Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time
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_ | 1866908812549554176 |
|---|---|
| author | Richman, Daniel D. Karaguesian, Jessica Suomivuori, Carl-Mikael Dror, Ron O. |
| author_facet | Richman, Daniel D. Karaguesian, Jessica Suomivuori, Carl-Mikael Dror, Ron O. |
| contents | The function of biomolecules such as proteins depends on their ability to interconvert between a wide range of structures or "conformations." Researchers have endeavored for decades to develop computational methods to predict the distribution of conformations, which is far harder to determine experimentally than a static folded structure. We present ConforMix, an inference-time algorithm that enhances sampling of conformational distributions using a combination of classifier guidance, filtering, and free energy estimation. Our approach upgrades diffusion models -- whether trained for static structure prediction or conformational generation -- to enable more efficient discovery of conformational variability without requiring prior knowledge of major degrees of freedom. ConforMix is orthogonal to improvements in model pretraining and would benefit even a hypothetical model that perfectly reproduced the Boltzmann distribution. Remarkably, when applied to a diffusion model trained for static structure prediction, ConforMix captures structural changes including domain motion, cryptic pocket flexibility, and transporter cycling, while avoiding unphysical states. Case studies of biologically critical proteins demonstrate the scalability, accuracy, and utility of this method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03312 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time Richman, Daniel D. Karaguesian, Jessica Suomivuori, Carl-Mikael Dror, Ron O. Biomolecules Machine Learning The function of biomolecules such as proteins depends on their ability to interconvert between a wide range of structures or "conformations." Researchers have endeavored for decades to develop computational methods to predict the distribution of conformations, which is far harder to determine experimentally than a static folded structure. We present ConforMix, an inference-time algorithm that enhances sampling of conformational distributions using a combination of classifier guidance, filtering, and free energy estimation. Our approach upgrades diffusion models -- whether trained for static structure prediction or conformational generation -- to enable more efficient discovery of conformational variability without requiring prior knowledge of major degrees of freedom. ConforMix is orthogonal to improvements in model pretraining and would benefit even a hypothetical model that perfectly reproduced the Boltzmann distribution. Remarkably, when applied to a diffusion model trained for static structure prediction, ConforMix captures structural changes including domain motion, cryptic pocket flexibility, and transporter cycling, while avoiding unphysical states. Case studies of biologically critical proteins demonstrate the scalability, accuracy, and utility of this method. |
| title | Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2512.03312 |