Elucidating enzyme–substrate specificity through co-folding foundation model
Preprint
Abstract
Enzymatic catalysis relies on precise structural and chemical complementarity, yet systematically mapping enzyme-substrate interactions remains a critical bottleneck. While structure-aware methods have advanced functional annotation, their reliance on predefined binding pockets and rigid-body docking fails to capture the ligand-induced conformational changes essential for catalytic turnover. Here we introduce Boltz2ESI, an end-to-end framework that predicts enzyme–substrate interactions by leveraging structural knowledge learned by a biomolecular foundation model. Through native co-folding, the framework inherently captures active-site plasticity without requiring predefined pocket annotations. Integrating these learned biophysical priors with global evolutionary context and geometric molecular descriptors, Boltz2ESI consistently outperforms state-of-the-art sequence-based and rigid-docking approaches. Extensive validation demonstrates that the framework accurately discriminates tight sub-family specificities, enabling effective candidate prioritization for biosynthetic pathway elucidation, as demonstrated on the withanolide pathway. Ultimately, this structure-dynamic approach establishes an actionable foundation for accelerating rational biocatalyst discovery and large-scale pathway de-orphaning.Keywords
Funding Information
- Torrey Coast Foundation
- National Research Foundation of Korea (NRF-2023R1A2C2004376)
This publication has 41 references indexed in Scilit:
- Enzyme functional classification using artificial intelligenceTrends in Biotechnology, 2025
- Toward an integrated omics approach for plant biosynthetic pathway discovery in the age of AITrends in Biochemical Sciences, 2025
- S‐PLM: Structure‐Aware Protein Language Model via Contrastive Learning Between Sequence and StructureAdvanced Science, 2024
- Building Enzymes through Design and EvolutionACS Catalysis, 2023
- Binding Affinity Determines Substrate Specificity and Enables Discovery of Substrates for N-MyristoyltransferasesACS Catalysis, 2021
- Machine learning‐based prediction of enzyme substrate scope: Application to bacterial nitrilasesProteins: Structure, Function, and Bioinformatics, 2020
- Exploration and Evaluation of Machine Learning-Based Models for Predicting Enzymatic ReactionsJournal of Chemical Information and Modeling, 2020
- Active Site Plasticity of a Computationally Designed Retro‐Aldolase EnzymeChemCatChem, 2014
- Evolutionary Optimization of Computationally Designed Enzymes: Kemp Eliminases of the KE07 SeriesJournal of Molecular Biology, 2010
- Basic Local Alignment Search ToolJournal of Molecular Biology, 1990