Adversarial-Residual-Coarse-Graining: Applying machine learning theory to systematic molecular coarse-graining

Abstract

We utilize connections between molecular coarse-graining approaches and implicit generative models in machine learning to describe a new framework for systematic molecular coarse-graining (CG). Focus is placed on the formalism encompassing generative adversarial networks. The resulting method enables a variety of model parameterization strategies, some of which show similarity to previous CG methods. We demonstrate that the resulting framework can rigorously parameterize CG models containing CG sites with no prescribed connection to the reference atomistic system (termed virtual sites); however, this advantage is offset by the lack of a closed-form expression for the CG Hamiltonian at the resolution obtained after integration over the virtual CG sites. Computational examples are provided for cases in which these methods ideally return identical parameters as Relative Entropy Minimization (REM) CG but where traditional REM CG optimization equations are not applicable.

arXiv commentThe following article has been submitted to the Journal of Chemical Physics. After it is published, it will be found at https://publishing.aip.org/resources/librarians/products/journals/

References in corpus (18)

• Auto-Encoding Variational Bayes
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Tutorial on Variational Autoencoders
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Identification of slow molecular order parameters for Markov model construction
• Estimating divergence functionals and the likelihood ratio by convex risk minimization
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Wasserstein GAN
• DeePCG: constructing coarse-grained models via deep neural networks
• Training generative neural networks via Maximum Mean Discrepancy optimization
• Learning in Implicit Generative Models
• Predictive Coarse-Graining
• In silico generation of novel, drug-like chemical matter using the LSTM neural network
• Adversarial Training For Sketch Retrieval
• $\mathcal{C}-$IBI: Targeting cumulative coordination within an iterative protocol to derive coarse-grained models of (multi-component) complex fluids
• Parameterization of Coarse-grained Molecular Interactions through Potential of Mean Force Calculations and Cluster Expansions Techniques
• The Inductive Bias of Restricted f-GANs
• Sobolev GAN

Cited by in corpus (8)

• Machine learning for molecular simulation
• Interactions in Active Colloids
• Ensuring thermodynamic consistency with invertible coarse-graining
• Differentiable Molecular Simulations for Control and Learning
• Scaling Graph Neural Networks to Large Proteins
• Explaining classifiers to understand coarse-grained models
• Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model
• Manifold learning for coarse-graining atomistic simulations: Application to amorphous solids