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

J 2025

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

SCHWARZEROVA, Jana; Dominika OLESOVA; Katerina JURECKOVA; Ales KVASNICKA; Ales KOSTOVAL et al.

Základní údaje

Originální název

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

Autoři

Vydání

Bioinformatics Advances, Oxford, Oxford University Press, 2025, 2635-0041

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 2.800 v roce 2024

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14110/25:00143831

Organizační jednotka

Lékařská fakulta

Klíčová slova anglicky

metabolomics; concept drift analysis; predictive modeling; confounding factors; model correction

Štítky

14110515

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 2. 3. 2026 13:36, Mgr. Tereza Miškechová

Anotace

V originále

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 https://github.com/JanaSchwarzerova/SAPCDAMP.

Citovat

SCHWARZEROVA, Jana; Dominika OLESOVA; Katerina JURECKOVA; Ales KVASNICKA; Ales KOSTOVAL; David FRIEDECKY; Jiri SEKORA; Jitka POMENKOVA; Valentýna PROVAZNÍK; Lubomír POPELÍNSKÝ a Wolfram WECKWERTH. Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors. Bioinformatics Advances. Oxford: Oxford University Press, 2025, roč. 5, č. 1, s. 1-12. ISSN 2635-0041. Dostupné z: https://doi.org/10.1093/bioadv/vbaf073.

@article{2557838,
   author = {Schwarzerova, Jana and Olesova, Dominika and Jureckova, Katerina and Kvasnicka, Ales and Kostoval, Ales and Friedecky, David and Sekora, Jiri and Pomenkova, Jitka and Provazník, Valentýna and Popelínský, Lubomír and Weckwerth, Wolfram},
   article_location = {Oxford},
   article_number = {1},
   doi = {https://doi.org/10.1093/bioadv/vbaf073},
   keywords = {metabolomics; concept drift analysis; predictive modeling; confounding factors; model correction},
   language = {eng},
   issn = {2635-0041},
   journal = {Bioinformatics Advances},
   title = {Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors},
   url = {https://academic.oup.com/bioinformaticsadvances/article/5/1/vbaf073/8106474},
   volume = {5},
   year = {2025}
}

TY  - JOUR
ID  - 2557838
AU  - Schwarzerova, Jana - Olesova, Dominika - Jureckova, Katerina - Kvasnicka, Ales - Kostoval, Ales - Friedecky, David - Sekora, Jiri - Pomenkova, Jitka - Provazník, Valentýna - Popelínský, Lubomír - Weckwerth, Wolfram
PY  - 2025
TI  - Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors
JF  - Bioinformatics Advances
VL  - 5
IS  - 1
SP  - 1-12
EP  - 1-12
PB  - Oxford University Press
SN  - 26350041
KW  - metabolomics
KW  - concept drift analysis
KW  - predictive modeling
KW  - confounding factors
KW  - model correction
UR  - https://academic.oup.com/bioinformaticsadvances/article/5/1/vbaf073/8106474
N2  - 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 https://github.com/JanaSchwarzerova/SAPCDAMP.
ER  -

SCHWARZEROVA, Jana; Dominika OLESOVA; Katerina JURECKOVA; Ales KVASNICKA; Ales KOSTOVAL; David FRIEDECKY; Jiri SEKORA; Jitka POMENKOVA; Valentýna PROVAZNÍK; Lubomír POPELÍNSKÝ a Wolfram WECKWERTH. Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors. \textit{Bioinformatics Advances}. Oxford: Oxford University Press, 2025, roč.~5, č.~1, s.~1-12. ISSN~2635-0041. Dostupné z: https://doi.org/10.1093/bioadv/vbaf073.

Přehled o publikaci