Deep Learning-Based Self-Adaptive Evolution of Enzymes

Abstract Biocatalysis has been widely used to prepare drug leads and intermediates. Enzymatic synthesis has advantages, mainly in terms of strict chirality and regional selectivity compared with chemical methods. However, the enzymatic properties of wild-type enzymes may or may not meet the requirements for biopharmaceutical applications. Therefore, protein engineering is required to improve their catalytic activities. Thanks to advances in algorithmic models and the accumulation of immense biological data, artificial intelligence can provide novel approaches for the functional evolution of enzymes. Deep learning has the advantage of learning functions that can predict the properties of previously unknown protein sequences. Deep learning-based computational algorithms can intelligently navigate the sequence space and reduce the screening burden during evolution. Thus, intelligent computational design combined with laboratory evolution is a powerful and potentially versatile strategy for developing enzymes with novel functions. Herein, we introduce and summarize deep-learning-assisted enzyme functional adaptive evolution strategies based on recent studies on the application of deep learning in enzyme design and evolution. Altogether, with the developments of technology and the accumulation of data for the characterization of enzyme functions, artificial intelligence may become a powerful tool for the design and evolution of intelligent enzymes in the future.