Artificial intelligence in enzyme catalysis: Emerging trends and applications in biocatalyst engineering
Open Access
- 30 March 2026
- journal article
- Published by Wiley in The Canadian Journal of Chemical Engineering
- Vol. 104 (10) , 5328-5349
Abstract
This study systematically explores the applications of artificial intelligence (AI) in enzyme research, emphasizing its role in enzyme design, catalytic function prediction, stability, discovery of novel enzymes, and process optimization. Using bibliometric review techniques, we quantified research subfields, mapped global scientific trends, and identified the machine learning (ML) approaches most frequently employed in enzymology. Our analysis reveals that algorithms such as random forests, support vector machines, decision trees, and K‐nearest neighbours are predominantly applied to predict protein solubility, enzyme stability after mutations, catalytic mechanisms, and drug‐enzyme interactions. These findings demonstrate how AI enables more accurate predictions of enzymatic behaviour, accelerates drug discovery pipelines, and supports the identification of new metabolic pathways for industrial biotechnology. Beyond mapping current applications, this work highlights significant challenges, including the scarcity of high‐quality datasets and the limited generalization of models across enzyme classes. Nonetheless, the results underscore the transformative potential of AI when integrated into experimental workflows, particularly with advances in laboratory automation and the emerging synergy between AI and quantum computing. By consolidating state‐of‐the‐art knowledge and identifying future directions, this study contributes to guiding research strategies in data‐driven enzyme engineering and promotes the development of sustainable biotechnological solutions.Keywords
Funding Information
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (00x0ma614)
- Fundação Cearense de Apoio ao Desenvolvimento Científico e Tecnológico (PS1‐0186‐00216.01.00/21)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (307454/2022‐3)
This publication has 197 references indexed in Scilit:
- Design Challenges for Machine/Deep Learning Algorithms2023
- Machine‐Learning‐Assisted Nanozyme Design: Lessons from Materials and Engineered EnzymesAdvanced Materials, 2023
- Applications of Bioinformatics Tools in Medicinal Biology and Biotechnology2023
- Machine learning‐based prediction of enzyme substrate scope: Application to bacterial nitrilasesProteins: Structure, Function, and Bioinformatics, 2020
- Machine Learning Enables Selection of Epistatic Enzyme Mutants for Stability Against Unfolding and Detrimental AggregationChemBioChem, 2020
- Creating Flavin Reductase Variants with Thermostable and Solvent‐Tolerant Properties by Rational‐Design EngineeringChemBioChem, 2019
- Accurate and cost‐effective prediction of HBsAg titer in industrial scale fermentation process of recombinant Pichia pastoris by using neural network based soft sensorBiotechnology and Applied Biochemistry, 2019
- Can Machine Learning Revolutionize Directed Evolution of Selective Enzymes?Advanced Synthesis & Catalysis, 2019
- Classification Models for Predicting Cytochrome P450 Enzyme‐Substrate SelectivityMolecular Informatics, 2012
- The linear interaction energy method for the prediction of protein stability changes upon mutationProteins: Structure, Function, and Bioinformatics, 2011