Enhanced metabolomic predictions using concept drift analysis
- Author(s)
- Jana Schwarzerova, Dominika Olesova, Katerina Jureckova, Ales Kvasnicka, Ales Kostoval, David Friedecky, Jiri Sekora, Jitka Pomenkova, Valentyna Provaznik, Lubos Popelinsky, Wolfram Weckwerth
- Abstract
MOTIVATION: 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 github.com/JanaSchwarzerova/SAPCDAMP.
- Organisation(s)
- Functional and Evolutionary Ecology
- External organisation(s)
- Department of Molecular and Clinical Pathology and Medical Genetics, University Hospital Ostrava, Ostrava 708 00, Czech Republic., Slovak Academy of Sciences (SAS), Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno 616 00, Czech Republic., Palacký University Olomouc, Department of Radio Electronics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno 616 00, Czech Republic., Masaryk University, Vienna Metabolomics Center (VIME), University of Vienna, Vienna 1010, Austria.
- Journal
- Bioinformatics advances
- Volume
- 5
- Pages
- vbaf073
- ISSN
- 2635-0041
- DOI
- https://doi.org/10.1093/bioadv/vbaf073
- Publication date
- 2025
- Peer reviewed
- Yes
- Austrian Fields of Science 2012
- 106005 Bioinformatics
- Portal url
- https://ucrisportal.univie.ac.at/en/publications/09762d87-e9de-4bf4-9a4f-f7f7c3f8225b