Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors

Simple item page
dc.contributor.authorSchwarzerová, Janacs
dc.contributor.authorOlešová, Dominikacs
dc.contributor.authorŠabatová, Kateřinacs
dc.contributor.authorKvasnička, Alešcs
dc.contributor.authorKoštoval, Alešcs
dc.contributor.authorFriedecký, Davidcs
dc.contributor.authorSekora, Jiřícs
dc.contributor.authorDluhá, Jitkacs
dc.contributor.authorProvazník, Valentýnacs
dc.contributor.authorPopelinsky, Luboscs
dc.contributor.authorWeckwerth, Wolframcs
dc.coverage.issue1cs
dc.coverage.volume5cs
dc.date.accessioned2025-05-27T09:57:09Z
dc.date.available2025-05-27T09:57:09Z
dc.date.issued2025-04-04cs
dc.description.abstractMotivation The increasing use of big data and optimized prediction methods in metabolomics requires techniques aligned with biological assumptions to improve early symptom diagnosis. One major challenge in predictive data analysis is handling confounding factors—variables influencing predictions but not directly included in the analysis. Results Detecting and correcting confounding factors enhances prediction accuracy, reducing false negatives that contribute to diagnostic errors. This study reviews concept drift detection methods in metabolomic predictions and selects the most appropriate ones. We introduce a new implementation of concept drift analysis in predictive classifiers using metabolomics data. Known confounding factors were confirmed, validating our approach and aligning it with conventional methods. Additionally, we identified potential confounding factors that may influence biomarker analysis, which could introduce bias and impact model performance. Availability and implementation Based on biological assumptions supported by detected concept drift, these confounding factors were incorporated into correction of prediction algorithms to enhance their accuracy. The proposed methodology has been implemented in Semi-Automated Pipeline using Concept Drift Analysis for improving Metabolomic Predictions (SAPCDAMP), an open-source workflow available at https://github.com/JanaSchwarzerova/SAPCDAMP.en
dc.formattextcs
dc.format.extent1-12cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationBioinformatics Advances. 2025, vol. 5, issue 1, p. 1-12.en
dc.identifier.doi10.1093/bioadv/vbaf073cs
dc.identifier.issn2635-0041cs
dc.identifier.orcid0000-0003-2918-9313cs
dc.identifier.orcid0000-0001-5143-9521cs
dc.identifier.orcid0000-0003-1968-9023cs
dc.identifier.orcid0000-0002-8060-0086cs
dc.identifier.orcid0000-0002-3422-7938cs
dc.identifier.other197854cs
dc.identifier.researcheridAAC-2736-2019cs
dc.identifier.researcheridF-9027-2019cs
dc.identifier.researcheridF-4121-2012cs
dc.identifier.scopus57205673155cs
dc.identifier.scopus23490150100cs
dc.identifier.scopus6701729526cs
dc.identifier.urihttps://hdl.handle.net/11012/251062
dc.language.isoencs
dc.publisherOxford Academiccs
dc.relation.ispartofBioinformatics Advancescs
dc.relation.urihttps://academic.oup.com/bioinformaticsadvances/article/5/1/vbaf073/8106474cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/2635-0041/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectMetabolomicsen
dc.subjectConcept drift analysisen
dc.subjectConfounding factorsen
dc.subjectPredictive modelingen
dc.subjectEnhanced classi-fiersen
dc.titleEnhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factorsen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-197854en
sync.item.dbtypeVAVen
sync.item.insts2025.05.27 11:57:09en
sync.item.modts2025.05.27 11:33:36en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav radioelektronikycs
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav biomedicínského inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
vbaf073.pdf
Size:
2.14 MB
Format:
Adobe Portable Document Format
Description:
file vbaf073.pdf
Download
Collections
Ústav radioelektroniky
Ústav biomedicínského inženýrství