Discrimination of white wine ageing based on untarget peak picking approach with multi-class target coupled with machine learning algorithms

Monforte, Ana Rita; Martins, Sara I.F.S.; Ferreira, A. C. Silva

doi:10.1016/j.foodchem.2021.129288

Cited by 12 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach has been applied for instance to wine classification using ICP MS 15 , nuclear magnetic resonance 16 , RP-HPLC/DAD 5 and UV-spectroscopy 17 or to wine region classification using GC/QTOFMS 18 , isotopic ratio 19 , absorbance-transmission and fluorescence excitation-emission matrix (A-TEEM) or climate data 20 . Other studies have also looked at sensorial properties and aroma profiles using gas chromatography (GC) 21 and wine quality using global chemical measurements (alcoholic contents or acidity as examples) 22 and the emergence of oxidative markers during aging with GC 23 .…”

mentioning

confidence: 99%

Predicting Bordeaux red wine origins and vintages from raw gas chromatograms

Schartner,

Beck,

Laboyrie

et al. 2023

Commun Chem

View full text Add to dashboard Cite

Connecting chemical properties to various wine characteristics is of great interest to the science of olfaction as well as the wine industry. We explored whether Bordeaux wine chemical identities and vintages (harvest year) can be inferred from a common and affordable chemical analysis, namely, a combination of gas chromatography (GC) and electron ionization mass spectrometry. Using 12 vintages (within the 1990–2007 range) from 7 estates of the Bordeaux region, we report that, remarkably, nonlinear dimensionality reduction techniques applied to raw gas chromatograms recover the geography of the Bordeaux region. Using machine learning, we found that we can not only recover the estate perfectly from gas chromatograms, but also the vintage with up to 50% accuracy. Interestingly, we observed that the entire chromatogram is informative with respect to geographic location and age, thus suggesting that the chemical identity of a wine is not defined by just a few molecules but is distributed over a large chemical spectrum. This study demonstrates the remarkable potential of GC analysis to explore fundamental questions about the origin and age of wine.

show abstract

mentioning

confidence: 99%

Predicting Bordeaux red wine origins and vintages from raw gas chromatograms

Schartner,

Beck,

Laboyrie

et al. 2023

Commun Chem

View full text Add to dashboard Cite

show abstract

“…The larger MDA indicates the greater importance of the variable. In this study, those variables with MDA larger than 1 were considered as important transcriptomic features for vitiligo ( Lu et al, 2020 ; Monforte et al, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

Development of a Multi-Target Strategy for the Treatment of Vitiligo via Machine Learning and Network Analysis Methods

et al. 2021

View full text Add to dashboard Cite

Vitiligo is a complex disorder characterized by the loss of pigment in the skin. The current therapeutic strategies are limited. The identification of novel drug targets and candidates is highly challenging for vitiligo. Here we proposed a systematic framework to discover potential therapeutic targets, and further explore the underlying mechanism of kaempferide, one of major ingredients from Vernonia anthelmintica (L.) willd, for vitiligo. By collecting transcriptome and protein-protein interactome data, the combination of random forest (RF) and greedy articulation points removal (GAPR) methods was used to discover potential therapeutic targets for vitiligo. The results showed that the RF model performed well with AUC (area under the receiver operating characteristic curve) = 0.926, and led to prioritization of 722 important transcriptomic features. Then, network analysis revealed that 44 articulation proteins in vitiligo network were considered as potential therapeutic targets by the GAPR method. Finally, through integrating the above results and proteomic profiling of kaempferide, the multi-target strategy for vitiligo was dissected, including 1) the suppression of the p38 MAPK signaling pathway by inhibiting CDK1 and PBK, and 2) the modulation of cellular redox homeostasis, especially the TXN and GSH antioxidant systems, for the purpose of melanogenesis. Meanwhile, this strategy may offer a novel perspective to discover drug candidates for vitiligo. Thus, the framework would be a useful tool to discover potential therapeutic strategies and drug candidates for complex diseases.

show abstract

“…Recently, a multi-class classification method based on learning vector quantization NN to classify tea samples of five commercial brands has been proposed 40 . Monforte et al presented an orthogonal partial least square discriminant analysis (OPLS-DA) and RF-combined multi-class pipeline for the discrimination of white wine ageing based on target oxidation markers 41 . Moreover, an SVM multiclass classification demonstrated high efficiency in the classification of 7 different types of raw food 42 .…”

Section: Introductionmentioning

confidence: 99%

VirtuousMultiTaste: Predicting Multiple Taste Sensations with a Multi- objective ML-driven Method

Androutsos,

Pallante,

Bompotas

et al. 2023

Preprint

View full text Add to dashboard Cite

Taste perception plays a pivotal role in guiding nutrient intake and aiding in the avoidance of potentially harmful substances through five basic tastes - sweet, bitter, umami, salty, and sour. Taste perception originates from molecular interactions in the oral cavity between taste receptors and chemical tastants. Hence, the recognition of taste receptors and the subsequent perception of taste heavily rely on the physicochemical properties of food ingredients. In recent years, several advances have been made towards the development of machine learning-based algorithms to classify chemical compounds' tastes using their molecular structures. Despite the great efforts, there remains significant room for improvement by developing multi-class models to predict the entire spectrum of basic tastes. Here, we present a multi-class predictor aimed at distinguishing three different tastes, i.e., bitter, sweet, and umami, from other taste sensations. The developed model has been integrated into a publicly accessible web platform. This work lays the groundwork for a comprehensive understanding of the molecular features that drive the perception of tastes, paving the way towards new methodologies in the rational design of foods, such as the pre-determination of specific tastes, the engineering of complementary diets to traditional pharmacological treatments, and many others.

show abstract

Discrimination of white wine ageing based on untarget peak picking approach with multi-class target coupled with machine learning algorithms

Cited by 12 publications

References 42 publications

Predicting Bordeaux red wine origins and vintages from raw gas chromatograms

Predicting Bordeaux red wine origins and vintages from raw gas chromatograms

Development of a Multi-Target Strategy for the Treatment of Vitiligo via Machine Learning and Network Analysis Methods

VirtuousMultiTaste: Predicting Multiple Taste Sensations with a Multi- objective ML-driven Method

Contact Info

Product

Resources

About