Developing a quantitative structure–property relationships (QSPR) model using Caco-2 cell bioavailability indicators (BA) to predict the BA of phytochemicals

Abstract

BACKGROUND: The present study aimed to measure bioavailability (BA) indicators, including epithelial barrier function, apparent permeability (Papp) and efflux ratio, of 84 types of phytochemicals using Caco-2 cell and to develop predictive model systems using machine learning with a quantitative structure–property relationship (QSPR) model based on BA indicators and an Isomeric Simplified Molecular Input Line Entry System (SMILES). Analysis of phytochemicals was carried out with a validated HPLC analytical method. RESULTS: With these BA indicators, Isomeric SMILES including information such as the stereochemistry, chemical structure and properties of phytochemicals was encoded to molecular descriptors using PaDEL-Descriptor and alvaDesc. The validity of the dataset was verified using principal component analysis, leverage plot and Williams plot. In the case of transepithelial electrical resistance (TEER), R2Train is 0.86, root mean square error (RMSE)Train is 55.25, R2Test is 0.63 and RMSETest is 74.77, respectively. Regarding the Papp, the model demonstrated strong performance on the training set with RMSETrain of 4.54 × 10−6 and R2Train of 0.95 with the test set results (RMSETest = 6.23 × 10−6 and R2Test = 0.91). For the efflux ratio, the modle explains 92% of the variance with RMSETrain of 0.39, R2Train of 0.92, R2Test of 0.85 and RMSETest of 0.71. CONCLUSION: The present study suggests that a prediction system for bioavailability, including TEER, Papp and efflux ratio, can be developed using a QSPR model, which could contribute to advancements in discover of functional ingredients and drugs. © 2025 The Author(s). Journal of the Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.