Predicting Biochemical and Physiological Parameters: Deep Learning from IgG Glycome Composition
International Journal of Molecular Sciences · 2024
DOI: 10.3390/ijms25189988 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Ana Vujić und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biology, Faculty of Science, University of Zagreb, 10000 Zagreb, Croatia. Hauptthemen laut MEDLINE: Immunoglobulin G, Deep Learning, Polysaccharides. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Croatian Science Foundation.
Abstract (Originalsprache)
In immunoglobulin G (IgG), N-glycosylation plays a pivotal role in structure and function. It is often altered in different diseases, suggesting that it could be a promising health biomarker. Studies indicate that IgG glycosylation not only associates with various diseases but also has predictive capabilities. Additionally, changes in IgG glycosylation correlate with physiological and biochemical traits known to reflect overall health state. This study aimed to investigate the power of IgG glycans to predict physiological and biochemical parameters. We developed two models using IgG N-glycan data as an input: a regression model using elastic net and a machine learning model using deep learning. Data were obtained from the Korčula and Vis cohorts. The Korčula cohort data were used to train both models, while the Vis cohort was used exclusively for validation. Our results demonstrated that IgG glycome composition effectively predicts several biochemical and physiological parameters, especially those related to lipid and glucose metabolism and cardiovascular events. Both models performed similarly on the Korčula cohort; however, the deep learning model showed a higher potential for generalization when validated on the Vis cohort. This study reinforces the idea that IgG glycosylation reflects individuals’ health state and brings us one step closer to implementing glycan-based diagnostics in personalized medicine. Additionally, it shows that the predictive power of IgG glycans can be used for imputing missing covariate data in deep learning frameworks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biology, Faculty of Science, University of Zagreb, 10000 Zagreb, Croatia.
- Genos Glycoscience Research Laboratory, 10000 Zagreb, Croatia.
- Faculty of Pharmacy and Biochemistry, University of Zagreb, 10000 Zagreb, Croatia.
- Department of Public Health, University of Split School of Medicine, 21000 Split, Croatia.
- Croatian Science Foundation, 10000 Zagreb, Croatia.
ORCID-Profile: Gordan Lauc, Ozren Polašek, Aleksandar Vojta
Förderung
- Croatian Science Foundation
Zitieren
APA
Vujić, A., Klasić, M., Lauc, G., Polašek, O., Zoldoš, V., & Vojta, A. (2024). Predicting Biochemical and Physiological Parameters: Deep Learning from IgG Glycome Composition. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms25189988
Vancouver
Vujić A, Klasić M, Lauc G, Polašek O, Zoldoš V, Vojta A. Predicting Biochemical and Physiological Parameters: Deep Learning from IgG Glycome Composition. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms25189988
BibTeX
@article{Vuji2024,
author = {Vujić, Ana and Klasić, Marija and Lauc, Gordan and Polašek, Ozren and Zoldoš, Vlatka and Vojta, Aleksandar},
title = {Predicting Biochemical and Physiological Parameters: Deep Learning from IgG Glycome Composition},
journal = {International Journal of Molecular Sciences},
year = {2024},
doi = {10.3390/ijms25189988}
}
EUVIMED