Aligning Protein Conformation Ensemble Generation with Physical Feedback

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Aurelie Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40436-40451, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-lu25b, title = {Aligning Protein Conformation Ensemble Generation with Physical Feedback}, author = {Lu, Jiarui and Chen, Xiaoyin and Lu, Stephen Zhewen and Lozano, Aurelie and Chenthamarakshan, Vijil and Das, Payel and Tang, Jian}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {40436--40451}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/lu25b/lu25b.pdf}, url = {https://proceedings.mlr.press/v267/lu25b.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Aligning Protein Conformation Ensemble Generation with Physical Feedback %A Jiarui Lu %A Xiaoyin Chen %A Stephen Zhewen Lu %A Aurelie Lozano %A Vijil Chenthamarakshan %A Payel Das %A Jian Tang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-lu25b %I PMLR %P 40436--40451 %U https://proceedings.mlr.press/v267/lu25b.html %V 267 %X 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.
APA
Lu, J., Chen, X., Lu, S.Z., Lozano, A., Chenthamarakshan, V., Das, P. & Tang, J.. (2025). Aligning Protein Conformation Ensemble Generation with Physical Feedback. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:40436-40451 Available from https://proceedings.mlr.press/v267/lu25b.html.

Related Material