Table 3.

Performance of Bayesian and recursive partitioning models on the test set.

Model	TP	FN	FP	TN	SE	SP	MCC	Q+	Q−
NB-a	426	7	68	2018	0.985	0.967	0.904	0.862	0.997
NB-b	425	8	27	2059	0.981	0.987	0.952	0.941	0.996
NB-c	346	62	356	1756	0.849	0.832	0.559	0.493	0.966
NB-d	389	19	40	2071	0.954	0.981	0.917	0.907	0.991
RP-a	426	8	31	2055	0.983	0.985	0.948	0.932	0.996
RP-b	427	6	29	2057	0.987	0.986	0.953	0.936	0.997
RP-c	379	54	81	2005	0.875	0.961	0.817	0.824	0.974
RP-d	401	33	35	2051	0.925	0.983	0.906	0.920	0.984

Note: NB-a: NB model with MOE 2D descriptors; NB-b: NB model with MOE 2D descriptors + ECFP_6; NB-c: NB model with DS 2D descriptors; NB-d: NB model with DS 2D descriptors + ECFP_6; RP-a: RP model with MOE 2D descriptors; RP-b: RP model with MOE 2D descriptors + ECFP_6; RP-c: RP model with DS 2D descriptors; RP-d: RP model with DS 2D descriptors + ECFP_6.