PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models

Fanmeng Wang, Wentao Guo, Qi Ou, Hongshuai Wang, Haitao Lin, Hongteng Xu, Zhifeng Gao
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63002-63015, 2025.

Abstract

Polymer conformation generation is a critical task that enables atomic-level studies of diverse polymer materials. While significant advances have been made in designing conformation generation methods for small molecules and proteins, these methods struggle to generate polymer conformations due to their unique structural characteristics. Meanwhile, the scarcity of polymer conformation datasets further limits progress, making this important area largely unexplored. In this work, we propose PolyConf, a pioneering tailored polymer conformation generation method that leverages hierarchical generative models to unlock new possibilities. Specifically, we decompose the polymer conformation into a series of local conformations (i.e., the conformations of its repeating units), generating these local conformations through an autoregressive model, and then generating their orientation transformations via a diffusion model to assemble them into the complete polymer conformation. Moreover, we develop the first benchmark with a high-quality polymer conformation dataset derived from molecular dynamics simulations to boost related research in this area. The comprehensive evaluation demonstrates that PolyConf consistently outperforms existing conformation generation methods, thus facilitating advancements in polymer modeling and simulation. The whole work is available at https://polyconf-icml25.github.io.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25ah, title = {{P}oly{C}onf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models}, author = {Wang, Fanmeng and Guo, Wentao and Ou, Qi and Wang, Hongshuai and Lin, Haitao and Xu, Hongteng and Gao, Zhifeng}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {63002--63015}, 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/wang25ah/wang25ah.pdf}, url = {https://proceedings.mlr.press/v267/wang25ah.html}, abstract = {Polymer conformation generation is a critical task that enables atomic-level studies of diverse polymer materials. While significant advances have been made in designing conformation generation methods for small molecules and proteins, these methods struggle to generate polymer conformations due to their unique structural characteristics. Meanwhile, the scarcity of polymer conformation datasets further limits progress, making this important area largely unexplored. In this work, we propose PolyConf, a pioneering tailored polymer conformation generation method that leverages hierarchical generative models to unlock new possibilities. Specifically, we decompose the polymer conformation into a series of local conformations (i.e., the conformations of its repeating units), generating these local conformations through an autoregressive model, and then generating their orientation transformations via a diffusion model to assemble them into the complete polymer conformation. Moreover, we develop the first benchmark with a high-quality polymer conformation dataset derived from molecular dynamics simulations to boost related research in this area. The comprehensive evaluation demonstrates that PolyConf consistently outperforms existing conformation generation methods, thus facilitating advancements in polymer modeling and simulation. The whole work is available at https://polyconf-icml25.github.io.} }
Endnote
%0 Conference Paper %T PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models %A Fanmeng Wang %A Wentao Guo %A Qi Ou %A Hongshuai Wang %A Haitao Lin %A Hongteng Xu %A Zhifeng Gao %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-wang25ah %I PMLR %P 63002--63015 %U https://proceedings.mlr.press/v267/wang25ah.html %V 267 %X Polymer conformation generation is a critical task that enables atomic-level studies of diverse polymer materials. While significant advances have been made in designing conformation generation methods for small molecules and proteins, these methods struggle to generate polymer conformations due to their unique structural characteristics. Meanwhile, the scarcity of polymer conformation datasets further limits progress, making this important area largely unexplored. In this work, we propose PolyConf, a pioneering tailored polymer conformation generation method that leverages hierarchical generative models to unlock new possibilities. Specifically, we decompose the polymer conformation into a series of local conformations (i.e., the conformations of its repeating units), generating these local conformations through an autoregressive model, and then generating their orientation transformations via a diffusion model to assemble them into the complete polymer conformation. Moreover, we develop the first benchmark with a high-quality polymer conformation dataset derived from molecular dynamics simulations to boost related research in this area. The comprehensive evaluation demonstrates that PolyConf consistently outperforms existing conformation generation methods, thus facilitating advancements in polymer modeling and simulation. The whole work is available at https://polyconf-icml25.github.io.
APA
Wang, F., Guo, W., Ou, Q., Wang, H., Lin, H., Xu, H. & Gao, Z.. (2025). PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:63002-63015 Available from https://proceedings.mlr.press/v267/wang25ah.html.

Related Material