AlphaFold2 and Deep Learning for Elucidating Enzyme Conformational Flexibility and Its Application for Design

The recent success of AlphaFold2 (AF2) and other deeplearning(DL) tools in accurately predicting the folded three-dimensional (3D)structure of proteins and enzymes has revolutionized the structuralbiology and protein design fields. The 3D structure indeed revealskey information on the arrangement of the catalytic machinery of enzymesand which structural elements gate the active site pocket. However,comprehending enzymatic activity requires a detailed knowledge ofthe chemical steps involved along the catalytic cycle and the explorationof the multiple thermally accessible conformations that enzymes adoptwhen in solution. In this Perspective, some of the recent studiesshowing the potential of AF2 in elucidating the conformational landscapeof enzymes are provided. Selected examples of the key developmentsof AF2-based and DL methods for protein design are discussed, as wellas a few enzyme design cases. These studies show the potential ofAF2 and DL for allowing the routine computational design of efficientenzymes.

Automated summary

The recent success of AlphaFold2 (AF2) and other deep learning tools in accurately predicting the folded three-dimensional structure of proteins and enzymes has revolutionized the field of structural biology and protein design. However, understanding enzymatic activity requires detailed knowledge of the chemical steps involved in the catalytic cycle and the exploration of the multiple conformations that enzymes adopt in solution. This Perspective highlights the potential of AF2 in elucidating the conformational landscape of enzymes and discusses key developments in AF2-based and deep learning methods for protein design, as well as several enzyme design cases. These studies demonstrate the potential of AF2 and deep learning for routine computational design of efficient enzymes.