Multivariate versus machine learning-based classification of rapid evaporative Ionisation mass spectrometry spectra towards industry based large-scale fish speciation. (15th March 2023)

• Record Type: Journal Article
• Authors: De Graeve, Marilyn; Birse, Nicholas; Hong, Yunhe; Elliott, Christopher T.; Hemeryck, Lieselot Y.; Vanhaecke, Lynn
• Is Part Of: Food chemistry. Volume 404:Part B(2023)
• Publication Date: 2023-03-15
• Subjects: Ambient Ionisation Mass Spectrometry -- Multivariate Chemometric Modelling -- Machine Learning -- Fish Speciation -- Real-time Prediction -- Metabolomics; AIMS Ambient Ionisation Mass Spectrometry -- CV Cross-Validation -- ELISA Enzyme-Linked Immunosorbent Assays -- HRMS High Resolution Mass Spectrometry -- IUU Illegal, Unreported and Unregulated -- LC-MS Liquid Chromatography coupled to Mass Spectrometry -- LDA Linear Discriminant Analysis -- MALDI Matrix-Assisted Laser Desorption/Ionization -- ML Machine Learning -- MS Mass Spectrometry -- OPLS-DA Orthogonal Partial Least Squares-Discriminant Analysis -- PC Principal Component -- PCA Principal Component Analysis -- PCR Polymerase Chain Reaction -- QC Quality Control -- REIMS Rapid Evaporative Ionisation Mass Spectrometry -- RF Random Forest -- RT Retention time -- SVM Support Vector Machine -- TIC Total Ion Count -- UHPLC UltraHigh Performance Liquid Chromatography -- UV UniVariate scaling; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2022.134632
• Languages: English
• ISSNs: 0308-8146

Abstract

Graphical abstract: Highlights: iKnife-REIMS is a suitable technique for large-scale rapid in situ analysis to combat food fraud. A total of 1736 samples comprising 17 fish species were analysed using iKnife-REIMS. PCA-LDA and (O)PLS-DA generated accuracies from 93 to 100%, RF and SVM from 89 to 96% Real-time PCA-LDA outperformed all other classification strategies for all, white and pink fish speciation. Real-time PCA-LDA with an external batch (n = 432) yielded a correct speciation of 90–100 % Abstract: Detection and prevention of fish food fraud are of ever-increasing importance, prompting the need for rapid, high-throughput fish speciation techniques. Rapid Evaporative Ionisation Mass Spectrometry (REIMS) has quickly established itself as a powerful technique for the instant in situ analysis of foodstuffs. In the current study, a total of 1736 samples (2015–2021) - comprising 17 different commercially valuable fish species - were analysed using iKnife-REIMS, followed by classification with various multivariate and machine learning strategies. The results demonstrated that multivariate models, i.e. PCA-LDA and (O)PLS-DA, delivered accuracies from 92.5 to 100.0%, while RF and SVM-based classification generated accuracies from 88.7 to 96.3%. Real-time recognition on a separate test set of 432 samples (2022) generated correct speciation between 89.6 and 99.5% for the multivariate models, while the ML models underperformed (22.3–95.1%), in particular for the white fish species. As such, we propose a real-time validated modelling strategy using directly amenable PCA-LDA for rapid industry-proof large-scale fish speciation.