Detection of Biomarker in Biopsies Based on Hr-Mas 2D HSQC Spectroscopy Indexation

Abstract

Multiple Sclerosis MS is one of the principal causes of morbidity worldwide. One of the strategies employed by the emergent science of metabolomics is MS biomarker identification. In this context, the technique of High-Resolution Magic Angle Spinning (HR-MAS) Nuclear Magnetic Resonance (NMR) spectra is widely used in metabolomic analysis involving tissue studies. Indeed, the NMR offers the potential to study molecular structures and their associations and interactions. In this paper, we present a new content-based object indexing and retrieval scheme for biomarkers detection. The biomarker identification is addressed by comparing 2D NMR MS spectrum groups for metabolite change detection using kernel based support vector data description (SVDD). Preliminary results obtained on synthetic spectrum database are shortly presented.