Table 3.

Performance evaluation on the benchmark dataset. The current approach (DRIVE) is compared to the state-of-the-art model (CHASMplus) based on multiple performance metrics, both methodologies having been applied to the MutaGene computational framework. Overall, DRIVE outclassed CHASMplus, however, the limited size of the benchmark dataset has to be taken into consideration.

Model	Accuracy	Precision	Recall	F1-Score	AUC-ROC
DRIVE	0.852	0.843	0.866	0.854	0.919
CHASMplus	0.743	0.672	0.952	0.788	0.872