Chemical characterization and classification of vegetable oils using DESI-MS coupled with a neural network

Yiwei Cui; Liangcun Zhu; Yan Li; Kai Ge; Weibo Lu; Lijun Ge; Kang Chen; Jing Xue; Feiyang Zheng; Shuncong Dai; Huafei Pan; Jingjing Liang; Liting Ji; Qing Shen

doi:10.1016/j.foodchem.2024.142614

Chemical characterization and classification of vegetable oils using DESI-MS coupled with a neural network

Food Chem. 2024 Dec 26:470:142614. doi: 10.1016/j.foodchem.2024.142614. Online ahead of print.

Authors

Yiwei Cui¹, Liangcun Zhu¹, Yan Li¹, Kai Ge¹, Weibo Lu², Lijun Ge², Kang Chen², Jing Xue², Feiyang Zheng³, Shuncong Dai⁴, Huafei Pan⁵, Jingjing Liang⁶, Liting Ji⁷, Qing Shen⁸

Affiliations

¹ School of Biological and Environmental Engineering, Zhejiang Shuren University, Hangzhou 310015, China.
² Laboratory of Food Nutrition and Clinical Research, Institute of Seafood, Zhejiang Gongshang University, Hangzhou 310012, China.
³ Hangzhou Puyu Technology Development Co., Ltd, Hangzhou 310015, China.
⁴ Key Laboratory of Medicine-Food Homology Innovation and Transformation, Linping Hospital of Integrated Traditional Chinese and Western Medicine, Hangzhou 311110, China.
⁵ The Third People's Hospital of Yuhang District, Hangzhou 311115, China.
⁶ Zhejiang Provincial Institute for Food and Drug Control, Hangzhou 310052, China. Electronic address: [email protected].
⁷ School of Pharmaceutical Sciences, Zhejiang Chinese Medical University, Hangzhou 310006, China. Electronic address: [email protected].
⁸ Panvascular Diseases Research Center, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou 324000, China; Laboratory of Food Nutrition and Clinical Research, Institute of Seafood, Zhejiang Gongshang University, Hangzhou 310012, China. Electronic address: [email protected].

PMID: 39740437
DOI: 10.1016/j.foodchem.2024.142614

Abstract

This study tackled mislabeling fraud in vegetable oils, driven by price disparities and profit motives, by developing an approach combining desorption electrospray ionization mass spectrometry (DESI-MS) with a shallow convolutional neural network (SCNN). The method was designed to characterize lipids and distinguish between nine vegetable oils: corn, soybean, peanut, sesame, rice bran, sunflower, camellia, olive, and walnut oils. The optimized DESI-MS method enhanced the ionization of non-polar glycerides and detected ion adducts like [TG + Na]⁺, [TG + NH₄]⁺. This process identified 53 lipid peaks, forming a robust lipid fingerprint for each oil type. An SCNN model was developed using fingerprints, achieving an impressive classification accuracy of 98.5 ± 2.2 %. The integration of DESI-MS with SCNN provides a fast and reliable tool for identifying and classifying vegetable oils, thereby reducing mislabeling fraud and assuring oil quality. By enabling accurate authentication, it contributes to improved transparency and integrity in food labeling and quality control practices.

Keywords: Accurate identification; Desorption electrospray ionization mass spectrometry; Edible oils; Glycerolipid; Shallow convolutional neural network.