Table 6.

Provides the overall performance measures for the models generated using biological, chemical, and phenotypic features and the combination of the two and three levels of features on non-redundant testing dataset using under sampling of majority class

Type of feature	RF						SMO
	ACC	Precision	Recall	F-score	AUC	PRC	ACC	Precision	Recall	F-score	AUC	PRC
Biological	93.90	0.88	0.91	0.89	0.46	0.94	92.15	0.88	0.91	0.89	0.45	0.94
Chemical	93.32	0.85	0.88	0.87	0.48	0.94	93.69	0.85	0.89	0.87	0.44	0.93
Phenotypic	93.65	0.85	0.88	0.87	0.44	0.93	93.85	0.85	0.89	0.87	0.44	0.93
Biological + chemical	93.07	0.85	0.88	0.86	0.46	0.94	93.72	0.85	0.89	0.87	0.44	0.93
Biological + phenotypic	93.51	0.85	0.88	0.87	0.43	0.93	93.82	0.85	0.89	0.87	0.44	0.93
Chemical + phenotypic	93.43	0.85	0.88	0.87	0.45	0.94	93.83	0.85	0.89	0.87	0.44	0.93
Biological + chemical + phenotypic	93.06	0.85	0.88	0.86	0.47	0.94	93.61	0.85	0.89	0.87	0.44	0.93