Prediction of pyrazines and identification of flavor intensity in boletus bainiugan at different drying temperatures based on feature variables

IF 8 1区农林科学 Q1 FOOD SCIENCE & TECHNOLOGY Food Research International Pub Date : 2025-04-19 DOI:10.1016/j.foodres.2025.116467

Guangmei Deng , Jieqing Li , Honggao Liu , Yuanzhong Wang

{"title":"Prediction of pyrazines and identification of flavor intensity in boletus bainiugan at different drying temperatures based on feature variables","authors":"Guangmei Deng , Jieqing Li , Honggao Liu , Yuanzhong Wang","doi":"10.1016/j.foodres.2025.116467","DOIUrl":null,"url":null,"abstract":"<div><div>Abstract</div><div>Low-cost and high-throughput quantitative analysis of volatile compounds is essential for flavor studies in <em>Boletus bainiugan</em>. However, traditional methods are time-consuming and labor-intensive. Herein, a rapid prediction method of pyrazines based on spectroscopic and data fusion techniques for <em>Boletus bainiugan</em> of different drying temperatures is proposed. Four datasets, Fourier transform Near infrared (FT-NIR) spectroscopy, Attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy, and low-level and middle-level data fusion, are used to build 147 partial least squares regression (PLSR) prediction models based on different preprocessing and feature extraction methods. The results indicates that the second-order derivation- uninformative variable elimination (SD-UVE) based FT-NIR spectral dataset achieved accurate prediction for seven important compounds (pyrazines), with the coefficient of determination of prediction set (R<sup>2</sup><sub>p</sub>) higher than 0.840 and residual predictive deviation (RPD) are all greater than 2.418. The screened 189 feature wavenumbers can be used to accurately predict other pyrazine compounds with the highest R<sup>2</sup><sub>p</sub> of 0.909 and the best RPD of 2.506, and successfully differentiate between <em>Boletus bainiugan</em> with high flavor intensity (65 °C) and other drying temperature samples with a validation set accuracy of 95.23 %. This study achieved the work of predicting the relative content of pyrazine volatile compounds in different drying temperatures of <em>Boletus bainiugan</em>, which provides a theoretical basis for the study of other classes of compounds in spectral distribution and prediction.</div></div>","PeriodicalId":323,"journal":{"name":"Food Research International","volume":"211 ","pages":"Article 116467"},"PeriodicalIF":8.0000,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food Research International","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0963996925008051","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Low-cost and high-throughput quantitative analysis of volatile compounds is essential for flavor studies in Boletus bainiugan. However, traditional methods are time-consuming and labor-intensive. Herein, a rapid prediction method of pyrazines based on spectroscopic and data fusion techniques for Boletus bainiugan of different drying temperatures is proposed. Four datasets, Fourier transform Near infrared (FT-NIR) spectroscopy, Attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy, and low-level and middle-level data fusion, are used to build 147 partial least squares regression (PLSR) prediction models based on different preprocessing and feature extraction methods. The results indicates that the second-order derivation- uninformative variable elimination (SD-UVE) based FT-NIR spectral dataset achieved accurate prediction for seven important compounds (pyrazines), with the coefficient of determination of prediction set (R²_p) higher than 0.840 and residual predictive deviation (RPD) are all greater than 2.418. The screened 189 feature wavenumbers can be used to accurately predict other pyrazine compounds with the highest R²_p of 0.909 and the best RPD of 2.506, and successfully differentiate between Boletus bainiugan with high flavor intensity (65 °C) and other drying temperature samples with a validation set accuracy of 95.23 %. This study achieved the work of predicting the relative content of pyrazine volatile compounds in different drying temperatures of Boletus bainiugan, which provides a theoretical basis for the study of other classes of compounds in spectral distribution and prediction.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于特征变量的不同干燥温度下白牛肝菌中吡嗪类化合物的预测和风味强度的鉴定

摘要低成本、高通量的挥发性成分定量分析是研究白酵母风味的重要手段。然而，传统的方法既费时又费力。本文提出了一种基于光谱和数据融合技术的快速预测不同干燥温度下白牛菇中吡嗪类化合物含量的方法。利用傅里叶变换近红外光谱（FT-NIR）、衰减全反射傅里叶变换红外光谱（ATR-FTIR）和中低水平数据融合4个数据集，基于不同的预处理和特征提取方法，构建了147个偏最小二乘回归（PLSR）预测模型。结果表明，基于二阶导数-无信息变量消除（SD-UVE）的FT-NIR光谱数据集对7种重要化合物（吡嗪类）进行了准确预测，预测集决定系数（R2p）均大于0.840，剩余预测偏差（RPD）均大于2.418。筛选出的189个特征波数可用于准确预测其他吡唑类化合物，R2p最高为0.909，RPD最佳为2.506，并能成功区分高风味强度（65℃）的白菌菇与其他干燥温度样品，验证集准确率为95.23%。本研究完成了对白牛菇不同干燥温度下吡嗪类挥发性化合物相对含量的预测工作，为其他类化合物的光谱分布和预测研究提供了理论基础。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Food Research International 工程技术-食品科技

CiteScore

12.50

自引率

7.40%

发文量

1183

审稿时长

79 days

期刊介绍： Food Research International serves as a rapid dissemination platform for significant and impactful research in food science, technology, engineering, and nutrition. The journal focuses on publishing novel, high-quality, and high-impact review papers, original research papers, and letters to the editors across various disciplines in the science and technology of food. Additionally, it follows a policy of publishing special issues on topical and emergent subjects in food research or related areas. Selected, peer-reviewed papers from scientific meetings, workshops, and conferences on the science, technology, and engineering of foods are also featured in special issues.