Application of QSRR models for predicting the retention times of plant food bioactive compounds

Liquid chromatography (LC) coupled to mass spectrometry (MS) is a powerful and versatile technique with several applications in analytical chemistry such as the untargeted analysis of complex mixtures of plant food bioactive compounds. In this framework, identification of compounds mainly relies on mass and fragmentation patterns derived from MS spectra of available databases. However, to develop automated tools for a rapid compound identification, prior knowledge of retention times (RTs) has been demonstrated to be a valid support to MS data to reduce the number of possible candidate structures. Unlike experimental methods, which are time-consuming and limited to a few classes of compounds, data-driven computational approaches can predict retention times for a wide range of compounds using only their molecular structures and physicochemical properties. In this research, Genetic Algorithms (GAs) coupled to Multiple Linear Regression (MLR) were applied to select the most relevant molecular descriptors to establish quantitative structure-retention relationships (QSRRs) aimed at predicting the retention times of plant food bioactive compounds across three different LC chromatographic systems. The statistical parameters showed model robustness and satisfactory predictive ability. Particular attention was paid to measuring the uncertainty of predictions and assessing their reliability based on the model applicability domain. Interpretation of the selected molecular descriptors provided valuable insight into the separation mechanism. Finally, the developed models were applied to predict the unknown retention times, for the three studied LC chromatographic systems, of a large library of plant food bioactive compounds, which were made freely available to further assist the research in the field of natural products.