Update arguments to augur clades

This updates the workflow to use the new clades interface from augur
v22.0.1 (see nextstrain/augur#728). In the process we can remove two
rules from the workflow.

If this workflow is run with augur prior to v22, the emerging_lineages
rule  will error due to unknown arguments.

The script add_branch_labels.py is no longer used, but not removed here,
as it contains logic to export spike mutations as branch labels
which may be useful at some point. If we do use this, it would be better
to produce an intermediate node-data JSON with a custom branch label
to avoid modifying the auspice JSON after export.

docs/src/reference/change_log.md

@@ -5,6 +5,10 @@ We also use this change log to document new features that maintain backward comp
 
 ## New features since last version update
 
+## v13 (16 May 2022)
+
+- 16 May 2023: Update workflow to support [Augur v22](https://github.com/nextstrain/augur/releases/tag/22.0.0) which updates the `augur clades` interface and structure of the output files to allow specifying the clade label & coloring keys. Because we use custom scripts to parse these files this worflow also needed updating. This change results in a simplifying of the nCoV pipeline (PR [1000](https://github.com/nextstrain/ncov/pull/1000)).
+
 - 11 April 2023: Elevate XBB.1.16 as new clade 23B. See [PR 1059](https://github.com/nextstrain/ncov/pull/1059) for the rationale behind this clade update.
 
 - 6 April 2023: Update conda environment dependencies: augur 19.2.0 -> 21.1.0, nextalign/nextclade 2.9.1 -> 2.13.1, iqtree 2.2.0_beta -> 2.2.0.3. [PR 1056](https://github.com/nextstrain/ncov/pull/1056)

workflow/envs/nextstrain.yaml

@@ -4,7 +4,7 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - augur=21.1.0
+  - augur=22.0.1
   - epiweeks=2.1.2
   - iqtree=2.2.0.3
   - nextalign=2.13.1

workflow/snakemake_rules/main_workflow.smk

@@ -1075,7 +1075,7 @@ rule emerging_lineages:
         emerging_lineages = config["files"]["emerging_lineages"],
         clades = config["files"]["clades"]
     output:
-        clade_data = "results/{build_name}/temp_emerging_lineages.json"
+        clade_data = "results/{build_name}/emerging_lineages.json"
     log:
         "logs/emerging_lineages_{build_name}.txt"
     benchmark:
@@ -1089,27 +1089,11 @@ rule emerging_lineages:
         augur clades --tree {input.tree} \
             --mutations {input.nuc_muts} {input.aa_muts} \
             --clades {input.emerging_lineages} \
+            --membership-name emerging_lineage \
+            --label-name emerging_lineage \
             --output-node-data {output.clade_data} 2>&1 | tee {log}
         """
 
-rule rename_emerging_lineages:
-    input:
-        node_data = rules.emerging_lineages.output.clade_data
-    output:
-        clade_data = "results/{build_name}/emerging_lineages.json"
-    benchmark:
-        "benchmarks/rename_emerging_lineages_{build_name}.txt"
-    run:
-        import json
-        with open(input.node_data, 'r', encoding='utf-8') as fh:
-            d = json.load(fh)
-            new_data = {}
-            for k,v in d['nodes'].items():
-                if "clade_membership" in v:
-                    new_data[k] = {"emerging_lineage": v["clade_membership"]}
-        with open(output.clade_data, "w") as fh:
-            json.dump({"nodes": new_data}, fh, indent=2)
-
 rule colors:
     message: "Constructing colors file"
     input:
@@ -1366,7 +1350,7 @@ def _get_node_data_by_wildcards(wildcards):
         rules.refine.output.node_data,
         rules.ancestral.output.node_data,
         rules.translate.output.node_data,
-        rules.rename_emerging_lineages.output.clade_data,
+        rules.emerging_lineages.output.clade_data,
         rules.clades.output.clade_data,
         rules.recency.output.node_data,
         rules.traits.output.node_data,
@@ -1462,28 +1446,10 @@ rule export:
             --output {output.auspice_json} 2>&1 | tee {log}
         """
 
-rule add_branch_labels:
-    message: "Adding custom branch labels to the Auspice JSON"
-    input:
-        auspice_json = rules.export.output.auspice_json,
-        emerging_clades = rules.emerging_lineages.output.clade_data
-    output:
-        auspice_json = "results/{build_name}/ncov_with_branch_labels.json"
-    log:
-        "logs/add_branch_labels{build_name}.txt"
-    conda: config["conda_environment"]
-    shell:
-        """
-        python3 ./scripts/add_branch_labels.py \
-            --input {input.auspice_json} \
-            --emerging-clades {input.emerging_clades} \
-            --output {output.auspice_json}
-        """
-
 rule include_hcov19_prefix:
     message: "Rename strains to include hCoV-19/ prefix"
     input:
-        auspice_json = rules.add_branch_labels.output.auspice_json,
+        auspice_json = rules.export.output.auspice_json,
         tip_frequencies = rules.tip_frequencies.output.tip_frequencies_json
     output:
         auspice_json = "results/{build_name}/ncov_with_hcov19_prefix.json",