Deep reinforcement learning of transition states

Zhang, Jun; Lei, Yao-Kun; Zhang, Zhen; Han, Xu; Li, Maodong; Yang, Lijiang; Yang, Yi; Gao, Yi Qin

doi:10.1039/d0cp06184k

Cited by 25 publications

(28 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a difficult problem, as the set of possible factors is typically much larger than the subset which actually affect the reaction mechanism, but recent computational developments have led to renewed interest in attempting to learn reaction mechanisms automatically. RL was introduced to this effort by Zhang et al 139 via a method to determine reaction dynamics and transition state locations using molecular dynamics simulation and RL with two fully connected feedforward NNs. The learning approach is named variational target optimisation and is a combination of two techniques closely related to actor-critic methods which were earlier described by the same research group.…”

Section: Chemical Reaction Planning Optimisation and Controlmentioning

confidence: 99%

A review of reinforcement learning in chemistry

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Chemical Reaction Planning Optimisation and Controlmentioning

confidence: 99%

A review of reinforcement learning in chemistry

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Machine learning models have been widely utilized to determine the dominant CVs from trajectories obtained using MD simulations. [54][55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71] Furthermore, a feasible application is the nonlinear regression based on a deep neural network (DNN), which is expected to have a performance beyond that of the LR in searching for an appropriate RC. 67,72,73 In particular, nonlinear functions of a DNN with hidden layers will provide richer expressions when the number of CVs is drastically increased in the system of interest.…”

Section: Introductionmentioning

confidence: 99%

Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)

Kikutsuji,

Mori,

Okazaki

et al. 2022

Preprint

View full text Add to dashboard Cite

A method for obtaining appropriate reaction coordinates is required to identify transition states distinguishing product and reactant in complex molecular systems. Recently, abundant research has been devoted to obtaining reaction coordinates using artificial neural networks from deep learning literature, where many collective variables are typically utilized in the input layer. However, it is difficult to explain the details of which collective variables contribute to the predicted reaction coordinates owing to the complexity of the nonlinear functions in deep neural networks. To overcome this limitation, we used Explainable Artificial Intelligence (XAI) methods of the Local Interpretable Modelagnostic Explanation (LIME) and the game theory-based framework known as Shapley Additive exPlanations (SHAP). We demonstrated that XAI enables us to obtain the degree of contribution of each collective variable to reaction coordinates that is determined by nonlinear regressions with deep learning for the committor of the alanine dipeptide isomerization in vacuum. In particular, both LIME and SHAP provide important features to the predicted reaction coordinates, which are characterized by appropriate dihedral angles consistent with those previously reported from the committor test analysis. The present study offers an AI-aided framework to explain the appropriate reaction coordinates, which acquires considerable significance when the number of degrees of freedom increases.

show abstract

“…However, since the transition state region is sampled much less frequently than the potential wells, the configurations in TS are scarce in a small sample, causing the so-called unbalanced label problem in deep learning. To overcome these problems, we recently propose a machine learning method RL ⧧ to automatically unravel the chemical reaction mechanism. Since configurations with a large constitute the separatrix (or TS) of the reaction, we are more likely to acquire a successful shooting from an initial configuration R i with large Therefore, we can optimize the model’s prediction by maximizing the positive samples’ inferred transition path probability p w ( TP | R i + ) compared with the negative ones .…”

Section: Introductionmentioning

confidence: 99%

“…Unfortunately, neural network is notorious for its interpretability. Previous methods , mainly analyze the reaction mechanism by the derivative of committor or transition path probability with respect to input coordinates ( or ) averaged over the equilibrium ensemble. Such an approach has its limitations.…”

Section: Introductionmentioning

confidence: 99%

Locating Transition Zone in Phase Space

Lei

Zhang

Han

et al. 2022

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

Understanding the reaction mechanism is required for better control of chemical reactions and is usually achieved by locating transition states (TSs) along a proper one-dimensional coordinate called reaction coordinate (RC). The identification of RC can be very difficult for high-dimensional realistic systems. A number of methods have been proposed to tackle this problem. A machine learning method is developed here to incorporate the influence of velocity on the reaction process. The method is also free of the unbalanced label problem resulting from the rather low fraction of configurations near the TS and can be easily extended to large systems. It locates the transition zone in the phase space and defines the dividing surface with a high transmission coefficient. Moreover, considering that the reaction environment can not only change the reaction path but also activate the reactive mode through energy transfer, we devise two measures to quantify the influence of these two factors on the reaction process and find that solvents can assist the reaction by directly doing work along the reactive mode. Not surprisingly, there is a positive correlation between the efficiency of energy transfer into the reactive mode and the reaction rate.

show abstract

Deep reinforcement learning of transition states

Abstract: Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach, called RL‡, to automatically unravel chemical reaction mechanisms. In RL‡, locating the transition state of a...

Cited by 25 publications

References 35 publications

A review of reinforcement learning in chemistry

A review of reinforcement learning in chemistry

Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)

Locating Transition Zone in Phase Space

Contact Info

Product

Resources

About