From 28ad84d17367bf4b858e2c78ebf9d2c34a05c071 Mon Sep 17 00:00:00 2001 From: miseminger Date: Mon, 29 Jul 2024 23:03:19 -0700 Subject: [PATCH] merge dfs on 'protein symbol' instead --- bin/functional_annotation.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bin/functional_annotation.py b/bin/functional_annotation.py index 93e88b0..56ea82b 100755 --- a/bin/functional_annotation.py +++ b/bin/functional_annotation.py @@ -263,7 +263,7 @@ def write_tsv(dframe): index_cols_to_use = ['nucleotide position', 'nucleotide mutation', 'amino acid mutation', 'amino acid mutation alias', 'protein name', 'protein symbol', 'gene name'] dataFrame = dataFrame.drop(columns=index_cols_to_use) - merged_dataFrame = pd.merge(dataFrame, mutation_index, on=['original mutation description', 'gene symbol'], how='left') #, 'alias' + merged_dataFrame = pd.merge(dataFrame, mutation_index, on=['original mutation description', 'protein symbol'], how='left') #, 'alias' #dups = mutation_index[mutation_index.duplicated(subset=['nucleotide position', 'original mutation description'], keep=False)] #dups = dups.sort_values(by='nucleotide position') #dups.to_csv('madeline_testing/dups.tsv', sep='\t', index=False)