FP-ADMET: a compendium of fingerprint-based ADMET prediction models

Table 6 Example showing the property (\(pK_a\) and anticommensal effect) predictions and associated uncertainties for 3 molecules

Name	Anticommensal effect	Confidence	Credibility	\(\hat{pK_a}\)	Q = 0.025	Q = 0.975
G00001	Inactive	0.95	0.57	9.62	4.89	11.49
G00002	Active	0.95	0.51	4.41	− 1.60	13.06
G00003	Inactive	0.95	0.57	3.37	1.66	6.10

\(Q=0.025\) and \(Q=0.975\) are the predictions calculated at percentiles 0.025 and 0.975 and allow for 95% prediction intervals

ISSN: 1758-2946