---
title: "EnzyPGM: Pocket-conditioned Generative Model for Substrate-specific Enzyme Design"
authors:
  - "Zefeng Lin"
  - "Zhihang Zhang"
  - "Weirong Zhu"
  - "Tongchang Han"
  - "Xianyong Fang"
  - "Tianfan Fu"
  - "Xiaohua Xu"
doi: "10.24963/ijcai.2026/622"
url: "https://ijcai.org/proceedings/2026/622"
pdf: "https://ijcai.org/proceedings/2026/0622.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5585-5593"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: Bioinformatics"
  - "Multidisciplinary Topics and Applications: Life sciences"
---

# EnzyPGM: Pocket-conditioned Generative Model for Substrate-specific Enzyme Design

Zefeng Lin, Zhihang Zhang, Weirong Zhu, Tongchang Han, Xianyong Fang, Tianfan Fu, Xiaohua Xu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5585-5593. DOI: [10.24963/ijcai.2026/622](https://doi.org/10.24963/ijcai.2026/622)

## Abstract

Designing enzymes with substrate-binding pockets is a critical challenge in protein engineering, as catalytic activity depends on the precise interaction between pockets and substrates. Currently, generative models dominate functional protein design but cannot model pocket-substrate interactions, which limits enzyme generation with precise catalytic environments. To address this issue, we propose EnzyPGM, a unified framework that jointly generates enzymes and substrate-binding pockets conditioned on functional priors and substrates, with a particular focus on learning accurate pocket–substrate interactions. At its core, EnzyPGM includes two main modules: a Residue-atom Bi-scale Attention (RBA) that jointly models intra-residue dependencies and fine-grained interactions between pocket residues and substrate atoms, and a Residue Function Fusion (RFF) that incorporates enzyme function priors into residue representations. Also, we curate EnzyPock, an enzyme–pocket dataset comprising 84,336 enzyme–substrate pairs across 1,036 four-level enzyme families. Extensive experiments demonstrate that EnzyPGM achieves state-of-the-art performance on EnzyPock. Notably, EnzyPGM reduces the average binding energy by 0.47 kcal/mol over EnzyGen, showing its superior performance on substrate-specific enzyme design. The code is available at https://github.com/John-Lin98/EnzyPGM.