Machine learning prediction for constructing a universal multidimensional information library of Panax saponins (ginsenosides).

Accurate characterization of Panax herb ginsenosides is challenging because of the isomers and lack of sufficient reference compounds. More structural information could help differentiate ginsenosides and their isomers, enabling more accurate identification. Based on the VionTM ion-mobility high-resolution LC-MS platform, a multidimensional information library for ginsenosides, namely GinMIL, was established by predicting retention time (tR) and collision cross section (CCS) through machine learning. Robustness validation experiments proved tR and CCS were suitable for database construction. Among three machine learning models we attempted, gradient boosting machine (GBM) exhibited the best prediction performance. GinMIL included the multidimensional information (m/z, molecular formula, tR, CCS, and some MS/MS fragments) for 579 known ginsenosides. Accuracy in identifying ginsenosides from diverse ginseng products was greatly improved by a unique LC-MS approach and searching GinMIL, demonstrating a universal Panax saponins library constructed based on hierarchical design. GinMIL could improve the accuracy of isomers identification by approximately 88%.

A practical strategy enabling more reliable identification of ginsenosides from Panax quinquefolius flower by dimension-enhanced liquid chromatography/mass spectrometry and quantitative structure-retention relationship-based retention behavior prediction.

To accurately identify the metabolites is crucial in a number of research fields, and discovery of new compounds from the natural products can benefit the development of new drugs. However, the preferable phytochemistry or liquid chromatography/mass spectrometry approach is time-/labor-extensive or receives unconvincing identifications. Herein, we presented a strategy, by integrating offline two-dimensional liquid chromatography/ion mobility-quadrupole time-of-flight mass spectrometry (2D-LC/IM-QTOF-MS), exclusion list-containing high-definition data-dependent acquisition (HDDDA-EL), and quantitative structure-retention relationship (QSRR) prediction of the retention time (tR), to facilitate the in-depth and more reliable identification of herbal components and thus to discover new compounds more efficiently. Using the saponins in Panax quinquefolius flower (PQF) as a case, high orthogonality (0.79) in separating ginsenosides was enabled by configuring the XBridge Amide and CSH C18 columns. HDDDA-EL could improve the coverage in MS2 acquisition by 2.26 folds compared with HDDDA (2933 VS 1298). Utilizing 106 reference compounds, an accurate QSRR prediction model (R2 = 0.9985 for the training set and R2 = 0.88 for the validation set) was developed based on Gradient Boosting Machine (GBM), by which the predicted tR matching could significantly reduce the isomeric candidates identification for unknown ginsenosides. Isolation and establishment of the structures of two malonylginsenosides by NMR partially verified the practicability of the integral strategy. By these efforts, 421 ginsenosides were identified or tentatively characterized, and 284 thereof were not ever reported from the Panax species. The current strategy is thus powerful in the comprehensive metabolites characterization and rapid discovery of new compounds from the natural products.

Collision Cross Section Prediction Based on Machine Learning.

Ion mobility-mass spectrometry (IM-MS) is a powerful separation technique providing an additional dimension of separation to support the enhanced separation and characterization of complex components from the tissue metabolome and medicinal herbs. The integration of machine learning (ML) with IM-MS can overcome the barrier to the lack of reference standards, promoting the creation of a large number of proprietary collision cross section (CCS) databases, which help to achieve the rapid, comprehensive, and accurate characterization of the contained chemical components. In this review, advances in CCS prediction using ML in the past 2 decades are summarized. The advantages of ion mobility-mass spectrometers and the commercially available ion mobility technologies with different principles (e.g., time dispersive, confinement and selective release, and space dispersive) are introduced and compared. The general procedures involved in CCS prediction based on ML (acquisition and optimization of the independent and dependent variables, model construction and evaluation, etc.) are highlighted. In addition, quantum chemistry, molecular dynamics, and CCS theoretical calculations are also described. Finally, the applications of CCS prediction in metabolomics, natural products, foods, and the other research fields are reflected.