中草药2026，Vol.57Issue(16)：6260-6272,13.DOI:10.7501/j.issn.0253-2670.2026.16.005
柔性-环增强图神经网络用于中药分子复杂结构的性质预测
Property prediction of complex traditional Chinese medicine molecular structures using a flexibility-ring enhanced graph neural network
摘要
Abstract
Objective To address the complex molecular structures and diverse ring systems characteristic of traditional Chinese medicine(TCM)compounds,this study aims to optimize the graph isomorphism network(GIN)to enhance its predictive capability for key molecular properties of TCM molecules.Methods Based on the GIN architecture,edge descriptors representing bond length strain and angle strain were introduced into the molecular graph,and multi-graph data were constructed by incorporating multiple favorable conformations,thereby developing a flexibility-ring enhanced graph neural network(FRGNN).The predictive performance of the proposed model on seven key molecular properties was evaluated using two TCM databases containing 37 822 molecules,and compared against three state-of-the-art(SOTA)graph neural network models and two basic graph neural network models.Results Compared with the second-best performing model,FRGNN achieved an average reduction of 8.63％in root mean square error across the seven property prediction tasks,for molecules containing polycyclic and macrocyclic structures,the predictive root mean square error was further reduced by 10.04％.Conclusion The proposed FRGNN model demonstrates superior performance over existing state-of-the-art models for small-molecule property prediction in the task of predicting key properties of TCM compounds,providing a novel and effective approach for the property prediction of complex natural products.关键词
人工智能/图神经网络/中药分子/中药数据库/性质预测Key words
artificial intelligence/graph neural networks/traditional Chinese medicine molecules/Chinese medicine datasets/property prediction分类
医药卫生引用本文复制引用
贺怀,刘曾,戴传云,陈治瑜,任琪,陈双扣,钟节,陶梦瑶,程榆淞,代浚豪,周寰宇..柔性-环增强图神经网络用于中药分子复杂结构的性质预测[J].中草药,2026,57(16):6260-6272,13.基金项目
国家自然科学基金面上项目(22578039) （22578039）
重庆市璧山区中医药领航联合专项重大项目(BSZYYLH001) （BSZYYLH001）
重庆市自然科学基金创新发展联合基金(CSTB2023NSCQ-LZX0060) （CSTB2023NSCQ-LZX0060）
