://github.com/nextstrain/rsv"
+    ],
+    "issues": [
+      "https://github.com/nextstrain/rsv/issues"
+    ],
+    "organizations": [
+      "Nextstrain"
+    ],
+    "authors": [
+      "Nextstrain team <https://nextstrain.org>"
+    ]
+  }
+}