Simulation-based inference of single-molecule experiments

TL;DR

This paper reviews the emerging use of simulation-based inference (SBI), combining physics-based simulations and machine learning, to analyze complex, noisy single-molecule experimental data such as force spectroscopy and cryo-EM.

Contribution

It introduces SBI methods tailored for single-molecule experiments, discusses their limitations, and illustrates initial applications in force-spectroscopy and cryo-EM data analysis.

Findings

SBI enables principled connection between models and experimental data.

Deep learning accelerates SBI development for complex models.

First applications of SBI to single-molecule experiments are demonstrated.

Abstract

Single-molecule experiments are a unique tool to characterize the structural dynamics of biomolecules. However, reconstructing molecular details from noisy single-molecule data is challenging. Simulation-based inference (SBI) integrates statistical inference, physics-based simulators, and machine learning and is emerging as a powerful framework for analysing complex experimental data. Recent advances in deep learning have accelerated the development of new SBI methods, enabling the application of Bayesian inference to an ever-increasing number of scientific problems. Here, we review the nascent application of SBI to the analysis of single-molecule experiments. We introduce parametric Bayesian inference and discuss its limitations. We then overview emerging deep-learning-based SBI methods to perform Bayesian inference for complex models encoded in computer simulators. We illustrate the first applications of SBI to single-molecule force-spectroscopy and cryo-electron microscopy experiments. SBI allows us to leverage powerful computer algorithms modeling complex biomolecular phenomena to connect scientific models and experiments in a principled way.