diff --git a/genie/database_to_staging.py b/genie/database_to_staging.py index 4c1d3576..f249cba3 100644 --- a/genie/database_to_staging.py +++ b/genie/database_to_staging.py @@ -686,7 +686,7 @@ def filter_out_germline_variants( input_data: pd.DataFrame, status_col_str: str ) -> pd.DataFrame: """Filters out germline variants given a status col str. Genie pipeline - cannot have any of these variants. NOTE: We have to search for the + cannot have any of these variants. NOTE: We have to search for the status column because there's no column name validation in the release steps so the status column may have different casing. diff --git a/tests/test_database_to_staging.py b/tests/test_database_to_staging.py index f1c22f7c..e7c1f731 100644 --- a/tests/test_database_to_staging.py +++ b/tests/test_database_to_staging.py @@ -142,12 +142,12 @@ def test_store_assay_info_files(syn): ), ( pd.DataFrame( - dict(SV_Status=["GERMLINE", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"]) + dict( + SV_Status=["GERMLINE", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"] + ) ), "SV_STATUS", - pd.DataFrame( - dict(SV_Status=["SOMATIC"], Sample_ID=["GENIE-2"]) - ), + pd.DataFrame(dict(SV_Status=["SOMATIC"], Sample_ID=["GENIE-2"])), ), ], ids=["all_germline", "some_germline", "no_germline", "diff_status_col_case"],