From 59d3f4b6a091d32c8109973e6301537382d9d755 Mon Sep 17 00:00:00 2001 From: Jennifer Chang Date: Wed, 1 Nov 2023 17:07:32 -0700 Subject: [PATCH] Move the ncbi field map to config (#219) To be consistent with the nextclade-field-map.tsv, move the ncbi-field-map.tsv to config. --- ingest/config/config.yaml | 2 ++ ingest/workflow/snakemake_rules/fetch_sequences.smk | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/ingest/config/config.yaml b/ingest/config/config.yaml index eaa067a0..8d18c5f0 100644 --- a/ingest/config/config.yaml +++ b/ingest/config/config.yaml @@ -2,6 +2,8 @@ sources: ['genbank'] # Pathogen NCBI Taxonomy ID ncbi_taxon_id: '10244' +# Renames the NCBI dataset headers +ncbi_field_map: 'source-data/ncbi-dataset-field-map.tsv' # Params for the transform rule transform: diff --git a/ingest/workflow/snakemake_rules/fetch_sequences.smk b/ingest/workflow/snakemake_rules/fetch_sequences.smk index b8411801..3f32f9b4 100644 --- a/ingest/workflow/snakemake_rules/fetch_sequences.smk +++ b/ingest/workflow/snakemake_rules/fetch_sequences.smk @@ -80,7 +80,7 @@ rule format_ncbi_dataset_report: # The only fields we do not have equivalents for are "title" and "publications" input: dataset_package="data/ncbi_dataset.zip", - ncbi_field_map="source-data/ncbi-dataset-field-map.tsv", + ncbi_field_map=config["ncbi_field_map"], output: ncbi_dataset_tsv=temp("data/ncbi_dataset_report.tsv"), params: