Table 4.

Correlation coefficient between predicted and actual AUCs (correlation), and normalized mean square error (NMSE) for predicting AUC of our best single predictor, the RF GE, and linear stacking of five individual predictive models that appear in bold in Table 2

	Correlation	NMSE
RF GE	0.7276	0.791
RF GE + KNN Residual	0.7550	0.7225
Linear Stacking Ensemble	0.7746	0.6705