HyRes: a coarse-grained model for multi-scale enhanced sampling of disordered protein conformations

A coarse-grained model is derived for chlorophyll molecules in lipid bilayers using a multi-scale simulation ansatz aiming to understand the association behavior of the light harvesting complex (LHCII) of green plants.

Download Full-text

Deep Learning for Variational Multi-Scale Molecular Modeling

10.26434/chemrxiv.9640814.v4 ◽

2020 ◽

Author(s):

Jun Zhang ◽

Yaokun Lei ◽

Yi Isaac Yang ◽

Yi Qin Gao

Keyword(s):

Coarse Grained ◽

Atomistic Simulations ◽

Molecular Models ◽

Enhanced Sampling ◽

Physical Systems ◽

Molecular Systems ◽

Fine Grained ◽

Multi Scale ◽

Machine Learning Approach ◽

Training Objective

Molecular simulations are widely applied in the study of chemical and bio-physical systems. However, the accessible timescales of atomistic simulations are limited, and extracting equilibrium properties of systems containing rare events remains challenging. Two distinct strategies are usually adopted in this regard: either sticking to the atomistic level and performing enhanced sampling, or trading details for speed by leveraging coarse-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 so that 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, FG simulations can be boosted by the guidance of CG models via deep reinforcement learning. Our method defines a variational and adaptive training objective which allows end-to-end training of parametric molecular models using deep neural networks. Through multiple experiments, we show that our method is efficient and flexible, and performs well on challenging chemical and bio-molecular systems.

Download Full-text

Deep Learning for Variational Multi-Scale Molecular Modeling

10.26434/chemrxiv.9640814 ◽

2020 ◽

Cited By ~ 2

Author(s):

Jun Zhang ◽

Yaokun Lei ◽

Yi Isaac Yang ◽

Yi Qin Gao

Keyword(s):

Coarse Grained ◽

Atomistic Simulations ◽

Molecular Models ◽

Enhanced Sampling ◽

Physical Systems ◽

Molecular Systems ◽

Fine Grained ◽

Multi Scale ◽

Machine Learning Approach ◽

Training Objective

Molecular simulations are widely applied in the study of chemical and bio-physical systems. However, the accessible timescales of atomistic simulations are limited, and extracting equilibrium properties of systems containing rare events remains challenging. Two distinct strategies are usually adopted in this regard: either sticking to the atomistic level and performing enhanced sampling, or trading details for speed by leveraging coarse-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 so that 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, FG simulations can be boosted by the guidance of CG models via deep reinforcement learning. Our method defines a variational and adaptive training objective which allows end-to-end training of parametric molecular models using deep neural networks. Through multiple experiments, we show that our method is efficient and flexible, and performs well on challenging chemical and bio-molecular systems.

Download Full-text

Deep Learning for Multi-Scale Molecular Modeling

10.26434/chemrxiv.9640814.v3 ◽

2020 ◽

Author(s):

Jun Zhang ◽

Yaokun Lei ◽

Yi Isaac Yang ◽

Yi Qin Gao

Keyword(s):

Coarse Grained ◽

Atomistic Simulations ◽

Molecular Models ◽

Enhanced Sampling ◽

Physical Systems ◽

Molecular Systems ◽

Fine Grained ◽

Multi Scale ◽

Machine Learning Approach ◽

Training Objective

Molecular simulations are widely applied in the study of chemical and bio-physical systems. However, the accessible timescales of atomistic simulations are limited, and extracting equilibrium properties of systems containing rare events remains challenging. Two distinct strategies are usually adopted in this regard: either sticking to the atomistic level and performing enhanced sampling, or trading details for speed by leveraging coarse-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 so that 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, FG simulations can be boosted by the guidance of CG models via deep reinforcement learning. Our method defines a variational and adaptive training objective which allows end-to-end training of parametric molecular models using deep neural networks. Through multiple experiments, we show that our method is efficient and flexible, and performs well on challenging chemical and bio-molecular systems.

Download Full-text

Coarse graining from variationally enhanced sampling applied to the Ginzburg–Landau model

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1618455114 ◽

2017 ◽

Vol 114 (13) ◽

pp. 3370-3374 ◽

Cited By ~ 14

Author(s):

Michele Invernizzi ◽

Omar Valsson ◽

Michele Parrinello

Keyword(s):

Critical Point ◽

Sampling Method ◽

Coarse Graining ◽

Coarse Grained ◽

Atomistic Simulations ◽

Enhanced Sampling ◽

Ginzburg Landau ◽

Coarse Grained Model ◽

Unique Approach ◽

Physical Features

A powerful way to deal with a complex system is to build a coarse-grained model capable of catching its main physical features, while being computationally affordable. Inevitably, such coarse-grained models introduce a set of phenomenological parameters, which are often not easily deducible from the underlying atomistic system. We present a unique approach to the calculation of these parameters, based on the recently introduced variationally enhanced sampling method. It allows us to obtain the parameters from atomistic simulations, providing thus a direct connection between the microscopic and the mesoscopic scale. The coarse-grained model we consider is that of Ginzburg–Landau, valid around a second-order critical point. In particular, we use it to describe a Lennard–Jones fluid in the region close to the liquid–vapor critical point. The procedure is general and can be adapted to other coarse-grained models.

Download Full-text