Search

Accurately predicting drug-target binding affinity (DTA) is crucial for advancements in drug repositioning. In this paper, we present HBDTA, an innovative predictive methodology that harnesses the capabilities of graph deep learning and multi-layer networks for DTA prediction. The HBDTA approach encompasses a comprehensive framework with three distinct graph neural network (GNN) algorithms: multi-head graph attention networks (Multi-head GAT), generalized aggregation networks (GENConv), and graph convolutional networks (GCNConv) designed to extract drug features. Additionally, we employ a multi-layer bi-directional long short-term memory (MBLSTM) with residual blocks to extract protein features. After deriving feature vectors for drugs and proteins, they independently pass through fully connected layers before integration into a self-attention layer. Subsequently, the resulting feature vectors are concatenated and passed through four layers of fully secured networks to facilitate prediction. Finally, we assess our model's performance on the Davis, KIBA, Metz, and DTC datasets. Comparative analysis against state-of-the-art methodologies, such as DeepGLSTM, DeepNC, and GraphDTA, among others, underscores the effectiveness of HBDTA. The results suggest that HBDTA holds significant potential for practical drug discovery and personalized medicine applications. [ABSTRACT FROM AUTHOR]