Enzymatic reaction kinetics are central in analyzing enzymatic reaction mechanisms and target-enzyme optimization, and thus in biomanufacturing and other industries. The enzyme turnover number (k_cat) and Michaelis constant (K_m), key kinetic parameters for measuring enzyme catalytic efficiency, are crucial for analyzing enzymatic reaction mechanisms and the directed evolution of target enzymes. Experimental determination of k_cat and K_m is costly in terms of time, labor, and cost. To consider the intrinsic connection between k_cat and K_m and further improve the prediction performance_, we propose a universal pretrained multitask deep learning model, MPEK, to predict these parameters simultaneously while considering pH, temperature, and organismal information. Through testing on the same k_cat and K_m test datasets, MPEK demonstrated superior prediction performance over the previous models. Specifically, MPEK achieved the Pearson coefficient of 0.808 for predicting k_cat, improving ca. 14.6% and 7.6% compared to the DLKcat and UniKP models, and it achieved the Pearson coefficient of 0.777 for predicting K_m, improving ca. 34.9% and 53.3% compared to the Kroll_model and UniKP models. More importantly, MPEK was able to reveal enzyme promiscuity and was sensitive to slight changes in the mutant enzyme sequence. In addition, in three case studies, it was shown that MPEK has the potential for assisted enzyme mining and directed evolution. To facilitate in silico evaluation of enzyme catalytic efficiency, we have established a web server implementing this model, which can be accessed at http://mathtc.nscc-tj.cn/mpek.

Background: The sesquiterpene germacrene D is a highly promising product due to its wide variety of insecticidal activities and ability to serve as a precursor for many other sesquiterpenes. Biosynthesis of high value compounds through genome mining for synthases and metabolic engineering of microbial factories, especially Saccharomyces cerevisiae, has been proven to be an effective strategy. However, there have been no studies on the de novo synthesis of germacrene D from carbon sources in microbes. Hence, the construction of the S. cerevisiae cell factory to achieve high production of germacrene D is highly desirable. Results: We identified five putative sesquiterpene synthases (AcTPS1 to AcTPS5) from Acremonium chrysogenum and the major product of AcTPS1 characterized by in vivo, in vitro reaction and NMR detection was revealed to be (–)-germacrene D. After systematically comparing twenty-one germacrene D synthases, AcTPS1 was found to generate the highest amount of (–)-germacrene D and was integrated into the terpene precursor-enhancing yeast strain, achieving 376.2 mg/L of (–)-germacrene D. Iterative engineering was performed to improve the production of (–)-germacrene D, including increasing the copy numbers of AcTPS1, tHMG1 and ERG20, and downregulating or knocking out other inhibitory factors (such as erg9, rox1, dpp1). Finally, the optimal strain LSc81 achieved 1.94 g/L (–)-germacrene D in shake-flask fermentation and 7.9 g/L (–)-germacrene D in a 5-L bioreactor, which is the highest reported (–)-germacrene D titer achieved to date. Conclusion: We successfully achieved high production of (–)-germacrene D in S. cerevisiae through terpene synthase mining and metabolic engineering, providing an impressive example of microbial overproduction of high-value compounds.

γ-bisabolene is a monocyclic sesquiterpene with various biological activities; it has also been approved as a food additive. Additionally, the hydrogenated form of bisabolene is considered as a potential alternative to D2 diesel. Saccharomyces cerevisiae has the ability to produce a large amount of acetyl-CoA in both cytosol and peroxisomes, which serves as a precursor in terpene biosynthesis. In this study, AcTPS5 was identified as a new γ-bisabolene synthase. By expressing AcTPS5 and the mevalonate pathway in peroxisomes, γ-bisabolene titer was achieved at 125.0 mg/L. Deleting the peroxisome autophagy gene atg36 further improved γ-bisabolene production to 216.9 mg/L. The implementation of dual cytoplasmic–peroxisomal engineering further boosted γ-bisabolene production to 296.4 mg/L. Finally, through increasing the acetyl-CoA supply and down-regulating the expression of ERG9, γ-bisabolene production was achieved at 584.14 mg/L in shake-flask fermentation and 2.69 g/L in fed-batch fermentation, which is the highest reported production of γ-bisabolene to date. The strategy presented in this study provides an efficient approach for terpene production in S. cerevisiae.

In recent years, the widespread application of artificial intelligence algorithms in protein structure, function prediction, and de novo protein design has significantly accelerated the process of intelligent protein design and led to many noteworthy achievements. This advancement in protein intelligent design holds great potential to accelerate the development of new drugs, enhance the efficiency of biocatalysts, and even create entirely new biomaterials. Protein characterization is the key to the performance of intelligent protein design. However, there is no consensus on the most suitable characterization method for intelligent protein design tasks. This review describes the methods, characteristics, and representative applications of traditional descriptors, sequence-based and structure-based protein characterization. It discusses their advantages, disadvantages, and scope of application. It is hoped that this could help researchers to better understand the limitations and application scenarios of these methods, and provide valuable references for choosing appropriate protein characterization techniques for related research in the field, so as to better carry out protein research.

Enzyme catalytic efficiency (kcat/Km) is a key parameter for identifying high-activity enzymes. Recently, deep learning techniques have demonstrated the potential for fast and accurate kcat/Km prediction. However, three challenges remain: (i) the limited size of the available kcat/Km dataset hinders the development of deep learning models; (ii) the model predictions lack reliable confidence estimates; and (iii) models lack interpretable insights into enzyme-catalyzed reactions. To address these challenges, we proposed IECata, a kcat/Km prediction model that provides uncertainty estimation and interpretability. IECata collected a dataset of 11 815 kcat/Km entries from the BRENDA and SABIO-RK databases, along with an out-of-domain test dataset of 806 entries from the literature. By introducing evidential deep learning, IECata provides uncertainty estimates for kcat/Km predictions. Moreover, it uses a bilinear attention mechanism to focus on learning crucial local interactions to interpret the key residues and substrate atoms in enzyme-catalyzed reactions. Testing results indicate that the prediction performance of IECata exceeds that of state-of-the-art benchmark models. More importantly, it provides a reliable confidence assessment for these predictions. Case studies further highlight that the incorporation of uncertainty in screening for highly active enzymes can effectively increase the hit ratio, thereby improving the efficiency of experimental validation and accelerating directed enzyme evolution. To facilitate researchers’ use of IECata, we have developed an online prediction platform: http://mathtc.nscc-tj.cn/cataai/.