Recently, the Feed Enzyme Engineering Innovation Research Team in the Institute of Animal Science (IAS-CAAS) and the team of Microbial Protein Design and Intelligent Manufacture in the Biotechnology Research Institute, Chinese Academy of Agricultural Sciences (BRI-CAAS) worked together to develop a new strategy to improve the catalytic activity of glycoside hydrolase based on deep neural networks and molecular evolution analysis. The findings are published in the journal of  Science Bulletin .

Glycoside hydrolase is the main enzyme system of polysaccharide degradation, which is widely used in food, feed, agricultural and sideline product processing and waste degradation industry, and has important application value. The market demand for glycoside hydrolase is increasing year by year, but how to improve the catalytic efficiency of glycoside hydrolase and maximize its catalytic potential remains to be a challenging problem.

Fig.1 Computational workflow for enhancing the catalytic efficiency of glycoside hydrolase proteins based on deep neural networks and molecular evolution.

The MECE platform includes DeepGH, a deep learning model that is able to identify GH families and functional residues. This model was developed utilizing 119 GH family protein sequences obtained from the Carbohydrate-Active enZYmes (CAZy) database. After undergoing ten-fold cross-validation, the DeepGH models exhibited a predictive accuracy of 96.73%. The utilization of gradient-weighted class activation mapping (Grad-CAM) was used to aid us in comprehending the classification features, which in turn facilitated the creation of enzyme mutants. As a result, the MECE platform was validated with the development of CHIS1754-MUT7, a mutant that boasts seven amino acid substitutions. The  k _cat/ K _m of CHIS1754-MUT7 was found to be 23.53 times greater than that of the wild type CHIS1754. Due to its high computational efficiency and low experimental cost, this method offers significant advantages and presents a novel approach for the intelligent design of enzyme catalytic efficiency. As a result, it holds great promise for a wide range of applications.

Huoqing Huang, Jian Tian, and Feifei Guan are co-corresponding authors of the paper. Hanqing Liu, Feifei Guan, Tuoyu Liu and Lixin Yang are co-first authors of the paper.

The online version available at：https://www.sciencedirect.com/science/article/abs/pii/S2095927323006746