Coarse-Grained Molecular Dynamics Study based on TorchMD

作     者：Peijun Xu Xiaohong Mou Qiuhan Guo Ting Fu Hong Ren Guiyan Wang Yan Li Guohui Li 许佩军;牟晓红;郭秋含;付婷;任虹;王贵艳;李焱;李国辉

作者机构：Liaoning Normal UniversityDalian 116029China Pharmacy Department of Affiliated Zhongshan Hospital of Dalian UniversityDalian 116001China Department of Ophthalmology Aerospace Center HospitalBeijing 100049China Dalian Ocean UniversityDalian 116029China Dalian Institute of Chemical PhysicsState Key Laboratory of Molecular Reaction DynamicsDalian 116023China 

出 版 物：《Chinese Journal of Chemical Physics》 (化学物理学报（英文）)

年 卷 期：2021年第34卷第6期

页      面：957-969,I0006,I0158-I0166页

核心收录：

学科分类：081704[工学-应用化学] 07[理学] 070304[理学-物理化学(含∶化学物理)] 08[工学] 0817[工学-化学工程与技术] 0703[理学-化学] 

基　　金：supported by the National Natural Science Foundation of China(No.31800615 and No.21933010) 

主　　题：Deep learning TorchMD Coarse grained Modified find density peaks String 

摘      要：The coarse grained(CG)model implements the molecular dynamics simulation by simplifying atom properties and interaction between *** losing certain detailed information,the CG model is still the first-thought option to study the large molecule in long time scale with less computing *** deep learning model mainly mimics the human studying process to handle the network input as the image to achieve a good classification and regression *** this work,the TorchMD,a MD framework combining the CG model and deep learning model,is applied to study the protein folding *** 3D collective variable(CV)space,the modified find density peaks algorithm is applied to cluster the conformations from the TorchMD CG *** center conformation in different states is *** the boundary conformations between clusters are *** string algorithm is applied to study the path between two states,which are compared with the end conformations from all atoms *** result shows that the main phenomenon of protein folding with TorchMD CG model is the same as the all-atom simulations,but with a less simulating time *** workflow in this work provides another option to study the protein folding and other relative processes with the deep learning CG model.