Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
2 results
Search Results
Article Storage Protein Allergen Sensitization Patterns in Children: Insights from Multiplex Microarray Profiling and Hierarchical Clustering(Wiley, 2025) Caka, Canan; Ozcivici, Engin; Karakus, Ceyda Oksel; Sekerel, Bulent EnisBackground Storage proteins (SPs), including 2S albumins, vicilins, and legumins, are key allergenic molecules (AMs) of peanuts, tree nuts (TNs), and sesame. Their structural stability contributes to allergenicity and sensitization. This study explored SP AM clustering patterns and evaluated the test performance of multiplex microarray (MM) testing in a pediatric cohort. Methods We retrospectively analyzed 350 children (median age: 3.7 years) with detectable SP sensitizations (>= 0.1 kU(A)/L) using the ALEX(2) MM platform. Sensitization interrelationships were analyzed using correlation heatmaps, hierarchical clustering (HC), dimensionality reduction, and feature elimination. Predictive utility was assessed through ROC curve analysis at different sensitization cut-offs (>0.1 and >0.3 kU(A)/L) and total IgE thresholds (>0, >20, and >50 kU/L). Results HC identified a broad SP cluster spanning peanuts, TNs, sesame, poppy seed, and buckwheat. Strong correlations and early HC linkages suggested extensive cross-sensitization (e.g., Ana o 3-Pis v 1 and Jug r 4-Cor a 9), alongside evidence of co-sensitization and molecular spreading. Unexpected clustering of structurally dissimilar peanut and pistachio AMs pointed to shared epitopes and/or cross-contamination. 2S albumins (Ara h 2, Cor a 14, Jug r 1, Ana o 3, and Ses i 1) were most predictive for clinical reactivity. Lower cut-offs and exclusion of patients with low total IgE improved test performance. Alpha-hairpinin (Pap s 2S albumin) showed potential as specific markers. Conclusions MM testing enables detailed SP sensitization profiling. Cluster-based interpretation may clarify cross- vs. co-sensitization, supporting informed clinical decisions. Use of recombinant AMs and IgE stratification may further enhance MM utility in food allergy diagnostics.Book Part Citation - WoS: 299Citation - Scopus: 406Introduction To Machine Learning(Humana Press, 2014) Baştanlar, Yalın; Özuysal, MustafaThe machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning approaches for this application area. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning and types of classification. Then, we point out the main issues of designing machine learning experiments and their performance evaluation. Finally, we introduce some supervised learning methods.