Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate

Jiahe Du, Kaixiong Zhou, Xinyu Hong, Zhaozhuo Xu, Jinbo Xu, Xiao Huang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14719-14734, 2025.

Abstract

Generating novel enzymes for target molecules in zero-shot scenarios is a fundamental challenge in biomaterial synthesis and chemical production. Without known enzymes for a target molecule, training generative models becomes difficult due to the lack of direct supervision. To address this, we propose a retrieval-augmented generation method that uses existing enzyme-substrate data to guide enzyme design. Our method retrieves enzymes with substrates that share structural similarities with the target molecule, leveraging functional similarities in catalytic activity. Since none of the retrieved enzymes directly catalyze the target molecule, we use a conditioned discrete diffusion model to generate new enzymes based on the retrieved examples. An enzyme-substrate relationship classifier guides the generation process to ensure optimal protein sequence distributions. We evaluate our model on enzyme design tasks with diverse real-world substrates and show that it outperforms existing protein generation methods in catalytic capability, foldability, and docking accuracy. Additionally, we define the zero-shot substrate-specified enzyme generation task and introduce a dataset with evaluation benchmarks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-du25i, title = {Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate}, author = {Du, Jiahe and Zhou, Kaixiong and Hong, Xinyu and Xu, Zhaozhuo and Xu, Jinbo and Huang, Xiao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {14719--14734}, 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/du25i/du25i.pdf}, url = {https://proceedings.mlr.press/v267/du25i.html}, abstract = {Generating novel enzymes for target molecules in zero-shot scenarios is a fundamental challenge in biomaterial synthesis and chemical production. Without known enzymes for a target molecule, training generative models becomes difficult due to the lack of direct supervision. To address this, we propose a retrieval-augmented generation method that uses existing enzyme-substrate data to guide enzyme design. Our method retrieves enzymes with substrates that share structural similarities with the target molecule, leveraging functional similarities in catalytic activity. Since none of the retrieved enzymes directly catalyze the target molecule, we use a conditioned discrete diffusion model to generate new enzymes based on the retrieved examples. An enzyme-substrate relationship classifier guides the generation process to ensure optimal protein sequence distributions. We evaluate our model on enzyme design tasks with diverse real-world substrates and show that it outperforms existing protein generation methods in catalytic capability, foldability, and docking accuracy. Additionally, we define the zero-shot substrate-specified enzyme generation task and introduce a dataset with evaluation benchmarks.} }
Endnote
%0 Conference Paper %T Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate %A Jiahe Du %A Kaixiong Zhou %A Xinyu Hong %A Zhaozhuo Xu %A Jinbo Xu %A Xiao Huang %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-du25i %I PMLR %P 14719--14734 %U https://proceedings.mlr.press/v267/du25i.html %V 267 %X Generating novel enzymes for target molecules in zero-shot scenarios is a fundamental challenge in biomaterial synthesis and chemical production. Without known enzymes for a target molecule, training generative models becomes difficult due to the lack of direct supervision. To address this, we propose a retrieval-augmented generation method that uses existing enzyme-substrate data to guide enzyme design. Our method retrieves enzymes with substrates that share structural similarities with the target molecule, leveraging functional similarities in catalytic activity. Since none of the retrieved enzymes directly catalyze the target molecule, we use a conditioned discrete diffusion model to generate new enzymes based on the retrieved examples. An enzyme-substrate relationship classifier guides the generation process to ensure optimal protein sequence distributions. We evaluate our model on enzyme design tasks with diverse real-world substrates and show that it outperforms existing protein generation methods in catalytic capability, foldability, and docking accuracy. Additionally, we define the zero-shot substrate-specified enzyme generation task and introduce a dataset with evaluation benchmarks.
APA
Du, J., Zhou, K., Hong, X., Xu, Z., Xu, J. & Huang, X.. (2025). Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:14719-14734 Available from https://proceedings.mlr.press/v267/du25i.html.

Related Material