diff --git a/scripts/data_extraction.py b/scripts/data_extraction.py
index aac7cdb..b991490 100755
--- a/scripts/data_extraction.py
+++ b/scripts/data_extraction.py
@@ -572,7 +572,8 @@ print ('Firstly, applying tidy split on dr muts df', meta_gene_dr.shape
 # apply tidy_split()
 dr_WF0 = tidy_split(meta_gene_dr, col_to_split1, sep = ';') 
 # remove leading white space else these are counted as distinct mutations as well
-dr_WF0[dr_muts_col] = dr_WF0[dr_muts_col].str.lstrip() 
+#dr_WF0[dr_muts_col] = dr_WF0[dr_muts_col].str.lstrip() 
+dr_WF0[dr_muts_col] = dr_WF0[dr_muts_col].str.strip() 
 
 # extract only the samples/rows with nssnp_match
 #dr_gene_WF0 = dr_WF0.loc[dr_WF0[dr_muts_col].str.contains(gene_match)]