Discrimination of mung beans according to climate and growing region by untargeted metabolomics coupled with machine learning methods

Abstract

Mung bean is an important pulse in China owing to its nutritional and bioactive properties, however, the quality characteristics of mung beans from different climate zones and growing regions in China remain unknown. In the present study, an untargeted metabolomics approach based on ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry (UPLC-QTOF-MS) coupled with machine learning was used to compare and discriminate mung beans from different climate zones and growing regions. Based on orthogonal partial least squares-discriminant analysis (OPLS-DA), 39 and 35 differential metabolites were identified in mung bean samples among three climate zones and 11 growing regions, respectively. The differential metabolites mainly included lipids, flavonoids, soyasaponins, amino acids, peptides, indoles and their derivatives, and acids. Random forest (RF) and support vector machine (SVM) models were established, optimized, and used to discriminate mung beans from different climate zones and growing regions. The SVM models performed better than the RF models in predicting both the climate zone and growing region of mung beans, with accuracies of 100% and 98.72%, respectively. Our results demonstrate that untargeted metabolomics coupled with machine learning could be a powerful tool for discriminating of mung beans from different climate zones and growing regions.