Integrating Metabolomic Data With Machine Learning Approach for Discovery of Q-markers From Jinqi Jiangtang Preparation Against Type 2 Diabetes

Abstract Background: Jinqi Jiangtang (JQJT) has been widely used in clinical practice to prevent and treat type 2 diabetes. However, little was known about its quality markers (Q-markers) associated with anti-diabetes bioactivity. In this study, a strategy combining mass spectrometry-based untargeted metabolomics with backpropagation artificial neural network (BP-ANN)-based machine learning approach was proposed to screen Q-markers from JQJT preparation. Methods: This strategy mainly involved chemical profiling of herbal medicines, statistic processing of metabolomic datasets, detection of different anti-diabetes activities and establishing of BP-ANN model. The chemical features of seventy-eight batches of JQJT extracts were first profiled using an untargeted UPLC-LTQ-Orbitrap metabolomic approach. The obtained chemical features associated with different anti-diabetes activities based on three modes of action were normalized, ranked, and then pre-selected by using ReliefF feature selection, respectively. BP-ANN model was then established and optimized to screen Q-markers based on mean impact value (MIV).Results: Optimized BP-ANN architecture was established with high accuracy of R > 0.9983 and relative low error of MSE < 0.0014, which showed better performance than that of PLSR calibration model (R2 < 0.5). Meanwhile, the BP-ANN model was subsequently applied to further screen potential bioactive components from the pre-selected chemical features by calculating their MIVs. Using this machine learning model, 15 potential Q-markers with bioactivity were discovered from JQJT. The tested anti-diabetes bioactivities of 78 batches of JQJT could be accurately predicted.Conclusions: The proposed artificial intelligence approach is suitable for quick and easy discovery of Q-markers with bioactivity from herbal medicines.