remove potential duplicate rows from table

directlfq/lfq_manager.py

@@ -50,6 +50,7 @@ def run_lfq(input_file, columns_to_add = [], selected_proteins_file :str = None
  input_df = lfqutils.sort_input_df_by_protein_id(input_df)
  input_df = lfqutils.index_and_log_transform_input_df(input_df)
  input_df = lfqutils.remove_allnan_rows_input_df(input_df)
+ input_df = lfqutils.remove_potential_quant_id_duplicates(input_df)
 
  if not deactivate_normalization:
  LOGGER.info("Performing sample normalization.")

directlfq/utils.py

@@ -310,6 +310,15 @@ def index_and_log_transform_input_df(data_df):
 def remove_allnan_rows_input_df(data_df):
  return data_df.dropna(axis = 0, how = 'all')
 
+def remove_potential_quant_id_duplicates(data_df):
+ before_drop = len(data_df)
+ data_df = data_df.drop_duplicates(subset=config.QUANT_ID, keep='first')
+ after_drop = len(data_df)
+ if before_drop != after_drop:
+ entries_removed = before_drop - after_drop
+ LOGGER.info(f"Duplicate quant_ids detected. {entries_removed} rows removed from input df.")
+
+
 def sort_input_df_by_protein_id(data_df):
  return data_df.sort_values(by = config.PROTEIN_ID,ignore_index=True)