The PCCs and RMSEs (<i>pK</i>_<i>d</i>/<i>pK</i>_<i>i</i>) for our DC-GBT models in three test cases, i.e., PDBbind-v2007, PDBbind-v2013 and PDBbind-v2016.

Three DC-GBT models are considered with features from different types of bipartite graphs. The DC-GBT(Dist) model uses features from distance-based bipartite graphs; The DC-GBT(Chrg) model uses features from electrostatic-based bipartite graphs; The DC-GBT(Dist+Chrg) model uses features from both distance-based bipartite graphs and electrostatic-based bipartite graphs.本数据集包含三款基于不同类型二分图（bipartite graph）提取特征的DC-GBT模型。其中DC-GBT(Dist)模型采用基于距离的二分图所提取的特征；DC-GBT(Chrg)模型采用基于静电的二分图所提取的特征；DC-GBT(Dist+Chrg)模型则同时采用基于距离的二分图与基于静电的二分图所提取的特征。