DeepMHADTA: Prediction of Drug-Target Binding Affinity Using Multi-Head Self-Attention and Convolutional Neural Network

Current Issues in Molecular Biology

Lei Deng¹  Yunyun Zeng¹  Xuejun Liu²  Hui Liu²  Zixuan Liu³ 

[1] School of Computer Science and Engineering, Central South University, Changsha 410083, China;School of Computer Science and Technology, Nanjing Tech University, Nanjing 211816, China;School of Software, Xinjiang University, Urumqi 830046, China;

关键词: binding affinity;    multi-head self attention mechanism;    convolutional neural network;    residual network;    word embedding;   

DOI  :  10.3390/cimb44050155

来源: DOAJ

【 摘 要 】

Drug-target interactions provide insight into the drug-side effects and drug repositioning. However, wet-lab biochemical experiments are time-consuming and labor-intensive, and are insufficient to meet the pressing demand for drug research and development. With the rapid advancement of deep learning, computational methods are increasingly applied to screen drug-target interactions. Many methods consider this problem as a binary classification task (binding or not), but ignore the quantitative binding affinity. In this paper, we propose a new end-to-end deep learning method called DeepMHADTA, which uses the multi-head self-attention mechanism in a deep residual network to predict drug-target binding affinity. On two benchmark datasets, our method outperformed several current state-of-the-art methods in terms of multiple performance measures, including mean square error (MSE), consistency index (CI), $r_m^2$, and PR curve area (AUPR). The results demonstrated that our method achieved better performance in predicting the drug–target binding affinity.

【 授权许可】

Unknown