updated script to combine dfs

scripts/or_kinship_link.py

@@ -261,6 +261,20 @@ else:
     sys.exit()
     
 del(df_ncols, ncols_add)
+
+#%% now adding mutation style = <gene>_p.abc1cde 
+dfm2_mis['mutation'] = gene.lower() + '_' + dfm2_mis['mut_info_f2'].astype(str)
+# convert to lowercase
+dfm2_mis['mutation'] = dfm2_mis['mutation'].str.lower()
+
+# quick sanity check
+check = dfm2_mis['mutation'].value_counts().value_counts() == dfm2_mis['mut_info_f2'].value_counts().value_counts()
+
+if check.all():
+    print('PASS: added column "mutation" containing mutation format: <gene>_p.abc1cde')
+else:
+    print('FAIL: could not add "mutation" column!')
+    sys.exit()
 #%% Calculating OR from beta coeff
 print('Calculating OR...')
 df_ncols = dfm2_mis.shape[1]
@@ -364,7 +378,7 @@ print('Reordering', dfm2_mis.shape[1], 'columns'
 
 #dfm2_mis.columns
 
-column_order = [#'mutation',
+column_order = ['mutation',
  'mutationinformation', 
  'wild_type', 
  'position',