Umami is an important widely-used taste component of food seasoning. Umami peptides are specific structural peptides endowing foods with a favorable umami taste. Laboratory approaches used to identify umami peptides are time-consuming and labor-intensive, which are not feasible for rapid screening. Here, we developed a novel peptide sequence-based umami peptide predictor, namely iUP-BERT, which was based on the deep learning pretrained neural network feature extraction method. After optimization, a single deep representation learning feature encoding method (BERT: bidirectional encoder representations from transformer) in conjugation with the synthetic minority over-sampling technique (SMOTE) and support vector machine (SVM) methods was adopted for model creation to generate predicted probabilistic scores of potential umami peptides. Further extensive empirical experiments on cross-validation and an independent test showed that iUP-BERT outperformed the existing methods with improvements, highlighting its effectiveness and robustness. Finally, an open-access iUP-BERT web server was built. To our knowledge, this is the first efficient sequence-based umami predictor created based on a single deep-learning pretrained neural network feature extraction method. By predicting umami peptides, iUP-BERT can help in further research to improve the palatability of dietary supplements in the future.

A bitter taste often identifies hazardous compounds and it is generally avoided by most animals and humans. Bitterness of hydrolyzed proteins is caused by the presence of bitter peptides. To improve palatability, bitter peptides need to be identified experimentally in a time-consuming and expensive process, before they can be removed or degraded. Here, we report the development of a machine learning prediction method, iBitter-DRLF, which is based on a deep learning pre-trained neural network feature extraction method. It uses three sequence embedding techniques, soft symmetric alignment (SSA), unified representation (UniRep), and bidirectional long short-term memory (BiLSTM). These were initially combined into various machine learning algorithms to build several models. After optimization, the combined features of UniRep and BiLSTM were finally selected, and the model was built in combination with a light gradient boosting machine (LGBM). The results showed that the use of deep representation learning greatly improves the ability of the model to identify bitter peptides, achieving accurate prediction based on peptide sequence data alone. By helping to identify bitter peptides, iBitter-DRLF can help research into improving the palatability of peptide therapeutics and dietary supplements in the future. A webserver is available, too.

Glycosylation is one of the most common and important modifications in natural products (NPs), which can alter the biological activities and properties of NPs, effectively increase structural diversity, and improve pharmacological activities. The biosynthesis of glycosylation in natural products involves multiple complex biological processes, which are coordinated by many enzymes. UDP-glycosyltransferases (UGTs) play a crucial role in glycosylation modification, and have attracted long-term and widespread research attention. UGTs can catalyze the O-, C-, S-, and N-glycosylation of different substrates, producing a variety of glycosides with broad biological activity, while improving the solubility, stability, bioavailability, pharmacological activity, and other functions of NPs. In recent years, the rapid development of synthetic biology and advanced manufacturing technologies, especially the widespread application of artificial intelligence in the field of synthetic biology, has led to a series of new discoveries in the biosynthesis of NP glycosides by UGT. This work summarizes the latest progress and challenges in the field of NP glycosylation, covering the research results and potential applications of glycosylated derivatives of terpenes, flavonoids, polyphenols, aromatic compounds, and other compounds in terms of biogenesis. Looking to the future, research may leverage artificial intelligence-driven synthetic biology techniques to decipher genes related to the synthetic pathway, which is expected to further promote the large-scale synthesis and application of glycosylated NPs, and increase the diversity of NPs in the pharmaceutical, functional food, and cosmetic industries.

Steviol glycosides (SGs) are high-intensity, zero-calorie natural sweeteners with demonstrated safety and potential health benefits, positioning them as ideal sucrose substitutes for metabolic disorder management. However, their broad application is limited by inherent drawbacks such as bitterness, low solubility, and inefficient production systems. This review provides a comprehensive summary of recent advances in SG research, covering their sources, properties, and bioactivities. A particular focus is placed on innovative bioproduction strategies—including enzyme engineering, metabolic pathway optimization, and sustainable extraction techniques. Strategies to overcome these challenges through sensory-function enhancement—including formulation and structural modification—are discussed. Furthermore, it highlights emerging trends like microbial chassis-based production and next-generation sweetener design, providing actionable insights for overcoming industrial bottlenecks. By integrating multidisciplinary advances in bioengineering, sensory science, and sustainable processing, this review offers a forward-looking perspective on the development and application of SGs as functional sweeteners in the global food industry.

Background: Eurotium cristatum (E. cristatum) is the probiotic fungus in Fu-brick tea, with which fermentation brings a unique flavor and taste and health-promoting effects. Tartary buckwheat leaves are rich in functional active substances such as flavonoids and phenolic compounds, yet are not effectively utilized. Methods: Tartary buckwheat leaves were processed into raw green tea first and subsequently fermented with E. cristatum to develop a novel fermented leaf tea. The tea quality was evaluated by the aspects of the sensory scores by E-tongue, the volatile compounds by HS-SPME-GC-MS, the non-volatile profile by biochemical and UPLC-MS/MS methods and the antioxidant activity by the colorimetric assay. Results: Fermented leaf tea displayed a golden yellow color, a unique “flower” aroma and a dark-tea taste, with an improved sensory acceptability. Fermentation raised the content of volatile heterocyclic and aromatic compounds, alkenes and other aromatic components, which produced a unique floral flavor. The proportion of sour, bitter and astringency accounting non-volatile compounds such as phenolic acids and amino acids decreased, while the proportion of umami and sweet accounting substances such as responsible amino acids increased. Fermented leaf tea displayed a relative stronger total antioxidant activity against ABTS. Conclusion: E. cristatum fermentation exerted positive effects on Tartary buckwheat leaf tea quality.

Titanium has been reported to have positive effects on crop growth and production in various species. However, the impact of titanium on the Tartary buckwheat crops has not yet been studied. Therefore, an experiment was conducted to investigate the effect of spraying different concentrations of ionic titanium on the growth, photosynthesis, and uptake of mineral nutrients in Tartary buckwheat. The results showed that the application of titanium significantly improved dry matter accumulation, internode diameter, main stem node, root length, root average diameter, root surface area, root volume, grains per plant, and weight of grains per plant. Additionally, chlorophyll and photosynthetic parameters showed improvement regardless of the concentration of titanium used. The study found that titanium accumulation was mainly in leaves. The content of titanium in leaves showed a significant positive correlation with K, Ca, Mg, Mn, Cu, Zn, and B. This suggests a potential synergistic relationship between titanium and minerals in Tartary buckwheat leaves. Furthermore, the study also observed a significant increase in the total accumulation of P, K, Ca, Mg, Mn, Cu, Zn, and B in Tartary buckwheat plants. Overall, this study provides evidence for the positive effects of titanium on Tartary buckwheat and offers a theoretical foundation for practical production.