Merge pull request #122 from nextstrain/update-location-threshold

Update location threshold

README.md

@@ -96,14 +96,6 @@ The current available options for `geo_resolutions` are
 The `prepare_data` params in `config/config.yaml` are used to subset the full
 case counts and clades counts data to specific date range, locations, and clades.
 
-As of 2023-04-04, the config for the automated pipeline is set to only include data from:
-
-- the past 150 days
-    - excluding sequences from the last 12 days since they may be overly enriched for variants
-- locations that have at least 500 sequences in the last 30 days
-    - excluding locations specifically listed in `defaults/global_excluded_locations.txt`
-- clades that have at least 5000 sequences in the last 150 days
-
 ### Model configurations
 
 The specific model configurations are housed in separate config YAML files or each model.

config/config.yaml

@@ -16,39 +16,35 @@ prepare_data:
     nextstrain_clades:
       global:
         included_days: 150
-        location_min_seq: 50
-        location_min_seq_days: 30
+        location_min_seq: 1000
+        location_min_seq_days: 150
         excluded_locations: "defaults/global_excluded_locations.txt"
-        prune_seq_days: 12
-        clade_min_seq: 2000
+        clade_min_seq: 500
         clade_min_seq_days: 150
     pango_lineages:
       global:
         included_days: 150
-        location_min_seq: 150
-        location_min_seq_days: 30
+        location_min_seq: 1000
+        location_min_seq_days: 150
         excluded_locations: "defaults/global_excluded_locations.txt"
-        prune_seq_days: 12
         clade_min_seq: 1
         clade_min_seq_days: 150
         collapse_threshold: 350
   open:
     nextstrain_clades:
       global:
         included_days: 150
-        location_min_seq: 50
-        location_min_seq_days: 30
+        location_min_seq: 1000
+        location_min_seq_days: 150
         excluded_locations: "defaults/global_excluded_locations.txt"
-        prune_seq_days: 12
-        clade_min_seq: 2000
+        clade_min_seq: 500
         clade_min_seq_days: 150
     pango_lineages:
       global:
         included_days: 150
-        location_min_seq: 150
-        location_min_seq_days: 30
+        location_min_seq: 1000
+        location_min_seq_days: 150
         excluded_locations: "defaults/global_excluded_locations.txt"
-        prune_seq_days: 12
         clade_min_seq: 1
         clade_min_seq_days: 150
         collapse_threshold: 350

viz/src/App.jsx

@@ -31,7 +31,7 @@ function App() {
         <p>
           Each line represents the estimated frequency of a particular clade through time.
           Equivalent Pango lineage is given in parenthesis, eg clade 23A (lineage XBB.1.5). Only
-          locations with more than 50 sequences from samples collected in the previous 30 days are
+          locations with more than 1000 sequences from samples collected in the previous 150 days are
           included. Results last updated {mlrCladesData?.modelData?.get('updated') || 'loading'}.
         </p>
         <div id="cladeFrequenciesPanel" class="panelDisplay"> {/* surrounding div(s) used for static-images.js script */}
@@ -54,7 +54,7 @@ function App() {
         <p>
           Each line represents the estimated frequency of a particular Pango lineage through time.
           Lineages with fewer than 350 observations are collapsed into parental lineage. Only
-          locations with more than 150 sequences from samples collected in the previous 30 days are
+          locations with more than 1000 sequences from samples collected in the previous 150 days are
           included. Results last updated {mlrLineagesData?.modelData?.get('updated') || 'loading'}.
         </p>
         <div id="lineageFrequenciesPanel" class="panelDisplay">