As the realm of “big data” takes hold due to the exponential growth of omics data, the task of extracting valuable insights from these diverse datasets has become increasingly complex. The advent of machine learning has made significant contributions to addressing challenges in the fields of biology and biomedicine. It has paved the way for the development of therapeutic and diagnostic strategies, particularly in the realm of precision medicine. While machine learning models are relatively recent in the context of omics datasets, there is a growing trend in publications centred around multi-omic integration. Machine learning techniques provide novel tools for analyzing various omics data types, facilitating the identification of fresh biomarkers.
Our objective is to incorporate machine learning applications into clinical glycomics and glycoproteomics to enable the early diagnosis of diseases, including cancer.
Selected Publications:
Demirhan, D. B., Yılmaz, H., Erol, H., Kayili, H. M., & Salih, B. (2023). Prediction of gastric cancer by machine learning integrated with mass spectrometry-based N-glycomics. Analyst, 148(9), 2073-2080.
