# TICA-Based Free Energy Matching for Machine-Learned Molecular Dynamics

Source: [TICA-Based Free Energy Matching for Machine-Learned Molecular Dynamics](<https://www.sota2.com/research/paper/68fa4bd51e209131ce948c67>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:55:01.242Z

Authors: Alexander Aghili, Andy Bruce, Daniel Sabo, Razvan Marinescu

Published: 2025-09-18T04:22:25.000Z

## Abstract

Molecular dynamics (MD) simulations provide atomistic insight into biomolecular systems but are often limited by high computational costs required to access long timescales. Coarse-grained machine learning models offer a promising avenue for accelerating sampling, yet conventional force matching approaches often fail to capture the full thermodynamic landscape as fitting a model on the gradient may not fit the absolute differences between low-energy conformational states. In this work, we incorporate a complementary energy matching term into the loss function. We evaluate our framework on the Chignolin protein using the CGSchNet model, systematically varying the weight of the energy loss term. While energy matching did not yield statistically significant improvements in accuracy, it revealed distinct tendencies in how models generalize the free energy surface. Our results suggest future opportunities to enhance coarse-grained modeling through improved energy estimation techniques and multi-modal loss formulations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Reaction coordinate distribution modeling on Chignolin protein](<https://www.sota2.com/research/sota/reaction-coordinate-distribution-modeling-on-chignolin-protein.md>): Reaction coordinate distribution modeling; Chignolin protein; W1: 0.65711.

- [TICA KDE distribution modeling on Chignolin protein](<https://www.sota2.com/research/sota/tica-kde-distribution-modeling-on-chignolin-protein.md>): TICA KDE distribution modeling; Chignolin protein; W1: 0.00057.

- [Bond angle distribution modeling on Chignolin protein](<https://www.sota2.com/research/sota/bond-angle-distribution-modeling-on-chignolin-protein.md>): Bond angle distribution modeling; Chignolin protein; W1: 0.24846.

- [Dihedral angle distribution modeling on Chignolin protein](<https://www.sota2.com/research/sota/dihedral-angle-distribution-modeling-on-chignolin-protein.md>): Dihedral angle distribution modeling; Chignolin protein; W1: 0.21482.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.14600>)

[PDF](<https://arxiv.org/pdf/2509.14600.pdf>)