A survey of probabilistic generative frameworks for molecular simulations

TL;DR

This survey compares flow-based and diffusion probabilistic models for molecular data, evaluating their accuracy and efficiency across various datasets to guide model selection in molecular simulations.

Contribution

It introduces a taxonomy of probabilistic generative models and benchmarks three representative models on molecular datasets, highlighting their strengths and limitations.

Findings

Neural Spline Flows excel at low-dimensional mode asymmetry.

Conditional Flow Matching performs best on high-dimensional, low-complexity data.

Denoising Diffusion Probabilistic Models are superior for low-dimensional, high-complexity data.

Abstract

Generative artificial intelligence is now a widely used tool in molecular science. Despite the popularity of probabilistic generative models, numerical experiments benchmarking their performance on molecular data are lacking. In this work, we introduce and explain several classes of generative models, broadly sorted into two categories: flow-based models and diffusion models. We select three representative models: Neural Spline Flows, Conditional Flow Matching, and Denoising Diffusion Probabilistic Models, and examine their accuracy, computational cost, and generation speed across datasets with tunable dimensionality, complexity, and modal asymmetry. Our findings are varied, with no one framework being the best for all purposes. In a nutshell, (i) Neural Spline Flows do best at capturing mode asymmetry present in low-dimensional data, (ii) Conditional Flow Matching outperforms other models for high-dimensional data with low complexity, and (iii) Denoising Diffusion Probabilistic Models appears the best for low-dimensional data with high complexity. Our datasets include a Gaussian mixture model and the dihedral torsion angle distribution of the Aib\textsubscript{9} peptide, generated via a molecular dynamics simulation. We hope our taxonomy of probabilistic generative frameworks and numerical results may guide model selection for a wide range of molecular tasks.