Kernel-based reliability potential to assist QSPR prediction and system transfer of SFC−MS retention time

Quantitative Structure-Property Relationship (QSPR) allows in silico prediction of chromatographic retention time of chemicals from their molecular structure. The QSPR approach relies on the principle that retention time is influenced by molecular properties, which can be encoded into chemical-structural descriptors and modelled with chemometric techniques. This study focuses on in silico prediction of supercritical fluid chromatography (SFC) retention time. First, we developed a novel QSPR model for predicting retention times measured with high-resolution mass spectrometry (SFC-HRMS); then, the same model was adapted to predict retention times of a different chromatographic system based on low-resolution mass spectrometry (SFC-LRMS). We used a kernel-based approach to account for prediction uncertainties and to leverage the model reliability by defining a structural domain in the chemical space where lower uncertainty is expected. Results demonstrated that the proposed approach can predict retention time across two chromatographic systems when considering the reliability domain established with the kernel approach. The use of the proposed method for estimating the reliability domain can enhance the application of QSPR models to predict and transfer retention times in chromatographic systems similar to those used for the calibration and, consequently, simplify the identification of compounds in untargeted analyses and boost the design, development and optimization of novel chromatographic methods. • QSPR is a reliable tool for rapid in silico prediction of chromatographic retention time • We developed QSPRs for predicting supercritical fluid chromatography (SFC-HRMS) retention time • Predictions were transferred to a different chromatographic system (SFC-LRMS) • We used a kernel-based approach to account for prediction reliability