Machine learning and multiple linear regression models can predict ascorbic acid and polyphenol contents, and antioxidant activity in strawberries.

BACKGROUND: Strawberry is a rich source of antioxidants, including ascorbic acid (ASA) and polyphenols, which have numerous health benefits. Antioxidant content and activity are often determined manually using laboratory equipment, which is destructive and time-consuming. This study constructs a prediction model for antioxidant compounds utilizing machine learning (ML) and multiple linear regression based on environmental, plant growth and agronomic fruit quality-related parameters as well as antioxidant levels. These were studied in three farms at two-week intervals during two years of cultivation. RESULTS: During the ML model screening, artificial neural network (ANN)-boosted models displayed a moderate coefficient of determination (R2) at 0.68-0.78 and relative root mean square error (RRMSE) at 3.8-4.8% in polyphenols and total ASA levels, as well as a high R2 of 0.96 and low RRMSE at <3.0% in antioxidant activity. Additionally, we developed variable selection models regarding the antioxidant activity, and variables two and five (environmental parameters and leaf length, respectively) with high accuracy were selected. The linear regression analysis between the actual and predicted data of antioxidants in the ANN-boosted models revealed high fitness with all parameters in almost all training, validation and test sets. Furthermore, environmental parameters are essential in developing such reliable models. CONCLUSION: We conclude that ANN-boosted, stepwise and double-Lasso regression models can predict antioxidant compounds with enhanced accuracy, and the relevant parameters can be easily acquired on-site without the need for any specific equipment. © 2024 Society of Chemical Industry.

C-terminal amino acids in the type I transmembrane domain of L-type lectin VIP36 affect γ-secretase susceptibility.

Regulated intramembrane proteolysis (RIP) is a two-step processing mechanism for transmembrane proteins consisting of ectodomain shedding (shedding), which removes the extracellular domain through juxtamembrane processing and intramembrane proteolysis, which processes membrane-anchored shedding products within the transmembrane domain. RIP irreversibly converts one transmembrane protein into multiple soluble proteins that perform various physiological functions. The only requirement for the substrate of γ-secretase, the major enzyme responsible for intramembrane proteolysis of type I transmembrane proteins, is the absence of a large extracellular domain, and it is thought that γ-secretase can process any type I membrane protein as long as it is shed. In the present study, we showed that the shedding susceptible type I membrane protein VIP36 (36 kDa vesicular integral membrane protein) and its homolog, VIPL, have different γ-secretase susceptibilities in their transmembrane domains. Analysis of the substitution mutants suggested that γ-secretase susceptibility is regulated by C-terminal amino acids in the transmembrane domain. We also compared the transmembrane domains of several shedding susceptible membrane proteins and found that each had a different γ-secretase susceptibility. These results suggest that the transmembrane domain is not simply a stretch of hydrophobic amino acids but is an important element that regulates membrane protein function by controlling the lifetime of the membrane-anchored shedding product.

Culture-based analysis of fungi in leaves after the primary and secondary fermentation processes during Ishizuchi-kurocha production and lactate assimilation of P. kudriavzevii.

Ishizuchi-kurocha is a Japanese traditional fermented tea that is produced by primary aerobic and secondary fermentation steps. The secondary fermentation step of Ishizuchi-kurocha is mainly mediated through lactic acid bacteria. Here, we performed quantitative analyses of the culturable fungal communities at each step and identified several morphologically representative fungal isolates. While filamentous fungi (median, 3.2 × 107 CFU/g sample) and yeasts (median, 3.7 × 107 CFU/g) were both detected after the primary fermentation step, only yeasts (median, 1.6 × 107 CFU/g) were detected in the end of the secondary fermentation step, suggesting that the fungal community in tea leaves are dramatically changed between the two steps. Pichia kudriavzevii and Pichia manshurica, the prevalent fungal species at the end of the secondary fermentation step, grew well in exudate from the secondary fermentation step. P. kudriavzevii also grew well in media containing d- or l-lactate as the sole carbon source. The growth of the disruptant of cyb2A encoding a cytochrome b2 lactate dehydrogenase in P. kudriavzevii was severely impaired on medium supplemented with l-lactate, but not d-lactate, suggesting that Cyb2Ap plays a crucial role in the use of l-lactate, and P. kudriavzevii efficiently uses both l- and d-lactate as carbon sources. Thus, lactate assimilation seems to be a key phenotype to become a prevalent species in the secondary fermentation step, and Cyb2Ap has a pivotal role in l-lactate metabolism in P. kudriavzevii. Further understanding and engineering of P. kudriavzevii and P. manshurica will contribute to the control of lactic acid bacteria fermentation during the fermented tea production and also to other industrial uses.

Draft Genome Sequence of the Yeast Pichia manshurica YM63, a Participant in Secondary Fermentation of Ishizuchi-Kurocha, a Japanese Fermented Tea.

Pichia manshurica is common in fermentation; however, genome analysis has never been reported for the species. This yeast plays a role in the secondary fermentation of Ishizuchi-kurocha, a traditional Japanese fermented tea. This paper presents the draft genome sequence of P. manshurica YM63, isolated from the leaves of fermented tea.