Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency

Chentong Wang, Yannan Qu, Zhangzhi Peng, Yukai Wang, Hongli Zhu, Dachuan Chen, Longxing Cao
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51376-51395, 2024.

Abstract

Diffusion-based generative models have been successfully employed to create proteins with novel structures and functions. However, the construction of such models typically depends on large, pre-trained structure prediction networks, like RFdiffusion. In contrast, alternative models that are trained from scratch, such as FrameDiff, still fall short in performance. In this context, we introduce Proteus, an innovative deep diffusion network that incorporates graph-based triangle methods and a multi-track interaction network, eliminating the dependency on structure prediction pre-training with superior efficiency. We have validated our model’s performance on de novo protein backbone generation through comprehensive in silico evaluations and experimental characterizations, which demonstrate a remarkable success rate. These promising results underscore Proteus’s ability to generate highly designable protein backbones efficiently. This capability, achieved without reliance on pre-training techniques, has the potential to significantly advance the field of protein design.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-wang24bi, title = {Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency}, author = {Wang, Chentong and Qu, Yannan and Peng, Zhangzhi and Wang, Yukai and Zhu, Hongli and Chen, Dachuan and Cao, Longxing}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {51376--51395}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/wang24bi/wang24bi.pdf}, url = {https://proceedings.mlr.press/v235/wang24bi.html}, abstract = {Diffusion-based generative models have been successfully employed to create proteins with novel structures and functions. However, the construction of such models typically depends on large, pre-trained structure prediction networks, like RFdiffusion. In contrast, alternative models that are trained from scratch, such as FrameDiff, still fall short in performance. In this context, we introduce Proteus, an innovative deep diffusion network that incorporates graph-based triangle methods and a multi-track interaction network, eliminating the dependency on structure prediction pre-training with superior efficiency. We have validated our model’s performance on de novo protein backbone generation through comprehensive in silico evaluations and experimental characterizations, which demonstrate a remarkable success rate. These promising results underscore Proteus’s ability to generate highly designable protein backbones efficiently. This capability, achieved without reliance on pre-training techniques, has the potential to significantly advance the field of protein design.} }
Endnote
%0 Conference Paper %T Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency %A Chentong Wang %A Yannan Qu %A Zhangzhi Peng %A Yukai Wang %A Hongli Zhu %A Dachuan Chen %A Longxing Cao %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-wang24bi %I PMLR %P 51376--51395 %U https://proceedings.mlr.press/v235/wang24bi.html %V 235 %X Diffusion-based generative models have been successfully employed to create proteins with novel structures and functions. However, the construction of such models typically depends on large, pre-trained structure prediction networks, like RFdiffusion. In contrast, alternative models that are trained from scratch, such as FrameDiff, still fall short in performance. In this context, we introduce Proteus, an innovative deep diffusion network that incorporates graph-based triangle methods and a multi-track interaction network, eliminating the dependency on structure prediction pre-training with superior efficiency. We have validated our model’s performance on de novo protein backbone generation through comprehensive in silico evaluations and experimental characterizations, which demonstrate a remarkable success rate. These promising results underscore Proteus’s ability to generate highly designable protein backbones efficiently. This capability, achieved without reliance on pre-training techniques, has the potential to significantly advance the field of protein design.
APA
Wang, C., Qu, Y., Peng, Z., Wang, Y., Zhu, H., Chen, D. & Cao, L.. (2024). Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:51376-51395 Available from https://proceedings.mlr.press/v235/wang24bi.html.

Related Material