Merge pull request #9 from nextstrain/testing_strain_name

Changing json names to show strain name.

phylogenetic/defaults/exclude.txt

@@ -0,0 +1,20 @@
+AY993909    #duplicated
+AY993910    #duplicated
+AY993911    #duplicated
+AF164532    #duplicated
+AY993909    #duplicated
+AY993910    #duplicated
+AY993911    #duplicated
+AY117135    #duplicated
+HM470140    #duplicated
+AY704563    #duplicated
+AY704568    #duplicated
+AY704566    #duplicated
+PP952117    #duplicated
+EF467371    #duplicated
+EF467372    #duplicated
+EF467370    #   duplicated
+EF467369    #   duplicated
+AF164531    #   duplicated
+NC_005775   #   duplicated
+AF441119    #   duplicated

phylogenetic/rules/export.smk

@@ -53,7 +53,7 @@ rule export:
         # description = config['export']['description'],
         auspice_config = config['export']['auspice_config'],
     output:
-        auspice ="auspice/oropouche_{segment}.json",
+        auspice ="results/{segment}/oropouche.json",
     params:
         strain_id_field = config["strain_id_field"],
     shell:
@@ -69,21 +69,21 @@ rule export:
             --include-root-sequence-inline
         """
 
-# rule final_strain_name:
-#     input:
-#         auspice_json="results/{segment}/oropouche.json",
-#         metadata="data/{segment}/metadata.tsv",
-#     output:
-#         auspice_json="auspice/oropouche_{segment}.json",
-#     params:
-#         strain_id_field=config["strain_id_field"],
-#         display_strain_field=config["display_strain_field"],
-#     shell:
-#         """
-#         python3 scripts/set_final_strain_name.py \
-#             --metadata {input.metadata} \
-#             --metadata-id-columns {params.strain_id_field} \
-#             --input-auspice-json {input.auspice_json} \
-#             --display-strain-name {params.display_strain_field} \
-#             --output {output.auspice_json}
-#         """
+rule final_strain_name:
+    input:
+        auspice_json="results/{segment}/oropouche.json",
+        metadata="data/{segment}/metadata.tsv",
+    output:
+        auspice_json="auspice/oropouche_{segment}.json",
+    params:
+        strain_id_field=config["strain_id_field"],
+        display_strain_field=config["display_strain_field"],
+    shell:
+        """
+        python3 scripts/set_final_strain_name.py \
+            --metadata {input.metadata} \
+            --metadata-id-columns {params.strain_id_field} \
+            --input-auspice-json {input.auspice_json} \
+            --display-strain-name {params.display_strain_field} \
+            --output {output.auspice_json}
+        """

phylogenetic/scripts/set_final_strain_name.py

@@ -0,0 +1,48 @@
+import pandas as pd
+import json
+import argparse
+from augur.io import read_metadata
+
+def replace_name_recursive(node, lookup, saveoldcolumn):
+    if node["name"] in lookup:
+        if saveoldcolumn == "accession":
+            node["node_attrs"][saveoldcolumn] = node["name"]
+        elif saveoldcolumn == "genbank_accession":
+            node["node_attrs"][saveoldcolumn] = {}
+            node["node_attrs"][saveoldcolumn]["value"] = node["name"]
+        else:
+            node["node_attrs"][saveoldcolumn] = node["name"]
+
+    if node["name"] in lookup:
+        node["name"] = lookup[node["name"]]
+
+    if "children" in node:
+        for child in node["children"]:
+            replace_name_recursive(child, lookup, saveoldcolumn)
+
+if __name__=="__main__":
+    parser = argparse.ArgumentParser(
+        description="Swaps out the strain names in the Auspice JSON with the final strain name",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+
+    parser.add_argument('--input-auspice-json', type=str, required=True, help="input auspice_json")
+    parser.add_argument('--metadata', type=str, required=True, help="input data")
+    parser.add_argument('--metadata-id-columns', nargs="+", help="names of possible metadata columns containing identifier information, ordered by priority. Only one ID column will be inferred.")
+    parser.add_argument('--display-strain-name', type=str, required=True, help="field to use as strain name in auspice")
+    parser.add_argument('--output', type=str, metavar="JSON", required=True, help="output Auspice JSON")
+    args = parser.parse_args()
+
+    metadata = read_metadata(args.metadata, id_columns=args.metadata_id_columns)
+    name_lookup = {}
+    for ri, row in metadata.iterrows():
+        strain_id = row.name
+        name_lookup[strain_id] = args.display_strain_name if pd.isna(row[args.display_strain_name]) else row[args.display_strain_name]
+
+    with open(args.input_auspice_json, 'r') as fh:
+        data = json.load(fh)
+
+    replace_name_recursive(data['tree'], name_lookup, "genbank_accession")
+
+    with open(args.output, 'w') as fh:
+        json.dump(data, fh)