Merge pull request #20 from nextstrain/assign-Troupin-clades

Assign clades using Troupin et al definitions
nextstrain · Jan 13, 2025 · 219e638 · 219e638
2 parents 01f492a + 9133653
commit 219e638
Show file tree

Hide file tree

Showing 6 changed files with 80 additions and 1 deletion.
diff --git a/phylogenetic/defaults/auspice_config.json b/phylogenetic/defaults/auspice_config.json
@@ -46,6 +46,11 @@
       "key": "host_common_name",
       "title": "Host common name",
       "type": "categorical"
+    },
+    {
+      "key": "clade_membership",
+      "title": "Clade",
+      "type": "categorical"
     }
   ],
   "geo_resolutions": [

diff --git a/phylogenetic/defaults/clades.tsv b/phylogenetic/defaults/clades.tsv
@@ -0,0 +1,51 @@
+clade	gene	site	alt
+Africa-2	nuc	499	G
+Africa-2	nuc	708	A
+Africa-2	nuc	3746	G
+Africa-2	nuc	3914	A
+Africa-2	nuc	4440	C
+Africa-2	nuc	4628	G
+Africa-2	nuc	4844	A
+Africa-3	nuc	332	A
+Africa-3	nuc	392	A
+Africa-3	nuc	821	T
+Africa-3	nuc	1209	T
+Africa-3	nuc	1258	G
+Africa-3	nuc	4473	T
+Africa-3	nuc	4940	A
+Arctic-related	nuc	248	T
+Arctic-related	nuc	1030	G
+Arctic-related	nuc	1036	A
+Arctic-related	nuc	3363	A
+Arctic-related	nuc	3494	T
+Arctic-related	nuc	3657	C
+Arctic-related	nuc	4775	C
+Asian	nuc	1471	A
+Asian	nuc	8234	C
+Asian	nuc	8837	G
+Asian	nuc	9038	G
+Asian	nuc	9113	G
+Asian	nuc	9773	T
+Asian	nuc	9965	T
+Asian	nuc	10773	A
+Bat	nuc	331	T
+Bat	nuc	413	A
+Bat	nuc	1879	C
+Bat	nuc	2449	C
+Bat	nuc	2594	A
+Bat	nuc	2955	G
+Bat	nuc	5083	T
+Bat	nuc	11189	T
+Cosmopolitan	nuc	781	A
+Cosmopolitan	nuc	1057	T
+Cosmopolitan	nuc	1470	A
+Cosmopolitan	nuc	3998	C
+Cosmopolitan	nuc	4697	A
+Cosmopolitan	nuc	4949	T
+Indian Subcontinent	nuc	1207	T
+Indian Subcontinent	nuc	3548	C
+Indian Subcontinent	nuc	5054	G
+RAC-SK	nuc	574	T
+RAC-SK	nuc	844	T
+RAC-SK	nuc	1207	C
+RAC-SK	nuc	3924	G
diff --git a/phylogenetic/defaults/config.yaml b/phylogenetic/defaults/config.yaml
@@ -5,6 +5,7 @@ files:
     colors: "defaults/colors.tsv"
     auspice_config: "defaults/auspice_config.json"
     description: "defaults/description.md"
+    clades: "defaults/clades.tsv"
 filter:
     group_by: "country year"
     sequences_per_group: 20

diff --git a/phylogenetic/defaults/description.md b/phylogenetic/defaults/description.md
@@ -12,6 +12,10 @@ We curate sequence data and metadata from NCBI as starting point for our analyse
 - [data.nextstrain.org/files/workflows/rabies/sequences.fasta.zst](https://data.nextstrain.org/files/workflows/rabies/sequences.fasta.zst)
 - [data.nextstrain.org/files/workflows/rabies/metadata.tsv.zst](https://data.nextstrain.org/files/workflows/rabies/metadata.tsv.zst)
 
+#### Clade annotation
+
+Clades are defined based on the "major clades" in [Troupin et al. 2016](https://journals.plos.org/plospathogens/article?id=10.1371/journal.ppat.1006041).
+
 ---
 
 Screenshots may be used under a [CC-BY-4.0 license](https://creativecommons.org/licenses/by/4.0/) and attribution to nextstrain.org must be provided.
diff --git a/phylogenetic/rules/annotate_phylogeny.smk b/phylogenetic/rules/annotate_phylogeny.smk
@@ -52,6 +52,23 @@ rule translate:
             2>&1 | tee {log}
         """
 
+rule clades:
+    input:
+        tree = "results/tree.nwk",
+        nt_muts = "results/nt_muts.json",
+        aa_muts = "results/aa_muts.json",
+        clade_defs = config["files"]["clades"]
+    output:
+        clades = "results/clades.json"
+    shell:
+        """
+        augur clades \
+            --tree {input.tree} \
+            --mutations {input.nt_muts} {input.aa_muts} \
+            --clades {input.clade_defs} \
+            --output {output.clades}
+        """
+
 rule add_year_metadata:
     input:
         metadata = "data/metadata.tsv",

diff --git a/phylogenetic/rules/export.smk b/phylogenetic/rules/export.smk
@@ -13,6 +13,7 @@ rule export:
         branch_lengths = "results/branch_lengths.json",
         nt_muts = "results/nt_muts.json",
         aa_muts = "results/aa_muts.json",
+        clades = "results/clades.json",
         year = "results/year.json",
         colors = config["files"]["colors"],
         auspice_config = config["files"]["auspice_config"],
@@ -31,7 +32,7 @@ rule export:
             --tree {input.tree} \
             --metadata {input.metadata} \
             --metadata-id-columns {params.strain_id} \
-            --node-data {input.branch_lengths} {input.nt_muts} {input.aa_muts} {input.year} \
+            --node-data {input.branch_lengths} {input.nt_muts} {input.aa_muts} {input.year} {input.clades} \
             --colors {input.colors} \
             --auspice-config {input.auspice_config} \
             --include-root-sequence-inline \