Distance plus attention for binding affinity prediction

Table 2 Results of five models and their averages when all models were trained using the same training dataset (PDBbind2016 and PDBbind2020) of CASF\(-\)2016.290

Training Dataset	Predictors	R\((\uparrow )\)	RMSE\((\downarrow )\)	MAE\((\downarrow )\)	SD\((\downarrow )\)	CI\((\uparrow )\)
PDBbind2016	Model-1	0.860	1.143	0.899	1.144	0.837
	Model-2	0.858	1.152	0.880	1.154	0.835
	Model-3	0.851	1.158	0.895	1.160	0.828
	Model-4	0.858	1.155	0.917	1.157	0.834
	Model-5	0.872	1.094	0.855	1.096	0.843
	Ensemble	0.886	1.067	0.836	1.069	0.853
PDBbind2020	Model-1	0.878	1.106	0.858	1.108	0.852
	Model-2	0.872	1.120	0.867	1.122	0.845
	Model-3	0.851	1.165	0.898	1.167	0.828
	Model-4	0.855	1.145	0.852	1.147	0.840
	Model-5	0.858	1.133	0.855	1.135	0.839
	Ensemble	0.909	0.987	0.745	0.988	0.876

Higher R and CI values and lower RMSE, MAE, and SD values denote superior performances. The best-performing values are emboldened

ISSN: 1758-2946