Machine Learning Empowers Enzyme Discovery, Structure Prediction, Engineering, and Design

Abstract Enzymes are efficient and selective biocatalysts, yet obtaining enzymes with desired properties remains challenging due to vast sequence spaces, incomplete functional annotation, limited structural information, and costly experimental screening. Machine learning (ML) offers a powerful complement to address these limitations. For enzyme discovery, sequence and structural representations enhance candidate retrieval and functional annotation, while property predictors support further prioritization. For structure prediction, ML methods have progressed from the use of evolutionary information to protein language model-based prediction and all-atom biomolecular modeling, broadening computational access from individual protein structures to multicomponent assemblies. For enzyme engineering, ML-guided strategies leverage experimental measurements and pretrained representations to predict and prioritize variants, supporting iterative optimization of fitness landscapes. Beyond optimizing existing enzymes, ML-enabled enzyme design further enables the construction of sequences and structures whose functional, structural, or catalytic properties are specified by design constraints. Despite these advances, persistent challenges remain in data quality, model generalization, conformational dynamics, and the correspondence between computational predictions and catalytic function. We conclude that closer integration of ML with mechanistic analysis and experimental validation is essential for developing robust and applicable workflows that span enzyme discovery, structure prediction, engineering, and design.