Machine Learning Directed Optimization of Classical Molecular Modeling Force Fields

Befort, Bridgette J.; DeFever, Ryan S.; Tow, Garrett M.; Dowling, Alexander W.; Maginn, Edward J.

doi:10.48550/arxiv.2103.03208

Cited by 1 publication

(3 citation statements)

References 52 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a challenging task but should be possible by simulating properties of interest for multiple parameter sets and then using modeling techniques well suited to sparse data, such as Gaussian process (GP) 79,80 regression. Befort et al 40 recently had success using GPs to build physical property surrogate models based on small molecule force fields. These methods could be enhanced with reweighting techniques like MBAR on simulated points to add gradient information to the surrogate models.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

“…To apply this technique to an arbitrary force field, one will usually need to construct such surrogate models for different properties. Common techniques to build these surrogate models might include reweighting, 52 Gaussian processes, 40 and machine learning methods. 39 Since the methods needed to construct such a model depend substantially on the property and the parameters of interest, that question is beyond the scope of this study; we focus only on applying Bayesian inference given a surrogate model for molecular properties.…”

Section: ■ Methodsmentioning

confidence: 99%

“…A general strategy for efficiently generating surrogate models for molecular simulation properties is still under development. 40 As the effort is expended to develop such algorithms, it is valuable to evaluate the utility of Bayesian inference to make decisions about the parametrization of molecular models.…”

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bayesian-Inference-Driven Model Parametrization and Model Selection for 2CLJQ Fluid Models

Madin

Boothroyd²,

Messerly

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

A high level of physical detail in a molecular model improves its ability to perform high accuracy simulations but can also significantly affect its complexity and computational cost. In some situations, it is worthwhile to add complexity to a model to capture properties of interest; in others, additional complexity is unnecessary and can make simulations computationally infeasible. In this work, we demonstrate the use of Bayesian inference for molecular model selection, using Monte Carlo sampling techniques accelerated with surrogate modeling to evaluate the Bayes factor evidence for different levels of complexity in the two-centered Lennard-Jones + quadrupole (2CLJQ) fluid model. Examining three nested levels of model complexity, we demonstrate that the use of variable quadrupole and bond length parameters in this model framework is justified only for some chemistries. Through this process, we also get detailed information about the distributions and correlation of parameter values, enabling improved parametrization and parameter analysis. We also show how the choice of parameter priors, which encode previous model knowledge, can have substantial effects on the selection of models, penalizing careless introduction of additional complexity. We detail the computational techniques used in this analysis, providing a roadmap for future applications of molecular model selection via Bayesian inference and surrogate modeling.

show abstract

Section: ■ Results and Discussionmentioning

confidence: 99%