Deciphering the TSH-Associated Gene Network: A Comparative Analysis Using Machine Learning Clustering Algorithms

In this study, we conducted gene ontology (GO) and pathway analyses to identify the GO terms most closely related to thyroid-stimulating hormone (TSH) and to infer the protein-protein interaction network using three machine learning clustering algorithms: K-means, MCL (Markov Clustering Algorithm), and DBSCAN (Density-Based Spatial Clustering of Applications with Noise). We analysed a collection of ۱۱۲ TSH-associated genes reported in the literature to date.Our analysis identified ۱۲ GO terms for Molecular Function (MF), ۲۵۹ terms for Biological Process (BP), and ۳ terms for Cellular Component (CC), along with ۱۷ KEGG, ۱۶ REACTOME, and ۱۱ Wiki Pathways in the pathway analysis. Of these, ۵ MF, ۱۰ BP, and ۲ CC GO terms were significant, however, no pathways were detected as significant at the P-value=۰.۰۵ level. The clustering algorithms yielded similar results, notably highlighted AKT۱, TSHR, GNAS, GATA۳, and KDR as key hub genes in the network.

کلیدواژه ها:

Thyroid-stimulating hormone ، Gene ontology ، Clustering algorithm ، Machine learning