A Standardized Benchmark for Machine-Learned Molecular Dynamics using Weighted Ensemble Sampling

TL;DR

This paper introduces a standardized, modular benchmarking framework for molecular dynamics simulations, utilizing weighted ensemble sampling and diverse metrics to enable reproducible comparison of classical and machine learning-based methods.

Contribution

It provides a flexible, open-source platform with comprehensive evaluation tools and a diverse protein dataset to facilitate consistent benchmarking of MD approaches.

Findings

Validated classical MD and machine learning models on diverse proteins

Demonstrated the framework's ability to compare different sampling methods

Provided extensive simulation data for future benchmarking studies

Abstract

The rapid evolution of molecular dynamics (MD) methods, including machine-learned dynamics, has outpaced the development of standardized tools for method validation. Objective comparison between simulation approaches is often hindered by inconsistent evaluation metrics, insufficient sampling of rare conformational states, and the absence of reproducible benchmarks. To address these challenges, we introduce a modular benchmarking framework that systematically evaluates protein MD methods using enhanced sampling analysis. Our approach uses weighted ensemble (WE) sampling via The Weighted Ensemble Simulation Toolkit with Parallelization and Analysis (WESTPA), based on progress coordinates derived from Time-lagged Independent Component Analysis (TICA), enabling fast and efficient exploration of protein conformational space. The framework includes a flexible, lightweight propagator interface that supports arbitrary simulation engines, allowing both classical force fields and machine learning-based models. Additionally, the framework offers a comprehensive evaluation suite capable of computing more than 19 different metrics and visualizations across a variety of domains. We further contribute a dataset of nine diverse proteins, ranging from 10 to 224 residues, that span a variety of folding complexities and topologies. Each protein has been extensively simulated at 300K for one million MD steps per starting point (4 ns). To demonstrate the utility of our framework, we perform validation tests using classic MD simulations with implicit solvent and compare protein conformational sampling using a fully trained versus under-trained CGSchNet model. By standardizing evaluation protocols and enabling direct, reproducible comparisons across MD approaches, our open-source platform lays the groundwork for consistent, rigorous benchmarking across the molecular simulation community.