Dual Interaction and Kernel-Diverse Network for Accurate Drug-Target Binding Affinity Prediction

Drug-target binding affinities measure the binding strength between drugs and targets, serving as the foundation for computer-aided drug design. The existing methods based on neural network rarely incorporate knowledge from biochemistry, which limits their performance. In this paper, we propose a dual interaction and kernel-diverse network for drug-target binding affinity prediction, termed DTANet, drawing inspiration from the biochemical properties of drugs and targets. Specifically, since functional groups and peptide chains are pivotal in determining the properties of drugs and their targets, and their lengths vary significantly. Drawing inspiration from this, we propose a Kernel-diverse Two-stream Network (KTN) and a Cross-Scale Interaction Module (CSIM) to extract the features of drugs and targets. The binding site of drug and target is crucial for precise affinity prediction. Inspired by this, we introduce the Drug-Target Interaction Module (DTIM) to explore the relationships between drugs and targets to focus on binding sites. Experiments have been conducted on two popular benchmarks: KIBA and Davis. Our DTANet obtains superior performance compared to existing methods on both datasets. Source codes are available at https://github.com/202324131016T/DTANet.