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…

Exploring intra-vineyard variability with sensor- and molecular-based approaches 

The application of remote and proximal sensing is a fast and efficient method to monitor grapevine vegetative and physiological parameters and is considered valuable to derive information on associated yield and quality traits in the vineyard. Further details can be obtained by the application of molecular analysis at the gene expression level aiming at elucidating how pathways controlling the formation of different grape quality traits are influenced by spatial variability. This work aims at evaluating intra-vineyard variability in grape composition at harvest and at comparing this with remotely sensed canopy vegetation data and molecular-based approaches.

Sugar accumulation disorder Berry Shrivel – from current knowledge towards novel hypothesis

In contrast to fruit and grape berry ripening, the biological processes causing ripening disorders are often much less understood, although shriveling disorders of fruits are manifold and contribute to yield losses and reduced fruit quality worldwide. Shrinking berries are a common feature for all shriveling disorders in grapevine although their timing of appearance during the berry ripening process and their underlying induction processes distinct them from each other. The sugar accumulation disorder Berry Shrivel (BS) is characterized by a suppression of sugar accumulation short after veraison resulting in berries low in sugar content and anthocyanins in berry skins, while the organic acid content is similar. Recent studies analyzed the biochemical, morphological and molecular processes affected in BS berries and linked early changes to the period of ripening onset [1,2].

Volatilome in grapevine leaves is defined by the variety and modulated by mycorrhizal symbiosis

Volatile organic compounds (VOCs) constitute a diverse group of secondary metabolites key for the communication of plants with other organisms and for their adaptation to environmental and biotic stresses. The emission of these compounds through leaves is also affected by the interaction of plants with symbiotic microorganisms, arbuscular mycorrhizal fungi (AMF) among them [1]. Our objective was to know the concentration and profile of VOCs emitted by the leaves of two grapevine varieties (Tempranillo, T, and Cabernet Sauvignon, CS, grafted onto R110 rootstocks), inoculated or not with a consortium of five AMF (Rhizophagus irregularis, Funneliformis mosseae, Septoglomus deserticola, Claroideoglomus claroideum and C. etunicatum).

New tool to evaluate color modifications during oxygen consumption in white and red wines

Measuring the effect of oxygen consumption on the color of wines as the level of dissolved oxygen decreases over time is very useful to know how much oxygen a wine can consume without significantly altering its color. The changes produced in wine after being exposed to high oxygen concentrations have been studied by different authors, but in all cases the wine has been analyzed once the oxygen consumption process has been completed. This work presents the results obtained with the use of an equipment designed and made to measure simultaneously the level of dissolved oxygen and the spectrum of the wine, during the oxygen consumption process from saturation levels with air to very low levels, which indicate the total consumption of the dosed oxygen[1,2].

Time vs drought: leaf age rather than drought drives osmotic adjustment in V. vinifera cv. Pinot Noir

Global warming and increased frequency and/or severity of drought events are among the most threatening consequences of climate change for agricultural crops. In response to drought, grapevine (as many other plants) exhibits osmotic adjustment through active accumulation of osmolytes which in turn shift the leaf turgor loss point (TLP) to more negative values, allowing to maintain stomata opened at lower water potentials1. We investigated the capacity of Pinot noir leaves to modulate their osmotic potential as a function of: (i) time (seasonal osmoregulation), (ii) growing temperatures, and (iii) drought events, to enhance comprehension of the resilience of grapevines in drought conditions. We performed trails under semi-controlled field conditions, and in two different greenhouse chambers (20/15 °C vs 25/20 °C day/night). For two consecutive vegetative seasons, grafted potted grapevines (Pinot noir/SO4) were subjected to two different water regimes for at least 30 days: well-watered (WW) and water deficit (WD).