Assessment of lemon juice adulteration by targeted screening using LC-UV-MS and untargeted screening using UHPLC-QTOF/MS with machine learning

Weiting Lyu; Bo Yuan; Siyu Liu; James E Simon; Qingli Wu

doi:10.1016/j.foodchem.2021.131424

Assessment of lemon juice adulteration by targeted screening using LC-UV-MS and untargeted screening using UHPLC-QTOF/MS with machine learning

Food Chem. 2022 Mar 30;373(Pt A):131424. doi: 10.1016/j.foodchem.2021.131424. Epub 2021 Oct 20.

Authors

Weiting Lyu¹, Bo Yuan², Siyu Liu³, James E Simon⁴, Qingli Wu⁵

Affiliations

¹ New Use Agriculture and Natural Plant Products Program, Department of Plant Biology and Center for Agricultural Food Ecosystems, Institute of Food, Nutrition & Health, Rutgers University, 59 Dudley Road, New Brunswick, NJ 08901, USA; Department of Medicinal Chemistry, Rutgers University, 160 Frelinghuysen Road, Piscataway, NJ 08854, USA.
² New Use Agriculture and Natural Plant Products Program, Department of Plant Biology and Center for Agricultural Food Ecosystems, Institute of Food, Nutrition & Health, Rutgers University, 59 Dudley Road, New Brunswick, NJ 08901, USA; Department of Food Science, Rutgers University, 59 Dudley Road, New Brunswick, NJ 08901, USA.
³ Citromax Flavors Group, Inc., 444 Washington Ave, Carlstadt, NJ 07072, USA.
⁴ New Use Agriculture and Natural Plant Products Program, Department of Plant Biology and Center for Agricultural Food Ecosystems, Institute of Food, Nutrition & Health, Rutgers University, 59 Dudley Road, New Brunswick, NJ 08901, USA; Department of Medicinal Chemistry, Rutgers University, 160 Frelinghuysen Road, Piscataway, NJ 08854, USA. Electronic address: jimsimon@rutgers.edu.
⁵ New Use Agriculture and Natural Plant Products Program, Department of Plant Biology and Center for Agricultural Food Ecosystems, Institute of Food, Nutrition & Health, Rutgers University, 59 Dudley Road, New Brunswick, NJ 08901, USA; Department of Medicinal Chemistry, Rutgers University, 160 Frelinghuysen Road, Piscataway, NJ 08854, USA; Department of Food Science, Rutgers University, 59 Dudley Road, New Brunswick, NJ 08901, USA. Electronic address: qlwu@sebs.rutgers.edu.

PMID: 34710685
DOI: 10.1016/j.foodchem.2021.131424

Abstract

The aim of this work was to develop an approach combining LC-MS-based metabolomics and machine learning to distinguish between and predict authentic and adulterated lemon juices. A targeted screening of six major flavonoids was first conducted using ultraviolet ion trap MS. To improve the prediction accuracy, an untargeted methodology was carried out using UHPLC-QTOF/MS. Based on the acquired metabolic profiles, both PCA and PLS-DA were conducted. Results exhibited a cluster pattern and a separation potential between authentic and adulterated samples. Five machine learning models were then developed to further analyze the data. The model of support vector machine achieved the highest prediction power, with accuracy up to 96.7 ± 7.5% for the cross-validation set and 100% for the testing set. In addition, 79 characteristic m/z were tentatively identified. This work demonstrated that untargeted screening coupled with machine learning models can be a powerful tool to facilitate detection of lemon juice adulteration.

Keywords: Flavonoids; Food safety; Metabolomics; PCA; PLSA; Predictive modelling; Quality control.

MeSH terms

Chromatography, High Pressure Liquid
Chromatography, Liquid
Fruit and Vegetable Juices*
Machine Learning
Mass Spectrometry
Metabolomics*