Aligning Protein Conformation Ensemble Generation with Physical Feedback
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918039265476608 |
|---|---|
| author | Lu, Jiarui Chen, Xiaoyin Lu, Stephen Zhewen Lozano, Aurélie Chenthamarakshan, Vijil Das, Payel Tang, Jian |
| author_facet | Lu, Jiarui Chen, Xiaoyin Lu, Stephen Zhewen Lozano, Aurélie Chenthamarakshan, Vijil Das, Payel Tang, Jian |
| contents | Protein dynamics play a crucial role in protein biological functions and properties, and their traditional study typically relies on time-consuming molecular dynamics (MD) simulations conducted in silico. Recent advances in generative modeling, particularly denoising diffusion models, have enabled efficient accurate protein structure prediction and conformation sampling by learning distributions over crystallographic structures. However, effectively integrating physical supervision into these data-driven approaches remains challenging, as standard energy-based objectives often lead to intractable optimization. In this paper, we introduce Energy-based Alignment (EBA), a method that aligns generative models with feedback from physical models, efficiently calibrating them to appropriately balance conformational states based on their energy differences. Experimental results on the MD ensemble benchmark demonstrate that EBA achieves state-of-the-art performance in generating high-quality protein ensembles. By improving the physical plausibility of generated structures, our approach enhances model predictions and holds promise for applications in structural biology and drug discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24203 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aligning Protein Conformation Ensemble Generation with Physical Feedback Lu, Jiarui Chen, Xiaoyin Lu, Stephen Zhewen Lozano, Aurélie Chenthamarakshan, Vijil Das, Payel Tang, Jian Biomolecules Machine Learning Protein dynamics play a crucial role in protein biological functions and properties, and their traditional study typically relies on time-consuming molecular dynamics (MD) simulations conducted in silico. Recent advances in generative modeling, particularly denoising diffusion models, have enabled efficient accurate protein structure prediction and conformation sampling by learning distributions over crystallographic structures. However, effectively integrating physical supervision into these data-driven approaches remains challenging, as standard energy-based objectives often lead to intractable optimization. In this paper, we introduce Energy-based Alignment (EBA), a method that aligns generative models with feedback from physical models, efficiently calibrating them to appropriately balance conformational states based on their energy differences. Experimental results on the MD ensemble benchmark demonstrate that EBA achieves state-of-the-art performance in generating high-quality protein ensembles. By improving the physical plausibility of generated structures, our approach enhances model predictions and holds promise for applications in structural biology and drug discovery. |
| title | Aligning Protein Conformation Ensemble Generation with Physical Feedback |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2505.24203 |