Interpretation of type 2 diabetes mellitus relevant GC-MS metabolomics fingerprints by using random forests

In this study, we discussed the application of random forest (RF) methods for extracting relevant biological knowledge from two type 2 diabetes mellitus (T2DM) relevant metabolomics fingerprinting experiments. The models constructed by RF could visually discriminate type 2 diabetic mice from a healthy control group and represent the variance of metabolic profiles of diabetic mice in the therapeutic process with repaglinide. Simultaneously, some informative metabolites have been successfully discovered by means of variable importance ranking in the RF program. The current research demonstrated that RF was a versatile classification algorithm, which was suitable for the analysis of complex metabolomics data and would be a complement or an alternative to pathogenesis and pharmacodynamics research.