diff --git a/prosit_data_merge.py b/prosit_data_merge.py
index 7a612c7931579b6044fce06bbfff5c8076383588..02b48fdf56b4233426b8fee6db1280fe8337a3b2 100644
--- a/prosit_data_merge.py
+++ b/prosit_data_merge.py
@@ -151,10 +151,12 @@ print(len(df))
 possible_charges = [1,2,3,4]
 df = df[df['Charge'].isin(possible_charges)]
 print(len(df))
+df.to_pickle('database/data_prosit_merged_holdout.pkl')
 df = pd.read_pickle('database/data_prosit_merged_train.pkl')
 print(len(df))
 df=df.loc[df['Retention time']!=0]
 df = df[df['Charge'].isin(possible_charges)]
 print(len(df))
+df.to_pickle('database/data_prosit_merged_train.pkl')