Harnessing generative AI to decode enzyme catalysis and evolution for enhanced engineering

Abstract

Enzymes, as paramount protein catalysts, occupy a central role in fostering remarkable progress across numerous fields. However, the intricacy of sequence-function relationships continues to obscure our grasp of enzyme behaviors and curtails our capabilities in rational enzyme engineering. Generative artificial intelligence (AI), known for its proficiency in handling intricate data distributions, holds the potential to offer novel perspectives in enzyme research. Generative models could discern elusive patterns within the vast sequence space and uncover new functional enzyme sequences. This review highlights the recent advancements in employing generative AI for enzyme sequence analysis. We delve into the impact of generative AI in predicting mutation effects on enzyme fitness, catalytic activity, and stability, rationalizing the laboratory evolution of de novo enzymes, decoding protein sequence semantics, and its applications in enzyme engineering. Notably, the prediction of catalytic activity and stability of enzyme using natural protein sequences serves as a vital link, indicating how enzyme catalysis shapes enzyme evolution. Overall, we foresee that the integration of generative AI into enzyme studies will remarkably enhance our knowledge of enzymes and expedite the creation of superior biocatalysts.

Merits and Demerits of Machine Learning of Ferroelectric, Flexoelectric, and Electrolytic Properties of Ceramic Materials

“…However, even in this case, consideration by human researchers on the importance of dislocation density is needed beforehand. In future, however, generative pre-trained AI may possibly overcome the difficulty and predict unknown optimal conditions for solid electrolytes beyond the pre-existing parameter space of the experimental data [ 185 , 186 , 187 ]. For example, generative AI pre-trained with many literatures on ionic conductivity could point out the importance of dislocation density and could predict all-dislocation-ceramics even without referring to the papers of all-dislocation-ceramics.…”

Preface: paving the road for AI in molecular sciences

“…[ 3 ], they proposed a robotic AI-Chemist which is characterized by high-throughput data acquisition, interactive calibration of theoretical and experimental data, and validation of literatures, with the aim to establish an AI-ready database covering massive scientific data and integrating chemical knowledge. The Review article by Wen Jun Xie and Arieh Warshel [ 4 ] focuses on how to employ generative AI for enzyme sequence analysis as well as enzyme engineering, which is expected to significantly enhance our knowledge of enzymes and expedite the creation of superior biocatalysts.…”