A novel freezing crystallization-HPLC method combined with machine learning for determining pigments and geographical classification of extra virgin olive oil

IF 1.9 4区农林科学 Q3 CHEMISTRY, APPLIED

Journal of the American Oil Chemists Society Pub Date : 2025-03-10 DOI:10.1002/aocs.12947

Cong-Hui Lu, Yu Gao, Hui-Yuan Lu, Wei-Jian Shen, Jules Muhire, Zhi-Bin Lu, Quan Jing, Xin-Yi Huang, Dong Pei, Duo-Long Di

{"title":"A novel freezing crystallization-HPLC method combined with machine learning for determining pigments and geographical classification of extra virgin olive oil","authors":"Cong-Hui Lu, Yu Gao, Hui-Yuan Lu, Wei-Jian Shen, Jules Muhire, Zhi-Bin Lu, Quan Jing, Xin-Yi Huang, Dong Pei, Duo-Long Di","doi":"10.1002/aocs.12947","DOIUrl":null,"url":null,"abstract":"Effective removal of the fatty acid matrix and enrichment of trace target components is a key step in the quantitative analysis of minor components in edible oils. In this study, a novel sample pretreatment method named freezing crystallization was developed to analyze pigments in extra virgin olive oil (EVOO). The limits of detection and limits of quantification of this method were 0.125–0.625 μg/mL and 0.5–2.5 μg/mL, respectively. Linear correlations were obtained (r2 ≥ 0.9995), and the recoveries at three spiked levels were 84.2%–105.8%. Besides, the primary pigment components information combined with machine learning to classify the origin of Chinese EVOOs. The k-nearest neighbor (kNN), decision tree (DT), and random forest (RF) were employed to classify the origin of EVOOs, and the accuracies were up to 88%, 88%, and 96%, respectively. This result shows that the novel method has good accuracy and stability, and pigments can be used as a basis for classifying the geographical origin of Chinese domestic EVOOs.","PeriodicalId":17182,"journal":{"name":"Journal of the American Oil Chemists Society","volume":"102 6","pages":"1029-1038"},"PeriodicalIF":1.9000,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American Oil Chemists Society","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/aocs.12947","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, APPLIED","Score":null,"Total":0}

引用次数: 0

Abstract

Effective removal of the fatty acid matrix and enrichment of trace target components is a key step in the quantitative analysis of minor components in edible oils. In this study, a novel sample pretreatment method named freezing crystallization was developed to analyze pigments in extra virgin olive oil (EVOO). The limits of detection and limits of quantification of this method were 0.125–0.625 μg/mL and 0.5–2.5 μg/mL, respectively. Linear correlations were obtained (r² ≥ 0.9995), and the recoveries at three spiked levels were 84.2%–105.8%. Besides, the primary pigment components information combined with machine learning to classify the origin of Chinese EVOOs. The k-nearest neighbor (kNN), decision tree (DT), and random forest (RF) were employed to classify the origin of EVOOs, and the accuracies were up to 88%, 88%, and 96%, respectively. This result shows that the novel method has good accuracy and stability, and pigments can be used as a basis for classifying the geographical origin of Chinese domestic EVOOs.

查看原文本刊更多论文

结合机器学习的冷冻结晶-高效液相色谱法测定特级初榨橄榄油的色素和地理分类

有效去除脂肪酸基质和富集微量目标成分是食用油微量成分定量分析的关键步骤。本研究建立了一种新的样品前处理方法——冷冻结晶法，用于分析特级初榨橄榄油（EVOO）中的色素。方法的检出限为0.125 ~ 0.625 μg/mL，定量限为0.5 ~ 2.5 μg/mL。结果表明，加样回收率在84.2% ~ 105.8%之间，具有良好的线性关系（r2≥0.9995）。此外，将主要色素成分信息与机器学习相结合，对中国evoo进行原产地分类。采用k近邻法（kNN）、决策树法（DT）和随机森林法（RF）对evo的起源进行分类，准确率分别达到88%、88%和96%。结果表明，该方法具有良好的准确性和稳定性，可作为我国国产EVOOs地理来源分类的依据。

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分钟内获得全文求助全文

来源期刊

Journal of the American Oil Chemists Society 工程技术-食品科技

CiteScore

4.10

自引率

5.00%

发文量

审稿时长

2.4 months

期刊介绍： The Journal of the American Oil Chemists’ Society (JAOCS) is an international peer-reviewed journal that publishes significant original scientific research and technological advances on fats, oils, oilseed proteins, and related materials through original research articles, invited reviews, short communications, and letters to the editor. We seek to publish reports that will significantly advance scientific understanding through hypothesis driven research, innovations, and important new information pertaining to analysis, properties, processing, products, and applications of these food and industrial resources. Breakthroughs in food science and technology, biotechnology (including genomics, biomechanisms, biocatalysis and bioprocessing), and industrial products and applications are particularly appropriate. JAOCS also considers reports on the lipid composition of new, unique, and traditional sources of lipids that definitively address a research hypothesis and advances scientific understanding. However, the genus and species of the source must be verified by appropriate means of classification. In addition, the GPS location of the harvested materials and seed or vegetative samples should be deposited in an accredited germplasm repository. Compositional data suitable for Original Research Articles must embody replicated estimate of tissue constituents, such as oil, protein, carbohydrate, fatty acid, phospholipid, tocopherol, sterol, and carotenoid compositions. Other components unique to the specific plant or animal source may be reported. Furthermore, lipid composition papers should incorporate elements of yeartoyear, environmental, and/ or cultivar variations through use of appropriate statistical analyses.