Department of Computer Science, University of California, Davis, Davis, California 95616, United States.
Genome Center, University of California, Davis, Davis, California 95616, United States.
J Agric Food Chem. 2024 Apr 10;72(14):8060-8071. doi: 10.1021/acs.jafc.3c07019. Epub 2024 Mar 27.
Smoke taint in wine has become a critical issue in the wine industry due to its significant negative impact on wine quality. Data-driven approaches including univariate analysis and predictive modeling are applied to a data set containing concentrations of 20 VOCs in 48 grape samples and 56 corresponding wine samples with a taster-evaluated smoke taint index. The resulting models for predicting the smoke taint index of wines are highly predictive when using as inputs VOC concentrations after log conversion in both grapes and wines (Pearson Correlation Coefficient PCC = 0.82; = 0.68) and less so when only grape VOCs are used (Pearson Correlation Coefficient PCC = 0.76; = 0.56), and the classification models also show the capacity for detecting smoke-tainted wines using both wine and grape VOC concentrations (Recall = 0.76; Precision = 0.92; F1 = 0.82) or using only grape VOC concentrations (Recall = 0.74; Precision = 0.92; F1 = 0.80). The performance of the predictive model shows the possibility of predicting the smoke taint index of the wine and grape samples before fermentation. The corresponding code of data analysis and predictive modeling of smoke taint in wine is available in the Github repository (https://github.com/IBPA/smoke_taint_prediction).
由于烟雾污染对葡萄酒质量的显著负面影响，葡萄酒行业中烟雾污染已成为一个关键问题。本研究采用单变量分析和预测建模等数据驱动方法，对包含 48 个葡萄样本和 56 个对应葡萄酒样本中 20 种挥发性有机化合物（VOC）浓度以及品尝者评估的烟雾污染指数的数据进行分析。结果表明，在使用葡萄和葡萄酒经过对数转换后的 VOC 浓度作为输入时，葡萄酒烟雾污染指数的预测模型具有较高的预测能力（Pearson 相关系数 PCC = 0.82， = 0.68），而仅使用葡萄 VOC 浓度时则预测能力稍差（Pearson 相关系数 PCC = 0.76， = 0.56），分类模型也显示出使用葡萄酒和葡萄 VOC 浓度（召回率 = 0.76，精度 = 0.92，F1 = 0.82）或仅使用葡萄 VOC 浓度（召回率 = 0.74，精度 = 0.92，F1 = 0.80）来检测受烟雾污染的葡萄酒的能力。预测模型的性能表明，在发酵前预测葡萄酒和葡萄样本烟雾污染指数的可能性。葡萄酒中烟雾污染的数据分析和预测建模的相应代码可在 Github 存储库中获得（https://github.com/IBPA/smoke_taint_prediction）。
