[Advances in machine learning for predicting protein functions].

Proteins play a variety of functional roles in cellular activities and are indispensable for life. Understanding the functions of proteins is crucial in many fields such as medicine and drug development. In addition, the application of enzymes in green synthesis has been of great interest, but the high cost of obtaining specific functional enzymes as well as the variety of enzyme types and functions hamper their application. At present, the specific functions of proteins are mainly determined through tedious and time-consuming experimental characterization. With the rapid development of bioinformatics and sequencing technologies, the number of protein sequences that have been sequenced is much larger than those can be annotated, thus developing efficient methods for predicting protein functions becomes crucial. With the rapid development of computer technology, data-driven machine learning methods have become a promising solution to these challenges. This review provides an overview of protein function and its annotation methods as well as the development history and operation process of machine learning. In combination with the application of machine learning in the field of enzyme function prediction, we present an outlook on the future direction of efficient artificial intelligence-assisted protein function research.

Constructing an Intensified UDP Recycling System for the Glycosylation of Natural Products by Phosphorylation of Byproduct Fructose.

UDP-glucosyltransferase can be coupled with sucrose synthase to construct a two-enzyme UDP (UDP-2E) recycling system for glucosylation of natural products with inexpensive sucrose as the consumed substrate. However, sucrose hydrolysis leads to the accumulation of fructose as a byproduct, which decreases the atom economy of sucrose and suppresses in situ UDP recycling. In this study, a polyphosphate-dependent glucokinase was demonstrated to convert fructose to fructose-6-phosphate independent of expensive ATP for the first time. Then the glucokinase was introduced into the UDP-2E recycling system to construct a modified three-enzyme UDP (UDP-3E) recycling system, which showed enhanced glucosylation efficiency of triterpenoids by fructose phosphorylation to accelerate sucrose hydrolysis and UDP recycling. Finally, by further introducing a phosphofructokinase into the UDP-3E recycling system, we transformed fructose-6-phosphate into fructose-1,6-diphosphate, demonstrating that the UDP-3E recycling system can be coupled with extra enzymes to obtain final products with high added-value without compromising the glycosylation efficiency.