Fixes for Andersen lab

ingest/build-configs/ncbi/bin/curate-andersen-lab-data

@@ -54,7 +54,7 @@ def create_new_record(anderson_record: dict) -> dict:
     new_record['originating_lab'] = center_name
     new_record['submitting_lab'] = center_name
 
-    new_record['strain'] = f'A/{anderson_record["Host"]}/{new_record["country"]}/{anderson_record["isolate"]}/{parse_year(new_record["date"])}'
+    new_record['strain'] = construct_strain_name(new_record, anderson_record['isolate'])
     return new_record
 
 
@@ -78,6 +78,20 @@ def parse_center_name(center_name: str) -> str:
     return center_name
 
 
+def construct_strain_name(record: dict, sample_id: str) -> str:
+    """
+    Construct a strain name for the *sample_id* using metadata from the *record*
+    to include host, country, and year.
+
+    Removes all spaces in the constructed strain name because they are not
+    allowed in the downstream phylogenetic workflow.
+    """
+    host = record['host']
+    country = record['country']
+    year = parse_year(record['date'])
+    return f"A/{host}/{country}/{sample_id}/{year}".replace(" ", "")
+
+
 def parse_year(date_string: str) -> str:
     """
     Parse the year from the provided `date_string`

ingest/build-configs/ncbi/defaults/config.yaml

@@ -139,4 +139,4 @@ join_ncbi_andersen:
   match_field: sra_accessions
   source_column_name: data_source
   ncbi_source: genbank
-  andersen_source: andersen-lab
+  andersen_source: sra-via-andersen-lab