Recent advances in protein conformation sampling by combining machine learning with molecular simulation  

作　　者：唐一鸣 杨中元 姚逸飞 周运 谈圆 王子超 潘瞳 熊瑞 孙俊力 韦广红 Yiming Tang;Zhongyuan Yang;Yifei Yao;Yun Zhou;Yuan Tan;Tong Pan;Rui Xiong;Junli Sun;Guanghong Wei(Department of Physics,State Key Laboratory of Surface Physics,and Key Laboratory for Computational Physical Sciences (Ministry of Education),Shanghai 200438,China)

机构地区：[1]Department of Physics,State Key Laboratory of Surface Physics,and Key Laboratory for Computational Physical Sciences (Ministry of Education),Shanghai 200438,China

出　　处：《Chinese Physics B》2024年第3期80-87,共8页中国物理B（英文版）

基　　金：Project supported by the National Key Research and Development Program of China(Grant No.2023YFF1204402);the National Natural Science Foundation of China(Grant Nos.12074079 and 12374208);the Natural Science Foundation of Shanghai(Grant No.22ZR1406800);the China Postdoctoral Science Foundation(Grant No.2022M720815).

摘　　要：The rapid advancement and broad application of machine learning(ML)have driven a groundbreaking revolution in computational biology.One of the most cutting-edge and important applications of ML is its integration with molecular simulations to improve the sampling efficiency of the vast conformational space of large biomolecules.This review focuses on recent studies that utilize ML-based techniques in the exploration of protein conformational landscape.We first highlight the recent development of ML-aided enhanced sampling methods,including heuristic algorithms and neural networks that are designed to refine the selection of reaction coordinates for the construction of bias potential,or facilitate the exploration of the unsampled region of the energy landscape.Further,we review the development of autoencoder based methods that combine molecular simulations and deep learning to expand the search for protein conformations.Lastly,we discuss the cutting-edge methodologies for the one-shot generation of protein conformations with precise Boltzmann weights.Collectively,this review demonstrates the promising potential of machine learning in revolutionizing our insight into the complex conformational ensembles of proteins.

关 键 词：machine learning molecular simulation protein conformational space enhanced sampling 

分 类 号：O561[理学—原子与分子物理] TP181[理学—物理] Q51[自动化与计算机技术—控制理论与控制工程]