EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine learning approach on plasma proteomics identifies signatures associated with obesity in the KORA FF4 cohort

Jiefei Niu iD, Jonathan Adam, Thomas Skurk, Jochen Seissler, Qiuling Dong iD, Esienanwan Efiong, Christian Gieger, Annette Peters, Sapna Sharma, Harald Grallert

Diabetes, Obesity and Metabolism · 2025

DOI: 10.1111/dom.16264 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diabetes, Obesity and Metabolism, 2025. Verfasst von Jiefei Niu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Research Unit of Molecular Epidemiology, Helmholtz Zentrum München, Neuherberg, Germany. Hauptthemen laut MEDLINE: Obesity, Machine Learning, Proteomics, Blood Proteins. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Helmholtz Zentrum München - German Research Center for Environmental Health, University Hospital of Augsburg, Bavarian State Ministry of Health, Care and Prevention.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

This study investigated the role of plasma proteins in obesity to identify predictive biomarkers and explore underlying biological mechanisms.

Methods

In the Cooperative Health Research in the Region of Augsburg (KORA) FF4 study, 809 proteins were measured in 2045 individuals (564 obese and 1481 non‐obese). Multivariate logistic regression adjusted for confounders (basic and full models) was used to identify obesity‐associated proteins. Priority‐Lasso was applied for feature selection, followed by machine learning models (support vector machine [SVM], random forest [RF], k‐nearest neighbour [KNN] and adaptive boosting [Adaboost]) for prediction. Correlation and enrichment analyses were performed to elucidate relationships between protein biomarkers, obesity risk factors and perturbed pathways. Mendelian randomisation (MR) assessed causal links between proteins and obesity.

Results

A total of 16 proteins were identified as significantly associated with obesity through multivariable logistic regression in the basic model and subsequent Priority‐Lasso analysis. Enrichment analyses highlighted immune response, lipid metabolism and inflammation regulation were linked to obesity. Machine learning models demonstrated robust predictive performance with area under the curves (AUC) of 0.820 (SVM), 0.805 (RF), 0.791 (KNN) and 0.819 (Adaboost). All 16 proteins correlated with obesity‐related risk factors such as blood pressure and lipid levels. MR analysis identified AFM, CRP and CFH as causal and potentially modifiable proteins.

Conclusions

The protein signatures identified in our study showed promising predictive potential for obesity. These findings warrant further investigation to evaluate their clinical applicability, offering insights into obesity prevention and treatment strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ObesityMachine LearningProteomicsBlood ProteinsHumansMaleFemaleMiddle AgedBiomarkersCohort StudiesAgedRisk FactorsAdultMendelian Randomization Analysis

Stichwörter der Autor:innen

cohort studymachine learningobesityproteomics

Substanzen

BiomarkersBlood Proteins

Autor:innen und Institutionen

  • Research Unit of Molecular Epidemiology, Helmholtz Zentrum München, Neuherberg, Germany.
  • Institute of Epidemiology, Helmholtz Zentrum München, Neuherberg, Germany.
  • Faculty of Medicine, Ludwig-Maximilians-University München, Munich, Germany.
  • German Center for Diabetes Research (DZD), Neuherberg, Germany.
  • School of Medicine, Technical University of Munich, Munich, Germany.
  • ZIEL Institute for Food & Health, Core Facility Human Studies, Technical University of Munich, Freising, Germany.

ORCID-Profile: Jiefei Niu, Qiuling Dong

Förderung

  • Helmholtz Zentrum München - German Research Center for Environmental Health
  • University Hospital of Augsburg
  • Bavarian State Ministry of Health, Care and Prevention
  • German Federal Ministry of Education and Research (BMBF)

Zitieren

APA

Niu, J., Adam, J., Skurk, T., Seissler, J., Dong, Q., Efiong, E., Gieger, C., Peters, A., Sharma, S., & Grallert, H. (2025). Machine learning approach on plasma proteomics identifies signatures associated with obesity in the KORA FF4 cohort. Diabetes, Obesity and Metabolism. https://doi.org/10.1111/dom.16264

Vancouver

Niu J, Adam J, Skurk T, Seissler J, Dong Q, Efiong E, et al. Machine learning approach on plasma proteomics identifies signatures associated with obesity in the KORA FF4 cohort. Diabetes, Obesity and Metabolism. 2025. doi:10.1111/dom.16264

BibTeX
@article{Niu2025,
  author = {Niu, Jiefei and Adam, Jonathan and Skurk, Thomas and Seissler, Jochen and Dong, Qiuling and Efiong, Esienanwan and Gieger, Christian and Peters, Annette and Sharma, Sapna and Grallert, Harald},
  title = {Machine learning approach on plasma proteomics identifies signatures associated with obesity in the KORA FF4 cohort},
  journal = {Diabetes, Obesity and Metabolism},
  year = {2025},
  doi = {10.1111/dom.16264}
}
Kostenlos starten →