Fast and accurate spectral prediction plays a crucial role in molecular design within fields such as pharmaceutical and materials science.Nevertheless,predicting molecular spectra typically requires quantum chemistry ...Fast and accurate spectral prediction plays a crucial role in molecular design within fields such as pharmaceutical and materials science.Nevertheless,predicting molecular spectra typically requires quantum chemistry calculations,posing significant challenges for fast predictions and highthroughput screening.In this paper,we propose an equivariant,fast,and robust model,named EnviroDetaNet,which integrates molecular environment information.EnviroDetaNet employs an E(3)-equivariant message-passing neural network combining intrinsic atomic properties,spatial features,and environmental information,allowing it tocomprehensively capture both local and global molecular information.Compared to state-of-the-art machine learning models,EnviroDetaNet excels in various predictive tasks and maintains high accuracy even with a 50%reduction in training data,demonstrating strong generalization capabilities.Ablation studies confirm that molecular environment information is crucial for improving model stability and accuracy.EnviroDetaNet also shows outstanding performance in spectral predictions for complex molecular systems,making it a powerful tool for accelerating molecular discovery.展开更多
基金supported by the National Key R&D Program of China(Grant No.2023YFF1204903)the National Natural Science Foundation of China(Grants No.22222303,22173032,21933010,22250710136,22333006)the Artificial Intelligence-Driven Reform of Scientific Research Paradigms:Empowerment Program for Discipline Advancement(Grants No.2024AI01009),Y.W.acknowledges support from the Schmidt Science Fellowship,in partnership with the Rhodes Trust,and the Simons Center for Computational Physical Chemistry at New York University,We sincerely thank the High-Performance Computing(HPC)resources supported by New York University and NYU Abu Dhabi.
文摘Fast and accurate spectral prediction plays a crucial role in molecular design within fields such as pharmaceutical and materials science.Nevertheless,predicting molecular spectra typically requires quantum chemistry calculations,posing significant challenges for fast predictions and highthroughput screening.In this paper,we propose an equivariant,fast,and robust model,named EnviroDetaNet,which integrates molecular environment information.EnviroDetaNet employs an E(3)-equivariant message-passing neural network combining intrinsic atomic properties,spatial features,and environmental information,allowing it tocomprehensively capture both local and global molecular information.Compared to state-of-the-art machine learning models,EnviroDetaNet excels in various predictive tasks and maintains high accuracy even with a 50%reduction in training data,demonstrating strong generalization capabilities.Ablation studies confirm that molecular environment information is crucial for improving model stability and accuracy.EnviroDetaNet also shows outstanding performance in spectral predictions for complex molecular systems,making it a powerful tool for accelerating molecular discovery.
