Table 2. Results for AChE Dataset (Model Dataset 2) with Best Weighting (0.5–0–0.5) Combination as Obtained from the Retrospective Study.

model	division method	R2	Q2	MAE95%Train	QExt-F12	MAE95%Test	correct prediction in %	training set range	number of compounds outside ADa
1	sorted responseb	0.68	0.65	0.49	0.58	0.55	87.32	7.82	10 (13, 336–338, 340, 342–344, 347, 360)
2		0.67	0.64	0.49	0.61	0.52	85.92		5 (242–244, 323, 360)
3		0.64	0.60	0.46	0.52	0.53	86.62		11 (32, 33, 35, 336–338, 340, 342–344, 347)
4		0.52	0.47	0.48	0.56	0.52	85.21		15 (32, 33, 242–244, 323, 336–338, 340, 342–344, 347, 368)
5		0.64	0.60	0.46	0.53	0.55	86.62		14 (32, 33, 35, 174, 218, 323, 336–338, 340, 342–344, 347)
6	Kennard–Stonec	0.71	0.69	0.49	0.48	0.58	84.38	7.82	1 (201)
7		0.69	0.67	0.51	0.48	0.58	91.41		1 (201)
8		0.74	0.71	0.47	0.53	0.56	91.41		1 (1)
9		0.69	0.67	0.51	0.50	0.59	85.94		1 (1)
10		0.70	0.68	0.48	0.53	0.57	88.26		0
11	modified-k-medoidsd	0.68	0.65	0.48	0.63	0.51	86.62	7.76	8 (177–179, 203, 219, 246, 310, 311)
12		0.68	0.65	0.49	0.61	0.52	87.32		8 (177–179, 203, 219, 246, 310, 311)
13		0.66	0.63	0.49	0.60	0.53	85.92		7 (177–179, 203, 219, 310, 311)
14		0.67	0.65	0.50	0.55	0.58	85.21		8 (177–179, 203, 219, 246, 310, 311)
15		0.65	0.62	0.50	0.58	0.56	87.32		1 (246)

^aAD using standardization technique is used and compound ID mentioned under parenthesis.

^bN_Training = 284, N_Test = 142.

^cN_Training = 284, N_Test = 142.

^dN_Training = 284, N_Test = 142.