ingest: Create new accession field without version

Resolves #39

Create a new accession field without the version number so that
annotations do not need to be updated when the version number is updated.

ingest/defaults/config.yaml

@@ -46,6 +46,7 @@ curate:
   # This is the first step in the pipeline, so any references to field names in the configs below should use the new field names
   field_map:
     accession: accession
+    accession_version: accession_version
     sourcedb: database
     sra-accs: sra_accessions
     isolate-lineage: strain
@@ -100,6 +101,7 @@ curate:
   # The list of metadata columns to keep in the final output of the curation pipeline.
   metadata_columns: [
     "accession",
+    "accession_version",
     "strain",
     "date",
     "region",

ingest/rules/fetch_from_ncbi.smk

@@ -97,6 +97,9 @@ rule format_ncbi_dataset_report:
             --fields {params.ncbi_datasets_fields:q} \
             --elide-header \
             | csvtk add-header -t -l -n {params.ncbi_datasets_fields:q} \
+            | csvtk rename -t -f accession -n accession_version \
+            | csvtk -tl mutate -f accession_version -n accession -p "^(.+?)\." \
+            | tsv-select -H -f accession --rest last \
             > {output.ncbi_dataset_tsv}
         """
 
@@ -120,7 +123,7 @@ rule format_ncbi_datasets_ndjson:
         augur curate passthru \
             --metadata {input.ncbi_dataset_tsv} \
             --fasta {input.ncbi_dataset_sequences} \
-            --seq-id-column accession \
+            --seq-id-column accession_version \
             --seq-field sequence \
             --unmatched-reporting warn \
             --duplicate-reporting warn \