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

2026-01-27

AI Summary

Current generative models struggle to accurately capture the intricate interactions between enzyme binding pockets and substrates, limiting the design of functionally specific enzymes. To address this challenge, this work proposes EnzyPGM, a novel framework that enables the first end-to-end joint generation of enzyme pockets conditioned on both substrate structures and functional priors. The method introduces a Residue–Atom dual-scale Attention mechanism (RBA) and a Residue Functional Fusion module (RFF) to explicitly model fine-grained interactions between pocket residues and substrate atoms. Furthermore, the authors curate EnzyPock, a large-scale enzyme–pocket dataset, to support training and evaluation. Experiments demonstrate that EnzyPGM significantly outperforms baseline methods on EnzyPock, achieving an average binding energy reduction of 0.47 kcal/mol compared to EnzyGen, thereby substantially enhancing the performance of substrate-specific enzyme design.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 the generation of enzymes 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 83,062 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 of 0.47 kcal/mol over EnzyGen, showing its superior performance on substrate-specific enzyme design. The code and dataset will be released later.

Problem

• enzyme design
• substrate-binding pocket
• pocket-substrate interaction
• protein engineering
• generative model

Innovation

• pocket-conditioned generative model
• residue-atom bi-scale attention
• enzyme-substrate interaction
• substrate-specific enzyme design
• functional protein generation