Serum protein Glycopatterns as biomarkers for machine learning diagnosis of major depressive disorder
Serumprotein-Glykopatterns als Biomarker für die Machine-Learning-Diagnose einer majoren depressiven Störung
Glycobiology · 05.11.2026 · 36 (12)
DOI: 10.1093/glycob/cwag080 ↗Auf einen Blick
Serumproben von 150 Personen wurden auf Glykopatterns untersucht. Mit maschinellem Lernen ließen sich MDD und Schweregrade mit guter Trefferquote klassifizieren.
Fragestellung
Eignen sich Serumprotein-Glykopatterns als Biomarker für die Diagnose und Schweregradeinteilung einer majoren depressiven Störung (MDD)?
Methode
Serumproben von 150 Personen wurden mit Lectin-Microarrays analysiert. Daraus trainierten die Autor:innen 7 Machine-Learning-Modelle; Bewertung in einer nested 5-fold cross-validation und in einer verblindeten Kohorte.
Ergebnisse
36 Lectine zeigten veränderte Bindungssignale. KNN war das beste Modell mit 95,3 % ± 2,7 % Accuracy und AUC (Micro) 0,990 ± 0,010. In der verblindeten Kohorte (n = 71) lagen die Accuracies bei 0,831, 0,662 und 0,831.
Schlussfolgerung der Autor:innen
Die Autor:innen schlussfolgern, dass Serum-Glycopatterns in Kombination mit maschinellem Lernen ein vielversprechendes objektives Instrument für MDD-Diagnose und Schweregradbeurteilung sind.
Kernaussagen
- 150 Serumproben wurden per Lectin-Microarray analysiert
- KNN erzielte die beste Leistung im Cross-Validation-Set
- Verblindete Kohorte: Accuracies 0,831, 0,662 und 0,831
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Glycobiology, online erschienen am 21.09.2026. Verfasst von Shiyi Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Functional Glycomics, Faculty of Life Science & Medicine, Northwest University, No. 229 Taibai Beilu, Beilin District, Xi'an 710069, S…. Hauptthemen laut MEDLINE: Major Depressive Disorder, Machine Learning, Blood Proteins. Die Arbeit nennt 50 Literaturangaben. Gefördert von: Doctoral Startup Fund of Shandong Mental Health Center, Natural Science Foundation of Shaanxi Province.
Abstract (Originalsprache)
The diagnosis of major depressive disorder (MDD) currently relies on subjective clinical assessment, underscoring the need for objective biomarkers. Glycosylation, a common post-translational modification, is involved in neuroinflammation and immune regulation, both implicated in MDD pathogenesis. This study aimed to identify serum protein glycopatterns as biomarkers for MDD diagnosis and severity stratification. Serum samples from 150 individuals, including healthy volunteers (HV, n = 38), mild-to-moderate MDD (M-MDD, n = 52), and severe MDD (S-MDD, n = 60), were analyzed using lectin microarrays. Thirty-six lectins showed significantly altered binding signals that indicating widespread glycosylation changes between HV, M-MDD, and S-MDD. These features were used to train seven machine-learning models, among which K-nearest neighbours (KNN) performed best, achieving 95.3% ± 2.7% accuracy and an AUC (Micro) of 0.990 ± 0.010 in a nested 5-fold cross-validation framework. In a blinded cohort (n = 71), the KNN model showed accuracies of 0.831, 0.662, and 0.831 for MDD, M-MDD, and S-MDD, respectively. SHAP analysis identified key lectins contributing to classification. These results demonstrated that serum glycopatterns combined with machine learning provided a promising objective tool for MDD diagnosis and severity assessment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Laboratory for Functional Glycomics, Faculty of Life Science & Medicine, Northwest University, No. 229 Taibai Beilu, Beilin District, Xi'an 710069, Shaanxi Province, China.
- Xi'an Key Laboratory of Metabolic Disease Imaging, Xi'an No. 3 Hospital, Affiliated Hospital of Northwest University, No. 10 East Section of Fengcheng 3rd Road, Weiyang District, Xi'an 710018, Shaanxi Province, China.
- Department of Psychiatry, Shandong Mental Health Center, Shandong University, No. 49 Wenhua East Road, Lixia District, Jinan 250014, Shandong Province, China.
ORCID-Profile: Xinyuan Hu, Zheng Li
Förderung
- Doctoral Startup Fund of Shandong Mental Health Center
- Natural Science Foundation of Shaanxi Province
Zitieren
APA
Wang, S., Shu, J., Yu, H., Shi, Y., Zhang, C., Hu, X., & Li, Z. (2026). Serum protein Glycopatterns as biomarkers for machine learning diagnosis of major depressive disorder. Glycobiology, 36(12). https://doi.org/10.1093/glycob/cwag080
Vancouver
Wang S, Shu J, Yu H, Shi Y, Zhang C, Hu X, et al. Serum protein Glycopatterns as biomarkers for machine learning diagnosis of major depressive disorder. Glycobiology. 2026;36(12). doi:10.1093/glycob/cwag080
BibTeX
@article{Wang2026,
author = {Wang, Shiyi and Shu, Jian and Yu, Hanjie and Shi, Yue and Zhang, Chen and Hu, Xinyuan and Li, Zheng},
title = {Serum protein Glycopatterns as biomarkers for machine learning diagnosis of major depressive disorder},
journal = {Glycobiology},
year = {2026},
volume = {36},
number = {12},
doi = {10.1093/glycob/cwag080}
}
EUVIMED