{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T18:58:21Z","timestamp":1777661901987,"version":"3.51.4"},"reference-count":32,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2020,11,7]],"date-time":"2020-11-07T00:00:00Z","timestamp":1604707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100016077","name":"EU","doi-asserted-by":"publisher","award":["grant agreement No 613688"],"award-info":[{"award-number":["grant agreement No 613688"]}],"id":[{"id":"10.13039\/100016077","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia, Portugal","award":["UIDB 50006\/2020"],"award-info":[{"award-number":["UIDB 50006\/2020"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia, Portugal","award":["UIDB 00690\/2020 (CIMO)"],"award-info":[{"award-number":["UIDB 00690\/2020 (CIMO)"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia, Portugal","award":["UIDB\/5757\/2020 (CeDRI)"],"award-info":[{"award-number":["UIDB\/5757\/2020 (CeDRI)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Foods"],"abstract":"<jats:p>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), na\u00efve 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 \u226599%, with ANN, na\u00efve 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.<\/jats:p>","DOI":"10.3390\/foods9111622","type":"journal-article","created":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T19:03:37Z","timestamp":1604862217000},"page":"1622","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Machine Learning Approaches Applied to GC-FID Fatty Acid Profiles to Discriminate Wild from Farmed Salmon"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9033-9486","authenticated-orcid":false,"given":"Liliana","family":"Grazina","sequence":"first","affiliation":[{"name":"REQUIMTE-LAQV, Faculdade de Farm\u00e1cia, Universidade do Porto, Rua de Jorge Viterbo Ferreira, 228, 4050-313 Porto, Portugal"}]},{"given":"P. J.","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Research Centre in Digitalization and Intelligent Robotics (CeDRI), Instituto Polit\u00e9cnico de Bragan\u00e7a, Campus de Santa Apol\u00f3nia, 5300-253 Bragan\u00e7a, Portugal"}]},{"given":"Get\u00falio","family":"Igrejas","sequence":"additional","affiliation":[{"name":"Research Centre in Digitalization and Intelligent Robotics (CeDRI), Instituto Polit\u00e9cnico de Bragan\u00e7a, Campus de Santa Apol\u00f3nia, 5300-253 Bragan\u00e7a, Portugal"}]},{"given":"Maria A.","family":"Nunes","sequence":"additional","affiliation":[{"name":"REQUIMTE-LAQV, Faculdade de Farm\u00e1cia, Universidade do Porto, Rua de Jorge Viterbo Ferreira, 228, 4050-313 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5311-8895","authenticated-orcid":false,"given":"Isabel","family":"Mafra","sequence":"additional","affiliation":[{"name":"REQUIMTE-LAQV, Faculdade de Farm\u00e1cia, Universidade do Porto, Rua de Jorge Viterbo Ferreira, 228, 4050-313 Porto, Portugal"}]},{"given":"Marco","family":"Arlorio","sequence":"additional","affiliation":[{"name":"Dipartimento di Scienze del Farmaco, Food Chemistry Unit, Universit\u00e0 del Piemonte Orientale \u201cA. Avogadro\u201d, Largo Donegani 2\/3, 28100 Novara, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6767-6596","authenticated-orcid":false,"given":"M. Beatriz P. P.","family":"Oliveira","sequence":"additional","affiliation":[{"name":"REQUIMTE-LAQV, Faculdade de Farm\u00e1cia, Universidade do Porto, Rua de Jorge Viterbo Ferreira, 228, 4050-313 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3648-7303","authenticated-orcid":false,"given":"Joana S.","family":"Amaral","sequence":"additional","affiliation":[{"name":"Centro de Investiga\u00e7\u00e3o de Montanha (CIMO), Instituto Polit\u00e9cnico de Bragan\u00e7a, Campus de Sta. Apol\u00f3nia, 5301-857 Bragan\u00e7a, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1016\/j.biotechadv.2011.05.017","article-title":"Health benefits of marine foods and ingredients","volume":"29","author":"Larsen","year":"2011","journal-title":"Biotechnol. Adv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3945\/an.111.000893","article-title":"Omega-3 Fatty Acids EPA and DHA: Health Benefits Throughout Life","volume":"3","author":"Swanson","year":"2012","journal-title":"Adv. Nutr."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1146\/annurev-food-111317-095850","article-title":"Omega-3 polyunsaturated fatty acids and their health benefits","volume":"9","author":"Shahidi","year":"2018","journal-title":"Annu. Rev. Food Sci. Technol."},{"key":"ref_4","unstructured":"FAO Food and Agriculture Organization (FAO) (2020, August 26). GLOBEFISH Highlights Issue 1\/2020, with Jan.\u2013Sep. 2019 Statistics\u2014A Quarterly Update on World Seafood Markets. Available online: http:\/\/www.fao.org\/3\/ca7968en\/CA7968EN.pdf."},{"key":"ref_5","unstructured":"FAO Food and Agriculture Organization (FAO) (2020, August 26). Salmon Commodity Statistics Update. Available online: http:\/\/www.fao.org\/3\/a-bq971e.pdf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1007\/s11745-005-1414-0","article-title":"Fatty acid composition of wild and farmed Atlantic salmon (Salmo salar) and rainbow trout (Oncorhynchus mykiss)","volume":"40","author":"Blanchet","year":"2005","journal-title":"Lipids"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.envres.2017.01.026","article-title":"Lower levels of persistent organic pollutants, metals and the marine omega 3-fatty acid DHA in farmed compared to wild Atlantic salmon (Salmo salar)","volume":"155","author":"Lundebye","year":"2017","journal-title":"Environ. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1016\/j.foodres.2018.10.013","article-title":"Assessing fish authenticity by direct analysis in real time-high resolution mass spectrometry and multivariate analysis: Discrimination between wildtype and farmed salmon","volume":"116","author":"Fiorino","year":"2019","journal-title":"Food Res. Int."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1016\/j.foodcont.2015.06.024","article-title":"Substitution of high-priced fish with low-priced species: Adulteration of common sole in German restaurants","volume":"59","author":"Kappel","year":"2016","journal-title":"Food Control"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1016\/j.foodres.2011.10.043","article-title":"Marketplace substitution of Atlantic salmon for Pacific salmon in Washington State detected by DNA barcoding","volume":"45","author":"Cline","year":"2012","journal-title":"Food Res. Int."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1021\/jf072370d","article-title":"Determination of origin of Atlantic salmon (Salmo salar): The use of multiprobe and multielement isotopic analyses in combination with fatty acid composition to assess wild or farmed origin","volume":"56","author":"Thomas","year":"2008","journal-title":"J. Agric. Food Chem."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Fernandes, T.J.R., Amaral, J.S., and Mafra, I. (2020). DNA barcode markers applied to seafood authentication: An updated review. Crit. Rev. Food Sci. Nutr., in press.","DOI":"10.1080\/10408398.2020.1811200"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3444","DOI":"10.1021\/jf8039268","article-title":"C-13 NMR pattern recognition techniques for the classification of Atlantic salmon (Salmo salar L.) according to their wild, farmed, and geographical origin","volume":"57","author":"Aursand","year":"2009","journal-title":"J. Agric. Food Chem."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1007\/s00216-006-1025-x","article-title":"Application of support vector machines to 1 H NMR data of fish oils: Methodology for the confirmation of wild and farmed salmon and their origins","volume":"387","author":"Masoum","year":"2007","journal-title":"Anal. Bioanal. Chem."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1007\/s00217-006-0314-0","article-title":"Identification of organically farmed Atlantic salmon by analysis of stable isotopes and fatty acids","volume":"224","author":"Molkentin","year":"2007","journal-title":"Eur. Food Res. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1111\/j.1600-0633.2004.00057.x","article-title":"Use of stable isotopes to distinguish farmed from wild Atlantic salmon, Salmo salar","volume":"13","author":"Dempson","year":"2004","journal-title":"Ecol. Freshw. Fish"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1007\/s11745-009-3294-6","article-title":"A simplified method to distinguish farmed (Salmo salar) from wild salmon: Fatty acid ratios versus astaxanthin chiral isomers","volume":"44","author":"Megdal","year":"2009","journal-title":"Lipids"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"7634","DOI":"10.1021\/jf9013235","article-title":"Classification of wild and farmed salmon using bayesian belief networks and gas chromatography-derived fatty acid distributions","volume":"57","author":"Axelson","year":"2009","journal-title":"J. Agric. Food Chem."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.foodchem.2009.03.026","article-title":"Identification of the farm origin of salmon by fatty acid and HR C-13 NMR profiling","volume":"116","author":"Martinez","year":"2009","journal-title":"Food Chem."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.foodcont.2015.01.003","article-title":"Traceability of organic fish e Authenticating the production origin of salmonids by chemical and isotopic analyses","volume":"53","author":"Molkentin","year":"2015","journal-title":"Food Control"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/s11746-000-0106-5","article-title":"Characterization of farmed and wild salmon (Salmo salar) by a combined use of compositional and isotopic analyses","volume":"77","author":"Aursand","year":"2000","journal-title":"JAOCS"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1139\/y59-099","article-title":"A rapid method of total lipid extraction and purification","volume":"37","author":"Bligh","year":"1959","journal-title":"Can. J. Biochem. Physiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7698","DOI":"10.1021\/jf030451d","article-title":"Determination of sterol and fatty acid compositions, oxidative stability, and nutritional value of six walnut (Juglans regia L.) cultivars grown in Portugal","volume":"51","author":"Amaral","year":"2003","journal-title":"J. Agric. Food Chem."},{"key":"ref_24","unstructured":"Jolliffe, I.T. (2002). Principal Component Analysis, Springer Inc.. [2nd ed.]."},{"key":"ref_25","first-page":"2579","article-title":"Visualizing Data Using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"Altman","year":"1992","journal-title":"Am. Stat."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S0020-7373(87)80053-6","article-title":"Simplifying decision trees","volume":"27","author":"Quinlan","year":"1987","journal-title":"Int. J. Man. Mach. Stud."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_29","unstructured":"Ho, T.K. (1995, January 14\u201316). Random Decision Forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_31","unstructured":"Russell, S., and Norvig, P. (2003). Artificial Intelligence: A Modern Approach, Prentice Hall. [2nd ed.]."},{"key":"ref_32","first-page":"771","article-title":"Short Introduction to Boosting","volume":"14","author":"Freund","year":"1999","journal-title":"J. Jpn. Soc. Artif. Intell."}],"container-title":["Foods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2304-8158\/9\/11\/1622\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:30:28Z","timestamp":1760178628000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2304-8158\/9\/11\/1622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,7]]},"references-count":32,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2020,11]]}},"alternative-id":["foods9111622"],"URL":"https:\/\/doi.org\/10.3390\/foods9111622","relation":{"is-referenced-by":[{"id-type":"doi","id":"10.1007\/s43621-025-01992-2","asserted-by":"object"}]},"ISSN":["2304-8158"],"issn-type":[{"value":"2304-8158","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,7]]}}}