diff --git a/Compared_ML_algorithms/Decision_tree_NCI-60.py b/Compared_ML_algorithms/Decision_tree_NCI-60.py
index cc893af..c2b3236 100644
--- a/Compared_ML_algorithms/Decision_tree_NCI-60.py
+++ b/Compared_ML_algorithms/Decision_tree_NCI-60.py
@@ -13,7 +13,6 @@
 import matplotlib.pyplot as plt
 from imblearn.over_sampling import SMOTE
 from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import classification_report, matthews_corrcoef
 from sklearn.metrics import f1_score, accuracy_score, precision_score, recall_score, roc_auc_score, roc_curve
@@ -127,7 +126,7 @@ def smiles_to_onehot(smiles, character_maximum, dist_char):
     smiles_to_onehot, character_maximum=largest_smiles_len, dist_char=dist_char
 )
 
-#SMOTE oversampling, train_test_split and normalization
+#SMOTE oversampling, train-test split
 X = df[['dist_char_ohe','Activity']]
 X.columns = ['feature_N' + str(i + 1) for i in range(X.shape[1])]
 x = X['feature_N1'].explode().to_frame()
@@ -146,14 +145,6 @@ def smiles_to_onehot(smiles, character_maximum, dist_char):
 X_over, y_over = smote.fit_resample(X1, y1)
 X_train2, X_test2, Y_train2, Y_test2 = train_test_split(X_over, y_over, random_state=42)
 
-#Normalization
-scaler = StandardScaler()
-scaler.fit(X_train2)
-X_train2 = scaler.transform(X_train2)
-scaler.fit(X_test2)
-X_test2 = scaler.transform(X_test2)
-
-
 #Implementing Decision Tree algorithm
 
 dt = DecisionTreeClassifier(criterion='entropy', max_depth=20, min_samples_leaf=5,random_state=42)