preprint · ChemRxiv · 2020

Deep Learning for Multi-Scale Molecular Modeling

Jun Zhang, Yao-Kun Lei, Yi Yang, Yi Qin Gao

Cited by 0Open access

Abstract

Molecular simulations are widely applied in the study of chemical and bio-physical systems. However, theaccessible timescales of atomistic simulations are limited, and extracting equilibrium properties of systemscontaining rare events remains challenging. Two distinct strategies are usually adopted in this regard: eithersticking to the atomistic level and performing enhanced sampling, or trading details for speed by leveragingcoarse-grained models. Although both strategies are promising, either of them, if adopted individually,exhibits severe limitations. In this paper we propose a machine-learning approach to ally both strategies sothat simulations on different scales can benefit mutually from their cross-talks: Accurate coarse-grained (CG)models can be inferred from the fine-grained (FG) simulations through deep generative learning; In turn, FGsimulations can be boosted by the guidance of CG models via deep reinforcement learning. Our methoddefines a variational and adaptive training objective which allows end-to-end training of parametricmolecular models using deep neural networks. Through multiple experiments, we show that our method isefficient and flexible, and performs well on challenging chemical and bio-molecular systems.

Cite this paper

APA 7

Zhang, J., Lei, Y.-K., Yang, Y., & Gao, Y. Q. (2020). Deep Learning for Multi-Scale Molecular Modeling. ChemRxiv. https://doi.org/10.26434/chemrxiv.9640814.v3

MLA 9

Zhang, Jun, et al. “Deep Learning for Multi-Scale Molecular Modeling.” ChemRxiv, 2020, https://doi.org/10.26434/chemrxiv.9640814.v3.

Chicago

Zhang, Jun, Yao-Kun Lei, Yi Yang, and Yi Qin Gao. 2020. “Deep Learning for Multi-Scale Molecular Modeling.” ChemRxiv. https://doi.org/10.26434/chemrxiv.9640814.v3.

Harvard

Zhang, J. et al. (2020) ‘Deep Learning for Multi-Scale Molecular Modeling’, ChemRxiv. Available at: https://doi.org/10.26434/chemrxiv.9640814.v3.

BibTeX

@misc{zhang2020deep,
  title = {{Deep Learning for Multi-Scale Molecular Modeling}},
  author = {Zhang, Jun and Lei, Yao-Kun and Yang, Yi and Gao, Yi Qin},
  journal = {ChemRxiv},
  year = {2020},
  doi = {10.26434/chemrxiv.9640814.v3}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.