Add lineage-1A and lineage-2 phylogenetic trees

.github/workflows/phylogenetic.yaml

@@ -106,6 +106,67 @@ jobs:
         phylogenetic/logs/
         phylogenetic/.snakemake/log/
 
+
+  phylogenetic_lineage_1A:
+    needs: [set_config_overrides]
+    permissions:
+      id-token: write
+    uses: nextstrain/.github/.github/workflows/pathogen-repo-build.yaml@master
+    secrets: inherit
+    with:
+      # Starting with the default docker runtime
+      # We can migrate to AWS Batch when/if we need to for more resources or if
+      # the job runs longer than the GH Action limit of 6 hours.
+      runtime: docker
+      env: |
+        NEXTSTRAIN_DOCKER_IMAGE: ${{ inputs.image }}
+        CONFIG_OVERRIDES: ${{ needs.set_config_overrides.outputs.config_overrides }}
+      run: |
+        nextstrain build \
+          phylogenetic \
+            deploy_all \
+            --configfile build-configs/nextstrain-automation/config.yaml defaults/lineage-1A/config.yaml \
+            $CONFIG_OVERRIDES
+      # Specifying artifact name to differentiate ingest build outputs from
+      # the phylogenetic build outputs
+      artifact-name: phylogenetic-1A-build-output
+      artifact-paths: |
+        phylogenetic/auspice/
+        phylogenetic/results/
+        phylogenetic/benchmarks/
+        phylogenetic/logs/
+        phylogenetic/.snakemake/log/
+
+  phylogenetic_lineage_2:
+    needs: [set_config_overrides]
+    permissions:
+      id-token: write
+    uses: nextstrain/.github/.github/workflows/pathogen-repo-build.yaml@master
+    secrets: inherit
+    with:
+      # Starting with the default docker runtime
+      # We can migrate to AWS Batch when/if we need to for more resources or if
+      # the job runs longer than the GH Action limit of 6 hours.
+      runtime: docker
+      env: |
+        NEXTSTRAIN_DOCKER_IMAGE: ${{ inputs.image }}
+        CONFIG_OVERRIDES: ${{ needs.set_config_overrides.outputs.config_overrides }}
+      run: |
+        nextstrain build \
+          phylogenetic \
+            deploy_all \
+            --configfile build-configs/nextstrain-automation/config.yaml defaults/lineage-2/config.yaml \
+            $CONFIG_OVERRIDES
+      # Specifying artifact name to differentiate ingest build outputs from
+      # the phylogenetic build outputs
+      artifact-name: phylogenetic-2-build-output
+      artifact-paths: |
+        phylogenetic/auspice/
+        phylogenetic/results/
+        phylogenetic/benchmarks/
+        phylogenetic/logs/
+        phylogenetic/.snakemake/log/
+
   phylogenetic_wa:
     needs: [set_config_overrides]
     permissions:

phylogenetic/defaults/description.md

@@ -2,6 +2,18 @@ We gratefully acknowledge the authors, originating and submitting laboratories o
 
 Special thanks to individuals at the [Northwest Pathogen Genomics Center of Excellence](https://github.com/NW-PaGe) and [Grubaugh lab](https://grubaughlab.com/) for comments, code and suggestions.
 
+We maintain four views of WNV evolution:
+
+The first is [`wnv/global`](https://next.nextstrain.org/staging/WNV/global), which focuses on broader viral diversity for all WNV sequences submitted to GenBank which contain at least 75% of the genome length.
+
+The second is [`wnv/wa`](https://next.nextstrain.org/staging/WNV/global), which focuses on Washington State WNV virus sequences with tiered subsampling from Washington, the surrounding states, and across the USA.
+
+The third is [`wnv/lineage-1A`](https://next.nextstrain.org/staging/WNV/lineage-1A), which focuses on lineage 1A and uses X as the reference.
+
+The third is [`wnv/lineage-2`](https://next.nextstrain.org/staging/WNV/lineage-2), which focuses on lineage 2 and uses X as the reference.
+
+#### Underlying data
+
 We curate sequence data and metadata from NCBI as starting point for our analyses. For global lineage designations, we query [pathoplexus](https://pathoplexus.org/) for lineage assignments and exclusively work with NCBI-sourced records at this time. Curated sequences and metadata are available as flat files at:
 
 * [data.nextstrain.org/files/workflows/WNV/sequences.fasta.zst](https://data.nextstrain.org/files/workflows/WNV/sequences.fasta.zst)

phylogenetic/defaults/lineage-1A/auspice_config.json

@@ -0,0 +1,70 @@
+{
+  "title": "West Nile Virus Build (lineage-1A)",
+  "data_provenance": [
+    {
+      "name": "GenBank",
+      "url": "https://www.ncbi.nlm.nih.gov/genbank/"
+    }
+  ],
+  "colorings": [
+    {"key": "gt", "title": "Genotype", "type": "categorical"},
+    {"key": "num_date", "title": "Sampling Date", "type": "continuous"},
+    {"key": "region", "title": "Region", "type": "categorical"},
+    {"key": "country", "title": "Country", "type": "categorical"},
+    {"key": "lineage", "title": "Pathoplexus lineage", "type": "categorical"},
+    {"key": "clade_membership", "title": "Clade", "type": "categorical"},
+    {"key": "author", "title": "Authors", "type": "categorical"},
+    {"key": "host", "title": "Host Species", "type": "categorical"},
+    {"key": "host_genus", "title": "Host Genus", "type": "categorical"},
+    {"key": "host_type", "title": "Host Type", "type": "categorical"}
+  ],
+  "geo_resolutions": [
+    "region",
+    "country"
+  ],
+  "maintainers": [
+    {"name": "Marcela Torres", "url": "https://github.com/NW-PaGe/WNV-nextstrain"},
+    {"name": "NW-PaGe", "url": "https://github.com/NW-PaGe/WNV-nextstrain"},
+    {"name": "Nextstrain Team", "url": "https://next.nextstrain.org/"}
+  ],
+  "filters": [
+    "region",
+    "country",
+    "division",
+    "author",
+    "host",
+    "host_genus",
+    "host_type"
+  ],
+  "display_defaults": {
+    "color_by": "region",
+    "map_triplicate": true,
+    "geo_resolution": "country",
+    "distance_measure": "div"
+  },
+  "metadata_columns": [
+    "accession",
+    "division",
+    "url"
+  ],
+  "extensions": {
+    "nextclade": {
+      "clade_node_attrs": [
+        {
+          "name": "lineage",
+          "displayName": "Pathoplexus lineage",
+          "description": "Global WNV lineages based on pathoplexus results."
+        }
+      ],
+      "pathogen": {
+        "schemaVersion":"3.0.0",
+        "defaultCds": "env",
+        "attributes": {
+          "name": "West Nile Virus Global Tree",
+          "reference name": "Reconstructed ancestor from global tree",
+          "reference accession": "none"
+        }
+      }
+    }
+  }
+}

phylogenetic/defaults/lineage-1A/config.yaml

@@ -0,0 +1,14 @@
+reference: "defaults/lineage-1A/reference.gb"
+root: "KX394399"
+builds: ['lineage-1A']
+
+subsampling:
+  region: --query "is_lab_host != 'true' & lineage == '1A'" --query-columns is_lab_host:str --min-length '8200' --group-by region year --subsample-max-sequences 3000 --exclude defaults/exclude.txt
+  force_include: --exclude-all --include defaults/lineage-1A/include.txt
+
+# Clock rate from Table 1 of May et al, 2010: https://pmc.ncbi.nlm.nih.gov/articles/PMC3067944/
+refine:
+  treetime_params: --coalescent opt --date-inference marginal --date-confidence --keep-polytomies --clock-rate 0.00106 --remove-outgroup
+
+export:
+  auspice_config: "defaults/lineage-1A/auspice_config.json"

phylogenetic/defaults/lineage-1A/include.txt

@@ -0,0 +1,66 @@
+KX394399 # Lineage 1B outgroup
+NC_009942 # Lineage 1 reference
+AF481864 # pre-NY
+MH166901 # NY99
+MH166903 # NY99
+MH166904 # NY99
+KX547395 # NY99
+KX547519 # NY99
+KX547602 # NY99
+HM488130 # NY99
+HM488132 # NY99
+HQ671707 # NY99
+AF202541 # NY99
+AF206518 # NY99
+HM488127 # NY99
+HM488126 # NY99
+KX547410 # WN02
+KJ501434 # WN02
+KX547456 # WN02
+KY216155 # WN02
+KX547460 # WN02
+MF175829 # WN02
+KX547482 # WN02
+MF175827 # WN02
+MF175839 # WN02
+KT020853 # WN02
+KX547548 # WN02
+MF175863 # WN02
+KX547286 # WN02
+MF175873 # WN02
+MF175865 # WN02
+MF175831 # WN02
+MF175858 # WN02
+KJ501117 # SW03
+KJ501120 # SW03
+MF175815 # SW03
+MG004533 # SW03
+KF704147 # SW03
+KF704153 # SW03
+KR348940 # SW03
+KR348937 # SW03
+KX547361 # SW03
+JX015523 # SW03
+KR348944 # SW03
+KJ501124 # SW03
+KX547552 # SW03
+KJ145829 # SW03
+KR348981 # SW03
+KJ501118 # SW03
+KR348938 # SW03
+KR348976 # SW03
+KJ501170 # SW03
+KR348993 # SW03
+JQ700438 # SW03
+KR348977 # SW03
+KR348942 # SW03
+KR348941 # SW03
+KJ501121 # SW03
+KJ501122 # SW03
+KX547375 # SW03
+KM012172 # SW03
+KC333375 # SW03
+KJ501222 # SW03
+MG004537 # SW03
+MF175866 # SW03
+MG004540 # SW03