Machine Learning Approaches Applied to GC-FID Fatty Acid Profiles to Discriminate Wild from Farmed Salmon

Abstract

In the last decade, there has been an increasing demand for wild-captured fish, which attains higher prices compared to farmed species, thus being prone to mislabeling practices. In this work, fatty acid composition coupled to advanced chemometrics was used to discriminate wild from farmed salmon. The lipids extracted from salmon muscles of different production methods and origins (26 wild from Canada, 25 farmed from Canada, 24 farmed from Chile and 25 farmed from Norway) were analyzed by gas chromatography with flame ionization detector (GC-FID). All the tested chemometric approaches, namely principal components analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE) and seven machine learning classifiers, namely k-nearest neighbors (kNN), decision tree, support vector machine (SVM), random forest, artificial neural networks (ANN), naïve Bayes and AdaBoost, allowed for differentiation between farmed and wild salmons using the 17 features obtained from chemical analysis. PCA did not allow clear distinguishing between salmon geographical origin since farmed samples from Canada and Chile overlapped. Nevertheless, using the 17 features in the models, six out of the seven tested machine learning classifiers allowed a classification accuracy of ≥99%, with ANN, naïve Bayes, random forest, SVM and kNN presenting 100% accuracy on the test dataset. The classification models were also assayed using only the best features selected by a reduction algorithm and the best input features mapped by t-SNE. The classifier kNN provided the best discrimination results because it correctly classified all samples according to production method and origin, ultimately using only the three most important features (16:0, 18:2n6c and 20:3n3 + 20:4n6). In general, the classifiers presented good generalization with the herein proposed approach being simple and presenting the advantage of requiring only common equipment existing in most labs.

A Brief Review of Machine Learning-Based Bioactive Compound Research

“…For example, recent studies identified many NP-like small molecules through the exploration of the chemical space of NPs [15][16][17]. In addition, ML models can accurately discriminate wild from farmed salmon based on gas chromatography with flame ionization detector (GC-FID) fatty acid profiles [18]. Therefore, with the help of state-of-the-art machine learning techniques, a variety of tasks such as discovering novel bioactive compounds with desired properties by training data measured through various large-scale experiments have become possible.…”

Changes of Volatile Flavor Compounds in Large Yellow Croaker (Larimichthys crocea) during Storage, as Evaluated by Headspace Gas Chromatography–Ion Mobility Spectrometry and Principal Component Analysis

“…In terms of the analyses of flavor compounds in such foods, current analytical techniques, such as gas chromatography (GC) and GC-mass spectrometry (MS), require solid-phase microextraction (SPME) and/or post-treatments [ 4 , 5 ]. By contrast, headspace-gas chromatography–ion mobility spectrometry (HS-GC-IMS) requires no pretreatment, as the solid, liquid, or headspace gas samples are injected directly [ 6 , 7 ].…”

Fingerprint Approaches Coupled with Chemometrics to Discriminate Geographic Origin of Imported Salmon in China’s Consumer Market

“…Traditional research on the adulteration of salmon has mainly focused on the following three areas: species identification, production mode (wild or farmed) [ 19 , 20 , 21 ] and origin identification. Many studies have identified species using molecular markers [ 22 , 23 ], DNA profiling [ 24 , 25 ] and droplet digital PCR (ddPCR) [ 26 ], all of which could achieve accurate single or multiple species identification results.…”