terclim by ICS banner
IVES 9 IVES Conference Series 9 International Congress on Grapevine and Wine Sciences 9 2ICGWS-2023 9 Predicting provenance and grapevine cultivar implementing machine learning on vineyard soil microbiome data: implications in grapevine breeding

Predicting provenance and grapevine cultivar implementing machine learning on vineyard soil microbiome data: implications in grapevine breeding

Abstract

The plant rhizosphere microbial communities are an essential component of plant microbiota, which is crucial for sustaining the production of healthy crops. The main drivers of the composition of such communities are the growing environment and the planted genotype. Recent viticulture studies focus on understanding the effects of these factors on soil microbial composition since microbial biodiversity is an important determinant of plant phenotype, and of wine’s organoleptic properties. Microbial biodiversity of different wine regions, for instance, is an important determinant of wine terroir. While conventional methods for microbiome analysis are extensively used, application of modern Artificial Intelligence (AI) based methods could unravel non-linear associations between microbial taxa and environmental/plant genetic factors. Here we compare the performance of shallow and Deep Machine Learning methods to predict the geographical provenance and the planted grape cultivar solely based on the soil microbiota. We used 885 previously published microbial amplicon-sequencing datasets (16S) collected from vineyards located in 13 countries across 4 continents and planted with 34 Vitis vinifera cultivars representing the largest collection of vineyard microbiomes analyzed to date. This research also aimed at addressing some common challenges associated with most ML-based studies such as easy availability of models to non-technical researchers which is necessary for research reproducibility. To facilitate this, the models built in this study will be available through a GUI-based containerized web platform. Also, to provide compatibility of processed data from other 16S studies, a computational step will be included that merge the features either by taxonomy or sequence identity. This study will be beneficial in several ways such as inferring lost/mislabeled samples, identifying important location-specific and cultivar-specific taxa. Ultimately, this approach could be implemented for the identification of the genes regulating host/microbe interactions, which will provide valuable targets for breeding programs aimed at producing more sustainable crops.  

Acknowledgements: This study was supported by the National Institute of Food and Agriculture, AFRI Competitive Grant Program Accession number 1018617, and the National Institute of Food and Agriculture, United States Department of Agriculture, Hatch Program accession number 1020852.

DOI:

Publication date: October 5, 2023

Issue: ICGWS 2023

Type: Article

Authors

Carlos M. Rodríguez López1*, Lakshay Anand1

1Environmental Epigenomics and Genomics Group, Department of Horticulture, College of Agriculture, Food and environment, University of Kentucky, Lexington, Kentucky, USA

Contact the author*

Keywords

rhizosphere microbiome, provenance, plant-microbiome interactions, breeding, machine learning

Tags

2ICGWS | ICGWS | ICGWS 2023 | IVES Conference Series

Citation

Related articles…

Antimicrobial activity of oenological polyphenols against Gram positive and Gram negative intestinal multidrug-resistant bacteria

Bacterial antibiotic resistance is a major current health problem. Polyphenols have demonstrated antibacterial activity, and in this work we studied the effect of oenological polyphenols on the growth of intestinal multidrug-resistant strains of human and animal origin. Two Enterococcus faecium strains, resistant to vancomycin and other antibiotics, and four Escherichia coli strains, resistant to ampicillin and other antibiotics, were included in this study. All strains showed multidrug resistant phenotypes and genotypes to at least two antibiotic families.

Lipids at the crossroads of protection: lipid signalling in grapevine defence mechanisms

Understanding grapevine molecular processes and the underlying defence responses is vital for developing sustainable disease control strategies. Lipid signalling pathways, involving the synthesis and degradation of lipid molecules, have emerged as a key regulator in plant defence against pathogens. This study aims to elucidate the role of fatty acids and lipid signalling in grapevine’s defence response to P. viticola infection. The expression of lipid metabolism-related as well as lipid signalling genes was analysed, by qPCR, in three grapevine genotypes: Chardonnay (susceptible), Regent (tolerant) with Rpv3-1 resistance loci, and Sauvignac (resistant) harbouring a pyramid of Rpv12 and Rpv3-1 resistance loci.

Effect of abiotic stress and grape variety on amino acid and polyamine composition of red grape berries

Vines are exposed to environmental conditions that cause abiotic stress on the plants (drought, nutrient and mineral deficits, salinity, etc.). Polyamines are growth regulators involved in various physiological processes, as in abiotic plant stress responses. Stressful conditions can modify grape’s composition, and in this work, we have focused on studying the effect of abiotic stress on the composition of polyamines and amino acids in grapes. In addition, the effect of grape variety on these compounds has been studied.

Effect of rising atmospheric CO2 levels on grapevine yield and composition by the middle of the 21st century: what can we learn from the VineyardFACE?

Atmospheric CO2 levels have been rising continuously since the industrial revolution, affecting crop physiology, yield and quality of harvest products, and grapevine is no exception [1]. Most of previously reported studies used potted plants in controlled environments, and explored grapevine response to relatively high CO2 levels, 700 ppm or more. The vineyardFACE, established in Geisenheim in 2012, uses a free air carbon dioxide enrichment (FACE) system to simulate a moderate (ambient +20%) increase in atmospheric CO2 in a vineyard planted with cvs. Cabernet-Sauvignon and Riesling grafted on rootstock 161-49 Couderc and SO4, respectively.

Physicochemical behaviour of wine spirit and wine distillate aged in Sherry Casks® and Brandy casks

Brandy is a spirit drink made from “wine spirit” (<86% Alcohol by Volume – ABV; high levels of congeners and they are mainly less volatile than ethanol), it may be blended with a “wine distillate” (<94.8%ABV; low levels of congeners and these are mainly more volatile than ethanol), as long as that distillate does not exceed a maximum of 50% of the alcoholic content of the finished product[1]. Brandy must be aged for at least 6 months in oak casks with <1000L of capacity. During ageing, changes occur in colour, flavour, and aroma that improve the quality of the original distillate.