Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912671416188928 |
|---|---|
| author | Frellsen, Jes Kassem, Maher M. Bengtsen, Tone Olsen, Lars Lindorff-Larsen, Kresten Ferkinghoff-Borg, Jesper Boomsma, Wouter |
| author_facet | Frellsen, Jes Kassem, Maher M. Bengtsen, Tone Olsen, Lars Lindorff-Larsen, Kresten Ferkinghoff-Borg, Jesper Boomsma, Wouter |
| contents | Inverse folding models have proven to be highly effective zero-shot predictors of protein stability. Despite this success, the link between the amino acid preferences of an inverse folding model and the free-energy considerations underlying thermodynamic stability remains incompletely understood. A better understanding would be of interest not only from a theoretical perspective, but also potentially provide the basis for stronger zero-shot stability prediction. In this paper, we take steps to clarify the free-energy foundations of inverse folding models. Our derivation reveals the standard practice of likelihood ratios as a simplistic approximation and suggests several paths towards better estimates of the relative stability. We empirically assess these approaches and demonstrate that considerable gains in zero-shot performance can be achieved with fairly simple means. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05596 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-shot protein stability prediction by inverse folding models: a free energy interpretation Frellsen, Jes Kassem, Maher M. Bengtsen, Tone Olsen, Lars Lindorff-Larsen, Kresten Ferkinghoff-Borg, Jesper Boomsma, Wouter Machine Learning Artificial Intelligence Biomolecules Inverse folding models have proven to be highly effective zero-shot predictors of protein stability. Despite this success, the link between the amino acid preferences of an inverse folding model and the free-energy considerations underlying thermodynamic stability remains incompletely understood. A better understanding would be of interest not only from a theoretical perspective, but also potentially provide the basis for stronger zero-shot stability prediction. In this paper, we take steps to clarify the free-energy foundations of inverse folding models. Our derivation reveals the standard practice of likelihood ratios as a simplistic approximation and suggests several paths towards better estimates of the relative stability. We empirically assess these approaches and demonstrate that considerable gains in zero-shot performance can be achieved with fairly simple means. |
| title | Zero-shot protein stability prediction by inverse folding models: a free energy interpretation |
| topic | Machine Learning Artificial Intelligence Biomolecules |
| url | https://arxiv.org/abs/2506.05596 |