terclim by ICS banner
IVES 9 IVES Conference Series 9 CONVOLUTIONAL NEURAL NETWORK TO PREDICT GENETIC GROUP AND SULFUR TOLERANCE OF BRETTANOMYCES BRUXELLENSIS

CONVOLUTIONAL NEURAL NETWORK TO PREDICT GENETIC GROUP AND SULFUR TOLERANCE OF BRETTANOMYCES BRUXELLENSIS

Abstract

The spoilage yeast Brettanomyces bruxellensis presents many strain dependent characteristics, particularly sulfur tolerance (1). Climate change and the evolution of oenological practices are at the origin of matrices with low levels of sulfur dioxide and higher pH. These parameters favor the development of this yeast and lead to serious financial losses for winemakers (2). Thus, it is essential to discriminate B. bruxellensis isolates at the strain level in order to predict their stress resistance capacities. Few predictive tools are available to reveal intraspecific diversity within B. bruxellensis species; also, they require expertise and can be expensive. In this study, to make analysis even faster, we further investigated the correlation between genetic groups previously described (3) and cell polymorphism using the analysis of optical microscopy images via deep learning. A Convolutional Neural Network (CNN) was trained and allowed the discrimination of B. bruxellensis isolates in 4 of the 6 genetic groups (GG), with an accuracy of 96.6% (4). Future works will have to be done for the no tested genetic groups. But already these results confirm the possibility to develop a tool allowing to determine the tolerance of a contaminant, in a short time, in order to help wine industry professionals to choose the appropriate corrective measure.

 

1. Avramova M, Cibrario A, Peltier E, Coton M, Coton E, Schacherer J, Spano G, Capozzi V, Blaiotta G,  Salin F, Dols-Lafargue M, Grbin P, Curtin C, AlbertinW, Masneuf-Pomarede I (2018) Brettanomyces bruxellensis population survey reveals a diploid-triploid complex structured according to substrate of isolation and geographical distribution. Sci. Rep. 8, 4136. https://doi.org/10.1038/s41598-018-
2. Alston J, Arvik T, Hart J. Lapsley JT (2021) Brettanomics I: The Cost of Brettanomyces in California Wine ProductionJournal of Wine Economics, Volume 16, Number 1, 2021, Pages 4–31 doi:10.1017/jwe.2020.20 
3. Lebleux M*, Abdo H*, Coelho C, Basmaciyan L, Albertin W, Maupeu J, Laurent J, Roullier-Gall C, Alexandre H, Guilloux-Benatier M, Weidmann S, Rousseaux S (2020) New advances on the Brettanomyces bruxellensis biofilm mode of life. Int J Food Microbiol, 318, pp.1084642. DOI : 10.1016/j.ijfoodmicro.2019.108464 
4. Lebleux M, Denimal E, De Oliveira D, Marin A, Desroche N, Alexandre H, Weidmann S, Rousseaux S (2021) Prediction of genetic groups within Brettanomyces bruxellensis through cell morphology using a deep learning tool in press J. Fungi, 7(8):581 https://doi.org/10.3390/jof7080581 

DOI:

Publication date: February 9, 2024

Issue: OENO Macrowine 2023

Type: Poster

Authors

Sandrine Rousseaux1, Manon Lebleux1, Emmanuel Denimal2, Stéphanie Weidmann 1

1. Laboratoire VAlMiS-IUVV, AgroSup Dijon, UMR PAM A 02.102, University Bourgogne Franche-Comté, F-21000 Dijon, France
2. AgroSup Dijon, Direction Scientifique, Appui à la Recherche, 26 Boulevard Docteur Petitjean, F-21000 Dijon, France

Contact the author*

Keywords

Brettanomyces bruxellensis, deep learning, cell morphology, genetic groups

Tags

IVES Conference Series | oeno macrowine 2023 | oeno-macrowine

Citation

Related articles…

AROMA AND SENSORY CHARACTERIZATION OF XINOMAVRO RED WINES FROM DIFFERENT GREEK PROTECTED DESIGNATIONS OF ORIGIN, EFFECT OF TERROIR CHARACTERISTICS

The quality of wines has often been associated with their geographical area of production. The aim of this work was to characterize Protected Designation of Origin (PDO) Xinomavro red wines from different geographical areas of Amyndeon and Naoussa in Northern Greece, elaborated with variables that contribute to their differentiation, such as soil characteristics, altitude, monthly average temperature and rainfall. Xinomavro fruit parcels from different vineyards within the two PDO zones (5 PDO Naoussa and 6 PDO Amyndeon) were vinified following a standard winemaking process. A total of 25 aroma compounds were quantified using gas chromatography-mass spectrometry (GC-MS) with simultaneous full scan and selected ion monitoring for data recording, and odor activity values (OAVs) were determined.

UNEXPECTED PRODUCTION OF DMS POTENTIAL DURING ALCOOLIC FERMENTATION FROM MODEL CHAMPAGNE-LIKE MUSTS

The overall quality of aged wines is in part due to the development of complex aromas over a long period (1.) The apparition of this aromatic complexity depends on multiple chemical reactions that include the liberation of odorous compounds from non-odorous precursors. One example of this phenomenon is found in dimethyl sulphide (DMS) which, with its characteristic odor truffle, is a known contributor to the bouquet of premium aged wine bouquet (1). DMS supposedly accumulates during the ten first years of ageing thanks to the hydrolysis of its precursor dimethylsulfoniopropionate (DMSp.) DMSp is a possible secondary by-product from the degradation of S-methylmethionine (SMM), an amino acid iden- tified in grapes (2), which can be metabolized by yeast during alcoholic fermentation.

SENSORY PROPERTIES IMPORTANT TO AUSTRALIAN FINE WINE CONSUMER SEGMENT PERCEPTION OF CHARDONNAY WINE COMPLEXITY AND PREFERENCE

Wine complexity is considered a multidimensional yet equivocal sensory percept. This project uncovered sensory attributes Australian Chardonnay wine consumers associate with Chardonnay wine complexity
and correlations between expert and consumer perceived wine complexity and preference. A
wine consumer test examined 6 Australian Chardonnay wines of three complexity levels designated low (LC1&2), medium (MC1&2), and high (HC1&2) by an expert panel (n = 8) using a benchtop sensory task. Consumers (n = 81) rated their perceived liking using a 9-point hedonic scale; wine complexity with a 5-point scale anchored “low”, “low-medium”, “medium”, “medium-high”, and “high” and lastly, profiled the wines using Rate-All-That-Apply (RATA). Psychographic segmentation with the Fine Wine Instrument
(FWI) generated three segments; Wine Enthusiasts (WE n=29), Aspirants (ASP n=40) and No- Frills (NF n=12).

HOW OXYGEN CONSUMPTION INFLUENCES RED WINES VOLTAMMETRIC PROFILE

Phenolic compounds play a central role in sensory characteristics of wine, such as colour, mouthfeel, flavour and determine its shelf life. Furthermore, the major non-enzymatic wine oxidation process is due to the catalytic oxidation of phenols in quinones. Due their importance, during the years have been developed different analytical methods to monitor the concentration of phenols in wine, such as Folin-Ciocalteu method, spectrophotometric techniques and HPLC. These methods can also be used to follow some oxidation-related chemical transformations.

ASSESSMENT OF GRAPE QUALITY THROUGH THE MONITORING OFPHENOLIC RIPENESS AND THE APPLICATION OF A NEW RAPID METHOD BASED ON RAMAN SPECTROSCOPY

The chemical composition of grape berries at harvest is one of the key aspects influencing wine quality and depends mainly on the ripeness level of grapes. Climate change affects this trait, unbalancing technological and phenolic ripeness, and this further raises the need for a fast determination of the grape maturity in order to quickly and efficiently determine the optimal time for harvesting. To this end, the characterization of variety-specific ripening curves and the development of new and rapid methods for determining grape ripeness are of key importance.