Identifying Candidate Diseases-related Metabolites Based on Disease Similarity

Functional related metabolites have a close relationship with complex diseases, and are often associated with the same or similar diseases. Therefore, identification of disease related metabolites is significant for understanding comprehensively pathogenesis of disease, aiming at improving the clinical medicine. Considering that a large number of metabolic markers of diseases need to be explored, we propose a method to identify potential disease-related metabolites based on metabolite functional similarity network. Firstly, we calculate the similarity of metabolites based on modified recommendation strategy of Collaborative Filtering utilizing the similarities between diseases. Next, a disease associated metabolite network is built with similarities between metabolites as weight. Finally, we utilize random walking with restart in this network to find more unknown metabolic markers related to one disease. This method offers researchers a new way to identify potential disease-related metabolic markers.