Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.14600 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912591466463232 |
|---|---|
| author | Aghili, Alexander Bruce, Andy Sabo, Daniel Marinescu, Razvan |
| author_facet | Aghili, Alexander Bruce, Andy Sabo, Daniel Marinescu, Razvan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14600 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TICA-Based Free Energy Matching for Machine-Learned Molecular Dynamics Aghili, Alexander Bruce, Andy Sabo, Daniel Marinescu, Razvan Machine Learning Biological Physics I.2.1 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. |
| title | TICA-Based Free Energy Matching for Machine-Learned Molecular Dynamics |
| topic | Machine Learning Biological Physics I.2.1 |
| url | https://arxiv.org/abs/2509.14600 |