Figure 3.

$p{K}_d$ prediction results of MolTrans and FP-Models trained with DAVIS and BindingDB, respectively. (A,B) are the $p{K}_d$ predictions of the FP-Model; linearity is evident within the label range. (C,D) are the $p{K}_d$ predictions of MolTrans, and the prediction distributions were divided into two sets for both datasets; the BindingDB dataset predicted a higher $p{K}_d$ value than the maximum value of the label range.