Proteomic Profiling and Machine Learning for Endotype Prediction in Chronic Rhinosinusitis
Journal of Allergy and Clinical Immunology, 2025
Morgenstern C., Bartosik T., Bayer K., Campion N., Frommlet F., Gangl K., Kidane F., Liu L., Schmetterer K., Stanek V., Tu A., Ungersbäck K., Zghaebi M., Schneider S., Eckl-Dorna J.
| Disease area | Application area | Sample type | Products |
|---|---|---|---|
Immunological & Inflammatory Diseases | Pathophysiology Patient Stratification | Serum Nasal Fluid |  Olink Target 96  Olink Explore 3072/384 |
Abstract
Background: Chronic rhinosinusitis (CRS) is a common, heterogeneous upper airway inflammatory disorder, affecting approximately 12% of the general population. The disease is clinically stratified into CRS without nasal polyps (CRSsNP) and CRS with nasal polyps (CRSwNP), including the most severe subtype of non-steroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD).
Objective: In order to identify molecular signatures and biomarkers allowing for the distinction between different disease endotypes and controls, we employed targeted proteomics combined with bioinformatics and Machine Learning analyses.
Methods: Nasal secretions and serum from 80 patients (20 each of CRSsNP, CRSwNP, N-ERD, and disease controls) were subjected to high-throughput targeted proteomics (Olink®) and the expression patterns of 161 and 2677 proteins, for nasal secretions and serum, respectively, analyzed alongside clinical evaluations of nasal polyp and smell test scores.
Results: Two distinct expression patterns were identified in nasal secretions: proteins associated with macrophage recruitment and type 2 inflammation were increased in CRSwNP and N-ERD, whilst proteins associated with innate immunity, particularly Toll-like receptor 4 signaling (TLR4), were gradually downregulated from DC to N-ERD. Furthermore, using Machine Learning, we confirmed two potential biomarkers for nasal polyposis: the glial cell line-derived neurotrophic factor (GDNF) in nasal secretions and Charcot-Leyden crystal protein (CLC) in serum.
Conclusion: Our findings provide unique insights into CRS pathophysiology and highlight potential biomarkers for precision diagnosis and treatment, particularly in severe cases such as N-ERD.
Clinical implications: Our findings enhance the understanding of CRS pathophysiology and identify potential biomarkers for precise diagnosis, especially in severe cases like N-ERD, informing the design of targeted therapeutic strategies.