Pango build for Nextclade

.gitignore

@@ -14,6 +14,8 @@ stats.json
 log/*
 !log/placeholder_for_sbatch_output
 deployed/*
+freezed
+
 
 .vscode/*
 .DS_Store

defaults/parameters.yaml

@@ -11,12 +11,28 @@ files:
   annotation: "defaults/annotation.gff"
   include: "defaults/include.txt"
   color_schemes: "defaults/color_schemes.tsv"
-  clades: "defaults/clades.tsv"
-  ordering: "defaults/color_ordering.tsv"
-  lat_longs: "defaults/lat_longs.tsv"
   auspice_config: "defaults/auspice_config.json"
   description: "defaults/description.md"
-  mut_fit: "defaults/mutational_fitness_distance_map.json"
+  clades: "builds/clades.tsv"
+  ordering: "builds/color_ordering.tsv"
+  lat_longs: "builds/lat_longs.tsv"
+  mut_fit: "builds/mutational_fitness_distance_map.json"
+  pango_designations: "builds/pango_designations.csv"
+  metadata_designated: "builds/metadata_designated.tsv"
+
+data_source:
+  clades: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/clades.tsv"
+  lat_longs: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/lat_longs.tsv"
+  color_ordering: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/color_ordering.tsv"
+  mut_fit: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/mutational_fitness_distance_map.json"
+  pango_designations: "https://raw.githubusercontent.com/cov-lineages/pango-designation/master/lineages.csv"
+
+origins:
+  gisaid:
+    metadata: "s3://nextstrain-ncov-private/metadata.tsv.gz"
+    sequences: "s3://nextstrain-ncov-private/sequences.fasta.xz"
+    exclude: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/exclude.txt"
+    filters: "--min-length 27000 --min-date 2019-12-01"
 
 tree:
   tree-builder-args: "'-ninit 10 -n 4 -czb'"
@@ -84,3 +100,13 @@ traits:
   sampling_bias_correction: 2.5
   columns: ["country"]
 
+distances:
+  comparisons: ['root', 'root', 'root', 'root', 'root', 'root']
+  attributes: ['S1_mutations', 'DMS_convalescent_serum', 'DMS_Class_1', 'DMS_Class_2', 'DMS_Class_3', 'ACE2_binding_site_mutations']
+  maps:
+    - "defaults/distance_maps/S1.json"
+    - "defaults/distance_maps/convalescent_serum_mean_dms.json"
+    - "defaults/distance_maps/class_1_mean_dms.json"
+    - "defaults/distance_maps/class_2_mean_dms.json"
+    - "defaults/distance_maps/class_3_mean_dms.json"
+    - "defaults/distance_maps/ace2.json"

profiles/basel-combined/builds.yaml

@@ -8,19 +8,15 @@ files:
   ordering: "builds/color_ordering.tsv"
   lat_longs: "builds/lat_longs.tsv"
   mut_fit: "builds/mutational_fitness_distance_map.json"
+  pango_designations: "builds/pango_designations.csv"
+  metadata_designated: "builds/metadata_designated.tsv"
 
 data_source:
   clades: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/clades.tsv"
   lat_longs: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/lat_longs.tsv"
   color_ordering: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/color_ordering.tsv"
   mut_fit: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/mutational_fitness_distance_map.json"
-
-origins:
-  gisaid:
-    metadata: "s3://nextstrain-ncov-private/metadata.tsv.gz"
-    sequences: "s3://nextstrain-ncov-private/sequences.fasta.xz"
-    exclude: "https://raw.githubusercontent.com/nextstrain/ncov/master/defaults/exclude.txt"
-    filters: "--min-length 27000 --min-date 2019-12-01"
+  pango_designations: "https://raw.githubusercontent.com/cov-lineages/pango-designation/master/lineages.csv"
 
 build_dir: "builds-combined"
 auspice_dir: "auspice-combined"

profiles/basel-countries/auspice_config.json

@@ -1,135 +1,135 @@
-{
-  "title": "Genomic epidemiology of SARS-CoV-2 in Europe",
-  "build_url": "https://github.com/neherlab/ncov-simple",
-  "maintainers": [
-    { "name": "Cornelius Roemer", "url": "https://neherlab.org" },
-    { "name": "Richard Neher", "url": "https://neherlab.org" }
-  ],
-  "data_provenance": [
-    {
-      "name": "GISAID"
-    }
-  ],
-  "colorings": [
-    {
-      "key": "country",
-      "title": "Country",
-      "type": "categorical"
-    },
-    {
-      "key": "division",
-      "title": "Admin Division",
-      "type": "categorical"
-    },
-    {
-      "key": "pango_lineage",
-      "title": "PANGO Lineage by GISAID",
-      "type": "categorical"
-    },
-    {
-      "key": "pango_default",
-      "title": "PANGO Lineage by Pangolin",
-      "type": "categorical"
-    },
-    {
-      "key": "pango_usher",
-      "title": "PANGO Lineage by Usher",
-      "type": "categorical"
-    },
-    {
-      "key": "S1_mutations",
-      "title": "S1 mutations",
-      "type": "continuous"
-    },
-    {
-      "key": "GISAID_clade",
-      "title": "GISAID Clade",
-      "type": "categorical"
-    },
-    {
-      "key": "subclade_membership",
-      "title": "Emerging clade",
-      "type": "categorical"
-    },
-    {
-      "key": "region",
-      "title": "Region",
-      "type": "categorical"
-    },
-    {
-      "key": "host",
-      "title": "Host",
-      "type": "categorical"
-    },
-    {
-      "key": "age",
-      "title": "Age",
-      "type": "continuous"
-    },
-    {
-      "key": "sex",
-      "title": "Sex",
-      "type": "categorical"
-    },
-    {
-      "key": "author",
-      "title": "Authors",
-      "type": "categorical"
-    },
-    {
-      "key": "originating_lab",
-      "title": "Originating Lab",
-      "type": "categorical"
-    },
-    {
-      "key": "submitting_lab",
-      "title": "Submitting Lab",
-      "type": "categorical"
-    },
-    {
-      "key": "recency",
-      "title": "Submission Date",
-      "type": "categorical"
-    },
-    {
-      "key": "country_exposure",
-      "title": "Country of exposure",
-      "type": "categorical"
-    },
-    {
-      "key": "division_exposure",
-      "title": "Division of exposure",
-      "type": "categorical"
-    },
-    {
-      "key": "region_exposure",
-      "title": "Region of exposure",
-      "type": "categorical"
-    }
-  ],
-  "geo_resolutions": ["location", "division", "country", "region"],
-  "display_defaults": {
-    "color_by": "clade_membership",
-    "distance_measure": "num_date",
-    "geo_resolution": "country",
-    "map_triplicate": true,
-    "branch_label": "clade",
-    "transmission_lines": false
-  },
-  "filters": [
-    "recency",
-    "region",
-    "country",
-    "division",
-    "location",
-    "host",
-    "S1_mutations",
-    "pango_lineage",
-    "pango_default",
-    "pango_usher",
-    "clade_membership",
-    "emerging_lineage",
-    "author"
-  ],
-  "panels": ["tree", "map", "entropy", "frequencies"]
-}
+{
+  "title": "Genomic epidemiology of SARS-CoV-2 in Europe",
+  "build_url": "https://github.com/neherlab/ncov-simple",
+  "maintainers": [
+    { "name": "Cornelius Roemer", "url": "https://neherlab.org" },
+    { "name": "Richard Neher", "url": "https://neherlab.org" }
+  ],
+  "data_provenance": [
+    {
+      "name": "GISAID"
+    }
+  ],
+  "colorings": [
+    {
+      "key": "country",
+      "title": "Country",
+      "type": "categorical"
+    },
+    {
+      "key": "division",
+      "title": "Admin Division",
+      "type": "categorical"
+    },
+    {
+      "key": "pango_lineage",
+      "title": "PANGO Lineage by GISAID",
+      "type": "categorical"
+    },
+    {
+      "key": "pango_default",
+      "title": "PANGO Lineage by Pangolin",
+      "type": "categorical"
+    },
+    {
+      "key": "pango_usher",
+      "title": "PANGO Lineage by Usher",
+      "type": "categorical"
+    },
+    {
+      "key": "S1_mutations",
+      "title": "S1 mutations",
+      "type": "continuous"
+    },
+    {
+      "key": "GISAID_clade",
+      "title": "GISAID Clade",
+      "type": "categorical"
+    },
+    {
+      "key": "subclade_membership",
+      "title": "Emerging clade",
+      "type": "categorical"
+    },
+    {
+      "key": "region",
+      "title": "Region",
+      "type": "categorical"
+    },
+    {
+      "key": "host",
+      "title": "Host",
+      "type": "categorical"
+    },
+    {
+      "key": "age",
+      "title": "Age",
+      "type": "continuous"
+    },
+    {
+      "key": "sex",
+      "title": "Sex",
+      "type": "categorical"
+    },
+    {
+      "key": "author",
+      "title": "Authors",
+      "type": "categorical"
+    },
+    {
+      "key": "originating_lab",
+      "title": "Originating Lab",
+      "type": "categorical"
+    },
+    {
+      "key": "submitting_lab",
+      "title": "Submitting Lab",
+      "type": "categorical"
+    },
+    {
+      "key": "recency",
+      "title": "Submission Date",
+      "type": "categorical"
+    },
+    {
+      "key": "country_exposure",
+      "title": "Country of exposure",
+      "type": "categorical"
+    },
+    {
+      "key": "division_exposure",
+      "title": "Division of exposure",
+      "type": "categorical"
+    },
+    {
+      "key": "region_exposure",
+      "title": "Region of exposure",
+      "type": "categorical"
+    }
+  ],
+  "geo_resolutions": ["location", "division", "country", "region"],
+  "display_defaults": {
+    "color_by": "clade_membership",
+    "distance_measure": "num_date",
+    "geo_resolution": "country",
+    "map_triplicate": true,
+    "branch_label": "clade",
+    "transmission_lines": false
+  },
+  "filters": [
+    "recency",
+    "region",
+    "country",
+    "division",
+    "location",
+    "host",
+    "S1_mutations",
+    "pango_lineage",
+    "pango_default",
+    "pango_usher",
+    "clade_membership",
+    "emerging_lineage",
+    "author"
+  ],
+  "panels": ["tree", "map", "entropy", "frequencies"]
+}