DEKP: a deep learning model for enzyme kinetic parameter prediction based on pretrained models and graph neural networks

• Published in: Briefings in bioinformatics Vol. 26; no. 2
• Main Authors: Wang, Yizhen, Cheng, Li, Zhang, Yanyun, Cao, Yujia, Alghazzawi, Daniyal
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 04.03.2025
• Subjects: Deep Learning; Enzymes - chemistry; Enzymes - genetics; Enzymes - metabolism; Graph Neural Networks; Kinetics; Neural Networks, Computer; Problem Solving Protocol; pretrained model; deep learning; enzyme kinetic parameters; graph neural network
• ISSN: 1467-5463; 1477-4054; 1477-4054
• DOI: 10.1093/bib/bbaf187

The prediction of enzyme kinetic parameters is crucial for screening enzymes with high catalytic efficiency and desired characteristics to catalyze natural or non-natural reactions. Data-driven machine learning models have been explored to reduce experimental cost and speed up the enzyme design process. However, the prediction performance is still subject to significant limitations due to the variance in sequence similarity between training and testing datasets. In this work, we introduce DEKP, an integrated deep learning approach enzyme kinetic parameter prediction. It leverages pretrained models of protein sequences and incorporates enhanced graph neural networks that provide comprehensive representation of protein structural features. This novel approach can effectively alleviate the performance degradation caused by sequence similarity variation. Moreover, it provides sensitive detection of changes in catalytic efficiency due to enzyme mutations. Experiments validate that DEKP outperforms existing models in predicting enzyme kinetic parameters. This work is expected to significantly improve the performance of the enzyme screening process and provide a robust tool for enzyme-directed evolution research.