Repository logo
 
Publication

Machine learning approaches applied to GC-FID fatty acid profiles to discriminate wild from farmed salmon

2020Journal article Open access
Simple item page
dc.contributor.authorGrazina, Liliana
dc.contributor.authorRodrigues, Pedro João
dc.contributor.authorIgrejas, Getúlio
dc.contributor.authorNunes, Maria A.
dc.contributor.authorMafra, Isabel
dc.contributor.authorArlorio, Marco
dc.contributor.authorOliveira, Beatriz
dc.contributor.authorAmaral, Joana S.
dc.date.accessioned2018-02-19T10:00:00Z
dc.date.accessioned2021-02-27T15:58:43Z
dc.date.available2018-01-19T10:00:00Z
dc.date.available2021-02-27T15:58:43Z
dc.date.issued2020
dc.description.abstractIn 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.en_EN
dc.description.sponsorshipThis work was supported by the European project FOODINTEGRITY (FP7-KBBE-2013-single-stage, under grant agreement No 613688) and FCT (Fundação para a Ciência e Tecnologia, Portugal) under the Partnership Agreements UIDB 50006/2020, UIDB 00690/2020 (CIMO) and UIDB/5757/2020 (CeDRI). L. Grazina and M.A. Nunes acknowledge the FCT grant SFRH/BD/132462/2017 and SFRH/BD/130131/2017 financed by POPH-QREN (subsidised by FSE and MCTES).
dc.description.versioninfo:eu-repo/semantics/publishedVersionen_EN
dc.identifier.citationGrazina, Liliana; Rodrigues, P. J.; Igrejas, Getúlio; Nunes, Maria A.; Mafra, Isabel; Arlorio, Marco; Oliveira, M. Beatriz; Amaral, Joana S. (2020). Machine learning approaches applied to GC-FID fatty acid profiles to discriminate wild from farmed salmon. Foods. ISSN 2304-8158. 9:11, p. 1-15en_EN
dc.identifier.doi10.3390/foods9111622en_EN
dc.identifier.urihttp://hdl.handle.net/10198/23356
dc.language.isoeng
dc.peerreviewedyesen_EN
dc.relationDevelopment of an olive oil-based spread fortified with an active ingredient from olive pomace - potential cardiovascular benefits
dc.subjectAuthenticityen_EN
dc.subjectChemometricsen_EN
dc.subjectFatty acidsen_EN
dc.subjectFishen_EN
dc.subjectMachine learningen_EN
dc.subjectMislabelingen_EN
dc.subjectSalmo salar Len_EN
dc.titleMachine learning approaches applied to GC-FID fatty acid profiles to discriminate wild from farmed salmonen_EN
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleDevelopment of an olive oil-based spread fortified with an active ingredient from olive pomace - potential cardiovascular benefits
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/POR_NORTE/SFRH%2FBD%2F130131%2F2017/PT
oaire.fundingStreamPOR_NORTE
person.familyNameSoares Rodrigues
person.familyNameIgrejas
person.familyNameSoares Amaral
person.givenNamePedro João
person.givenNameGetúlio
person.givenNameJoana Andrêa
person.identifier.ciencia-id1316-21BB-9015
person.identifier.ciencia-id5319-7DE8-BEDA
person.identifier.orcid0000-0002-0555-2029
person.identifier.orcid0000-0002-6820-8858
person.identifier.orcid0000-0002-3648-7303
person.identifier.ridM-8571-2013
person.identifier.scopus-author-id47761255900
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccessen_EN
rcaap.typearticleen_EN
relation.isAuthorOfPublication6c5911a6-b62b-4876-9def-60096b52383a
relation.isAuthorOfPublicationab4092ec-d1b1-4fe0-b65a-efba1310fd5a
relation.isAuthorOfPublication42be2cf4-adc4-4e7f-ac60-7aab515b38cd
relation.isAuthorOfPublication.latestForDiscovery42be2cf4-adc4-4e7f-ac60-7aab515b38cd
relation.isProjectOfPublication6a88d4ec-a29a-47c2-8abe-33f08b52bbd0
relation.isProjectOfPublication.latestForDiscovery6a88d4ec-a29a-47c2-8abe-33f08b52bbd0

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
18.pdf
Size:
1.47 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.75 KB
Format:
Plain Text
Description:
Download

Collections

CIMO - Artigos em Revistas Indexados à WoS/Scopus