Молекулярная и генетическая медицина

Combining Embeddings from Various Protein Language Models to Boost Protein O-GlcNAc Site Prediction Performance

Abstract

Juan Lopez

Protein Post-Translational Modifications (PTMs) are critical regulators of cellular processes, influencing protein function, localization, and interactions. O-GlcNAcylation, the addition of N-acetylglucosamine (GlcNAc) to serine or threonine residues of proteins, is a dynamic and reversible PTM with implications in various diseases, including diabetes, cancer, and neurodegeneration. Accurate prediction of O-GlcNAc sites is essential for understanding their roles in cellular signaling and disease mechanisms. Traditional experimental methods for identifying O-GlcNAc sites, such as mass spectrometry, are timeconsuming and costly. Computational approaches offer a cost-effective and efficient alternative, facilitating large-scale analysis of O-GlcNAcylatio.