NYUS.2: an automated machine learning prediction model for the large-scale real-time simulation of grapevine freezing tolerance in North America.

Accurate and real-time monitoring of grapevine freezing tolerance is crucial for the sustainability of the grape industry in cool climate viticultural regions. However, on-site data are limited due to the complexity of measurement. Current prediction models underperform under diverse climate conditions, which limits the large-scale deployment of these methods. We combined grapevine freezing tolerance data from multiple regions in North America and generated a predictive model based on hourly temperature-derived features and cultivar features using AutoGluon, an automated machine learning engine. Feature importance was quantified by AutoGluon and SHAP (SHapley Additive exPlanations) value. The final model was evaluated and compared with previous models for its performance under different climate conditions. The final model achieved an overall 1.36°C root-mean-square error during model testing and outperformed two previous models using three test cultivars at all testing regions. Two feature importance quantification methods identified five shared essential features. Detailed analysis of the features indicates that the model has adequately extracted some biological mechanisms during training. The final model, named NYUS.2, was deployed along with two previous models as an R shiny-based application in the 2022-23 dormancy season, enabling large-scale and real-time simulation of grapevine freezing tolerance in North America for the first time.

Roostocks/Scion/Nitrogen Interactions Affect Secondary Metabolism in the Grape Berry.

The present work investigates the interactions between soil content, rootstock, and scion by focusing on the effects of roostocks and nitrogen supply on grape berry content. Scions of Cabernet Sauvignon (CS) and Pinot Noir (PN) varieties were grafted either on Riparia Gloire de Montpellier (RGM) or 110 Richter (110R) rootstock. The 4 rooststock/scion combinations were fertilized with 3 different levels of nitrogen after fruit set. Both in 2013 and 2014, N supply increased N uptake by the plants, and N content both in vegetative and reproductory organs. Rootstock, variety and year affected berry weight at harvest, while nitrogen did not affect significantly this parameter. Grafting on RGM consistently increased berry weight compared to 110R. PN consistently produced bigger berries than CS. CS berries were heavier in 2014 than in 2013, but the year effect was less marked for PN berries. The berries were collected between veraison and maturity, separated in skin and pulp, and their content was analyzed by conventional analytical procedures and untargeted metabolomics. For anthocyanins, the relative quantitation was fairly comparable with both LC-MS determination and HPLC-DAD, which is a fully quantitative technique. The data show complex responses of the metabolite content (sugars, organic acids, amino acids, anthocyanins, flavonols, flavan-3-ols/procyanidins, stilbenes, hydroxycinnamic, and hydroxybenzoic acids) that depend on the rootstock, the scion, the vintage, the nitrogen level, the berry compartment. This opens a wide range of possibilities to adjust the content of these compounds through the choice of the roostock, variety and nitrogen fertilization.

Vine nitrogen status and volatile thiols and their precursors from plot to transcriptome level.

BACKGROUND: Volatile thiols largely contribute to the organoleptic characteristics and typicity of Sauvignon blanc wines. Among this family of odorous compounds, 3-sulfanylhexan-1-ol (3SH) and 4-methyl-4-sulfanylpentan-2-one (4MSP) have a major impact on wine flavor. These thiols are formed during alcoholic fermentation by the yeast from odorless, non-volatile precursors found in the berries and the must. The present study investigates the effects of vine nitrogen (N) status on 3SH and 4MSP content in Sauvignon blanc wine and on the glutathionylated and cysteinylated precursors of 3SH (Glut-3SH and Cys-3SH) in the berries and the must. This is paralleled by a RNA-seq analysis of gene expression in the berries. The impact of N supply on the expression of the glutathione-S-transferase 3 and 4 (VviGST3 and VviGST4) and the γ-glutamyltranspeptidase (VviGGT), considered as key genes in their biosynthesis, was also evaluated. RESULTS: N supply (N100 treatment) increased the 3SH content in wine while no effect was noticed on 4MSP level. Furthermore, N supply increased Glut-3SH levels in grape berries at late berry ripening stages, and this effect was highly significant in must at harvest. No significant effect of N addition was noticed on Cys-3SH concentration. The transcript abundance of the glutathione-S-transferases VviGST3 and VviGST4 and the γ-glutamyltranspeptidase (VviGGT), were similar between the control and the N100 treatment. New candidate genes which might be implicated in the biosynthetic pathway of 3SH precursors were identified by whole transcriptome shotgun sequencing (RNA-seq). CONCLUSIONS: High vine N status has a positive effect on 3SH content in wine through an increase of Glut-3SH levels in grape berries and must. Candidate GSTs and glutathione-S-conjugates type transporters involved in this stimulation were identified by RNA-seq analysis.

Vine Nitrogen Status Does Not Have a Direct Impact on 2-Methoxy-3-isobutylpyrazine in Grape Berries and Wines.

Methoxypyrazines (MP) constitute a large family of compounds that contribute to the vegetative varietal aroma of many grapevine varieties and wines. The berry content in 2-methoxy-3-isobutylpyrazine (IBMP), a major MP reminiscent of green-pepper aroma, can be influenced by environmental factors or cultural practices such as water status or mineral nutrition. To date, no study has investigated a possible direct effect of nitrogen (N) on IBMP synthesis without possible interference from water status and vigor variations. In this study, only vine nitrogen status was significantly different among treatments. Water status was controlled during the season, and vine vigor was similar among treatments. IBMP level was maximal at bunch closure and decreased during the season. There was no significant effect of nitrogen nutrition on this metabolite. Moreover, the expression profiles of VvOMT3 and VvOMT4, key genes in the IBMP biosynthetic pathway, were similar between treatments. This result indicates that when an effect of N on IBMP was found in previous studies, it was likely mediated through the modification of bunch-zone microclimate, induced by the higher vigor of high N-status vines.