With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties,machine learning methods have tremendously shifted the paradigms of computational sciences underpinning p...With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties,machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics,material science,chemistry,and biology.While existing machine learning models have yielded superior performances in many occasions,most of them model and process molecular systems in terms of homogeneous graph,which severely limits the expressive power for representing diverse interactions.In practice,graph data with multiple node and edge types is ubiquitous and more appropriate for molecular systems.Thus,we propose the heterogeneous relational message passing network(HermNet),an end-to-end heterogeneous graph neural networks,to efficiently express multiple interactions in a single model with ab initio accuracy.HermNet performs impressively against many top-performing models on both molecular and extended systems.Specifically,HermNet outperforms other tested models in nearly 75%,83%and 69%of tasks on revised Molecular Dynamics 17(rMD17),Quantum Machines 9(QM9)and extended systems datasets,respectively.In addition,molecular dynamics simulations and material property calculations are performed with HermNet to demonstrate its performance.Finally,we elucidate how the design of HermNet is compatible with quantum mechanics from the perspective of the density functional theory.Besides,HermNet is a universal framework,whose sub-networks could be replaced by other advanced models.展开更多
Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has ...Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has a lower computational cost but requires accurate force fields to achieve chemical accuracy.In this work,we develop a symmetry-adapted graph neural network framework called the molecular dynamics graph neural network(MDGNN)to construct force fields automatically for molecular dynamics simulations for both molecules and crystals.This architecture consistently preserves translation,rotation,and permutation invariance in the simulations.We also propose a new feature engineering method that includes high-order terms of interatomic distances and demonstrate that the MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.In addition,we demonstrate that force fields constructed by the proposed model have good transferability.The MDGNN is thus an efficient and promising option for performing molecular dynamics simulations of large-scale systems with high accuracy.展开更多
基金This work was supported by the Basic Science Center Project of NSFC(Grant No.51788104)the Ministry of Science and Technology of China(Grants Nos.2018YFA0307100,and 2018YFA0305603)+3 种基金the National Science Fund for Distinguished Young Scholars(Grant No.12025405)the National Natural Science Foundation of China(Grant No.11874035)Tsinghua University Initiative Scientific Research Programthe Beijing Advanced Innovation Center for Future Chip(ICFC).
文摘With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties,machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics,material science,chemistry,and biology.While existing machine learning models have yielded superior performances in many occasions,most of them model and process molecular systems in terms of homogeneous graph,which severely limits the expressive power for representing diverse interactions.In practice,graph data with multiple node and edge types is ubiquitous and more appropriate for molecular systems.Thus,we propose the heterogeneous relational message passing network(HermNet),an end-to-end heterogeneous graph neural networks,to efficiently express multiple interactions in a single model with ab initio accuracy.HermNet performs impressively against many top-performing models on both molecular and extended systems.Specifically,HermNet outperforms other tested models in nearly 75%,83%and 69%of tasks on revised Molecular Dynamics 17(rMD17),Quantum Machines 9(QM9)and extended systems datasets,respectively.In addition,molecular dynamics simulations and material property calculations are performed with HermNet to demonstrate its performance.Finally,we elucidate how the design of HermNet is compatible with quantum mechanics from the perspective of the density functional theory.Besides,HermNet is a universal framework,whose sub-networks could be replaced by other advanced models.
基金This work was supported by the Basic Science Center Project of National Natural Science Foundation of China(Grant No.51788104)the Ministry of Science and Technology of China(Grant Nos.2016YFA0301001,and 2017YFB0701502)the Beijing Advanced Innovation Center for Materials Genome Engineering.
文摘Molecular dynamics is a powerful simulation tool to explore material properties.Most realistic material systems are too large to be simulated using first-principles molecular dynamics.Classical molecular dynamics has a lower computational cost but requires accurate force fields to achieve chemical accuracy.In this work,we develop a symmetry-adapted graph neural network framework called the molecular dynamics graph neural network(MDGNN)to construct force fields automatically for molecular dynamics simulations for both molecules and crystals.This architecture consistently preserves translation,rotation,and permutation invariance in the simulations.We also propose a new feature engineering method that includes high-order terms of interatomic distances and demonstrate that the MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.In addition,we demonstrate that force fields constructed by the proposed model have good transferability.The MDGNN is thus an efficient and promising option for performing molecular dynamics simulations of large-scale systems with high accuracy.
