A Regressor-Guided Graph Diffusion Model for Predicting Enzyme Mutations to Enhance Turnover Number

Enzymes are biological catalysts that can accelerate chemical reactions compared to uncatalyzed reactions in aqueous environments. Their catalytic efficiency is quantified by the turnover number (k<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf>), a parameter in enzyme kinetics. Enhancing enzyme activity is important for optimizing slow chemical reactions, with far-reaching implications for both research and industrial applications. However, traditional wet-lab methods for measuring and optimizing enzyme activity are often resource-intensive and time-consuming. To address these limitations, we introduce k<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf>Diffuser, a novel regressor-guided diffusion model designed to predict and improve enzyme turnover numbers. Our approach innovatively reformulates enzyme mutation prediction as a protein inverse folding task, thereby establishing a direct link between structural prediction and functional optimization. k<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf>Diffuser is a graph diffusion model guided by a regressor, enabling the prediction of amino acid mutations at multiple random positions simultaneously. Evaluations on BERENDA dataset shows that k<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf>Diffuser can achieve a ∆logk<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf> of 0.209, outperforming state-of-the-art methods like ProteinMPNN, PiFold, GraDe-IF in improving enzyme turnover numbers. Additionally, k<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf>Diffuser maintains high structural fidelity with a recovery rate of 0.716, pLDDT score of 92.515, RMSD of 3.764, and TM-score of 0.934, demonstrating its ability to generate enzyme variants with enhanced activity while preserving essential structural properties. Overall, k<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cat</inf>Diffuser represents a more efficient and targeted approach to enhancing enzyme activity. The code is available at https://github.com/xz32yu/KcatDiffuser.