feat: stable

data_loader.py

 
                 df = (df - df.min()) / (df.max() - df.min())
                 df = df.fillna(0)
-
-                print("has null:")
-                print(df.isnull().sum().sum())
                 if intersect:
                     if file.startswith('cell'):
                         if cell_line_names:

evaluation.py

 
         # Step 2: Calculate and print AUC
         fpr, tpr, thresholds = metrics.roc_curve(all_targets, mlp_output)
-        auc = np.round(metrics.auc(fpr, tpr), 3)
+        auc = np.round(metrics.auc(fpr, tpr), 4)
 
         # Step 3: Calculate and print AUPRC
         precision, recall, thresholds = metrics.precision_recall_curve(all_targets, mlp_output)
-        auprc = np.round(metrics.auc(recall, precision), 3)
+        auprc = np.round(metrics.auc(recall, precision), 4)
 
         # Step 4: Print accuracy, AUC, AUPRC, and confusion matrix
         accuracy = accuracy_score(all_targets, all_predictions)
         precision = cm[0, 0] / (cm[0, 0] + cm[0, 1])
         recall = cm[0, 0] / (cm[0, 0] + cm[1, 0])
         f1_score = 2 * precision * recall / (precision + recall)
-        print(f'Accuracy: {accuracy:.2f}')
-        print(f'AUC: {auc:.2f}')
-        print(f'AUPRC: {auprc:.2f}')
+
         print(f'Confusion matrix:\n{cm}')
-        print(f'Precision: {precision:.3f}, Recall: {recall:.3f}, F1 score: {f1_score:.3f}')
+        print(
+            f'Accuracy: {accuracy:.3f}, Precision: {precision:.3f}, Recall: {recall:.3f}, F1 score: {f1_score:.3f}, AUC: {auc:.3f}, ,AUPRC: {auprc:.3f}')
 
         # Step 5: Display ROC and PR curves if requested
         if show_plot:

main.py

 
     # Step 2: Load training data
     train_data, train_drug_screen = RawDataLoader.load_data(data_modalities=DATA_MODALITIES,
-                                                            raw_file_directory=GDSC_RAW_DATA_FOLDER,
-                                                            screen_file_directory=GDSC_SCREENING_DATA_FOLDER,
+                                                            raw_file_directory=RAW_BOTH_DATA_FOLDER,
+                                                            screen_file_directory=BOTH_SCREENING_DATA_FOLDER,
                                                             sep="\t")
 
 

utils.py

 SAVE_MODEL = False  # Change it to True to save the trained model
 VARIATIONAL_AUTOENCODERS = False
 # DATA_MODALITIES=['cell_CN','cell_exp','cell_methy','cell_mut','drug_comp','drug_DT'] # Change this list to only consider specific data modalities
-DATA_MODALITIES = ['cell_exp', 'drug_desc']
+DATA_MODALITIES = ['cell_CN','cell_exp','cell_mut', 'drug_desc','drug_finger']
 RANDOM_SEED = 42  # Must be used wherever can be used