BioStructNet: Structure-Based Network with Transfer Learning for Predicting Biocatalyst Functions

Abstract

Enzyme-substrate interactions are essential to both biological processes and industrial applications. Advanced machine learning techniques have significantly accelerated biocatalysis research, revolutionizing the prediction of biocatalytic activities and facilitating the discovery of novel biocatalysts. However, the limited availability of data for specific enzyme functions, such as conversion efficiency and stereoselectivity, presents challenges for prediction accuracy. In this study, we developed BioStructNet, a structure-based deep learning network that integrates both protein and ligand structural data to capture the complexity of enzyme-substrate interactions. Benchmarking studies with the different algorithms showed the enhanced predictive accuracy of BioStructNet. To further optimize the prediction accuracy for the small dataset, we implemented transfer learning in the framework, training a source model on a large dataset and fine-tuning it on a small, function-specific dataset, using the CalB dataset as a case study. The model performance was validated by comparing the attention heat maps generated by the BioStructNet interaction module, with the enzyme substrate interactions revealed by enzyme-substrate complexes revealed from molecular simulations. BioStructNet would accelerate the discovery of functional enzymes for industrial use, particularly in cases where the training datasets for machine learning are small.