Compositional and Structural Analysis for Non-Insulin Dependent Diabetes through Artificial Intelligence and Bioinformatics Tools

NIDDM is a global health central problem resulting from a variety of interactions between genetics and environment conditions especially nutritional frailties that one is likely to develop during his or her early years. The scopes of this study is to perform a compositional and structural analysis of proteins involved in the development of NIDDM using advanced computational biology approaches and AI tools. In particular, we used Perl based algorithm to compare diverse protein sequences to identify potential PVs for a set of proteins involved in metabolic pathways implicated in insulin signalling, glucose homeostasis and cardiovascular disease. In this study, we provide an approach that uses machine learning to extract biomarkers and characterize IR and its symptoms. Through analyzing structural motifs and PTMs, we identify pathogenesis of NIDDM and define the targets for intervention. The information gaining from this research is useful in generating models of prognosis and treatments besides offering molecular aspect of NIDDM. Finally, the result of the current study underlines the need for early ENCN and the concept of individualized treatment for relieving and controlling NIDDM among high risk individuals.