Automated sampling assessment for molecular simulations using the effective sample size

TL;DR

This paper introduces a universal method to evaluate the sampling quality in molecular simulations by estimating the effective sample size, applicable to various systems and including an automated state identification process.

Contribution

It presents a novel, general approach to assess sampling quality through effective sample size estimation, applicable to both dynamic and nondynamic molecular simulation methods.

Findings

Method accurately estimates effective sample size across diverse systems.

Automated procedure identifies physical states from trajectories.

Robustness demonstrated in multiple molecular systems.

Abstract

To quantify the progress in development of algorithms and forcefields used in molecular simulations, a method for the assessment of the sampling quality is needed. We propose a general method to assess the sampling quality through the estimation of the number of independent samples obtained from molecular simulations. This method is applicable to both dynamic and nondynamic methods and utilizes the variance in the populations of physical states to determine the ESS. We test the correctness and robustness of our procedure in a variety of systems--two-state toy model, all-atom butane, coarse-grained calmodulin, all-atom dileucine and Met-enkaphalin. We also introduce an automated procedure to obtain approximate physical states from dynamic trajectories: this procedure allows for sample--size estimation for systems for which physical states are not known in advance.