A statistical framework to evaluate virtual screening

BMC Bioinformatics

Table 1 Comparisons of the "earliness" of different metrics to detect early recognitions for different number of actives (n = 5, 10, 20, 100).

Metric 1	Metric 2	10%	20%	30%	40%	50%	60%	70%	80%	90%	100%
n = 5
pROC	AU-ROC	0.80	0.80	0.70	0.70	0.70	0.56	0.42	0.42	0.42	0.32
BEDROC	AU-ROC	0.86	0.86	0.72	0.72	0.72	0.46	0.28	0.28	0.28	0.18
SLR	AU-ROC	0.79	0.79	0.72	0.72	0.72	0.58	0.43	0.43	0.43	0.32
SLR	pROC	0.52	0.52	0.52	0.52	0.52	0.52	0.51	0.51	0.51	0.52
SLR	BEDROC	0.44	0.44	0.47	0.47	0.47	0.61	0.66	0.66	0.66	0.67
pROC	BEDROC	0.46	0.46	0.48	0.48	0.48	0.60	0.65	0.65	0.65	0.67
n = 10
pROC	AU-ROC	0.78	0.77	0.73	0.67	0.61	0.52	0.46	0.40	0.35	0.32
BEDROC	AU-ROC	0.81	0.87	0.76	0.62	0.49	0.38	0.30	0.23	0.20	0.18
SLR	AU-ROC	0.76	0.76	0.73	0.67	0.61	0.54	0.47	0.41	0.36	0.33
SLR	pROC	0.54	0.52	0.54	0.54	0.55	0.54	0.54	0.54	0.54	0.54
SLR	BEDROC	0.50	0.35	0.45	0.54	0.61	0.66	0.67	0.69	0.70	0.70
pROC	BEDROC	0.51	0.37	0.45	0.55	0.61	0.65	0.68	0.69	0.69	0.69
n = 20
pROC	AU-ROC	0.77	0.75	0.71	0.66	0.58	0.52	0.45	0.39	0.35	0.33
BEDROC	AU-ROC	0.85	0.84	0.71	0.57	0.44	0.34	0.26	0.21	0.18	0.17
SLR	AU-ROC	0.77	0.75	0.71	0.66	0.60	0.54	0.47	0.41	0.36	0.34
SLR	pROC	0.51	0.52	0.53	0.53	0.53	0.53	0.53	0.53	0.53	0.53
SLR	BEDROC	0.40	0.38	0.50	0.58	0.65	0.69	0.71	0.72	0.72	0.72
pROC	BEDROC	0.41	0.38	0.48	0.58	0.63	0.66	0.69	0.70	0.70	0.70
n = 100
pROC	AU-ROC	0.75	0.73	0.67	0.61	0.54	0.48	0.42	0.38	0.35	0.34
BEDROC	AU-ROC	0.87	0.79	0.62	0.47	0.36	0.28	0.22	0.19	0.17	0.16
SLR	AU-ROC	0.75	0.72	0.68	0.62	0.56	0.50	0.44	0.39	0.36	0.35
SLR	pROC	0.55	0.55	0.56	0.56	0.56	0.57	0.57	0.58	0.58	0.58
SLR	BEDROC	0.32	0.42	0.56	0.64	0.69	0.72	0.74	0.74	0.74	0.74
pROCa	BEDROC	0.34	0.43	0.56	0.63	0.68	0.70	0.72	0.73	0.72	0.72

ISSN: 1471-2105