自动化学报2023，Vol.49Issue(12)：2507-2519,13.DOI:10.16383/j.aas.c220371
基于多层注意力和消息传递网络的药物相互作用预测方法
Drug-drug Interaction Prediction Method Based on Multi-level Attention Mechanism and Message Passing Neural Network
摘要
Abstract
Drug-drug interaction(DDI)denotes the presence of inhibitory or promoting effects between different drugs.The existing DDI prediction methods often directly use drug molecular feature representation,while ignoring the different effects of different atoms within drug molecule on DDI.To solve this problem,a DDI prediction meth-od is proposed based on multi-level attention mechanism and message passing neural network.This method models the task as a link prediction problem of predicting DDI by extracting the drug molecular features from their se-quence representations.First,the atomic feature network is developed based on attention mechanism and message passing neural network.Through integration with the proposed positional encoding based on molecular centroid,the proposed network can learn from different atoms and the correlated chemical bonds to construct drug molecular graph features.Second,attention mechanism-based molecular feature network is designed,and the DDI prediction can then be realized by using supervision and contrastive loss learning.Finally,experiments demonstrate the effect-iveness and superiority of the proposed method.关键词
药物相互作用预测/多层次注意力机制/消息传递神经网络/位置编码Key words
Drug-drug interaction prediction/multi-level attention mechanism/message passing neural network/positional encoding引用本文复制引用
饶晓洁,张通,孟献兵,陈俊龙..基于多层注意力和消息传递网络的药物相互作用预测方法[J].自动化学报,2023,49(12):2507-2519,13.基金项目
国家重点研发计划(2019YFB1703600),国家自然科学基金(62006081),广东省自然科学基金面上项目(2022A1515011317),中国博士后科学基金(2020M672630)资助Supported by National Key Research and Development Pro-gram of China(2019YFB1703600),National Natural Science Foundation of China(62006081),Natural Science Foundation of Guangdong Province(2022A1515011317),and China Postdoctor-al Science Foundation Project(2020M672630) （2019YFB1703600）
