物理化学学报2026，Vol.42Issue(5)：110-126,17.DOI:10.1016/j.actphy.2025.100209
MolUNet++:自适应粒度显式子结构与互作感知分子表示学习
MolUNet++:adaptive-grained explicit substructure and interaction aware molecular representation learning
摘要
Abstract
Molecular representation learning is a critical task in AI-driven drug development.While graph neural networks(GNNs)have demonstrated strong performance and gained widespread adoption in this field,efficiently extracting and explicitly analyzing functional groups remains a challenge.To address this issue,we propose MolUNet++,a novel model that employs Molecular Edge Shrinkage Pooling(MESPool)for hierarchical substructure extraction,utilizes a Nested UNet framework for multi-granularity feature integration,and incorporates a substructure masking explainer for quantitative fragment analysis.We evaluated MolUNet++on tasks including molecular property prediction,drug-drug interaction(DDI)prediction,and drug-target interaction(DTI)prediction.Experimental results demonstrate that MolUNet++not only outperforms traditional GNN models in predictive performance but also exhibits explicit,intuitive,and chemically logical interpretability.This capability provides valuable insights and tools for researchers in drug design and optimization.关键词
分子表示学习/图神经网络/结构识别/自适应粒度Key words
Molecular representation learning/GNN/Structure identification/Adaptive granularity分类
化学化工引用本文复制引用
徐凡丁,杨志伟,武思睿,苏武,王力卓,孟德宇,龙建刚..MolUNet++:自适应粒度显式子结构与互作感知分子表示学习[J].物理化学学报,2026,42(5):110-126,17.基金项目
陕西省重点研发计划(2021GXLH-Z-064和2024SF-ZDCYL-03-24) （2021GXLH-Z-064和2024SF-ZDCYL-03-24）
西安交通大学—中国移动数字政府联合研究院前沿探索研究基金(XJTU-CMCC-QY202508005,中国) （XJTU-CMCC-QY202508005,中国）
国家外国专家项目(G2022170026L,中国) （G2022170026L,中国）
西安交通大学基本科研业务费自由探索与创新-学生类项目(xzy022024049). （xzy022024049）
