Developing a quantitative structure–property relationships (QSPR) model using Caco‐2 cell bioavailability indicators (BA) to predict the BA of phytochemicals
Journal of the Science of Food and Agriculture · 2025
DOI: 10.1002/jsfa.14400 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Science of Food and Agriculture, 2025. Verfasst von Kang-Woo Lee und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Food Science and Biotechnology, Sejong University, Seoul, South Korea. Hauptthemen laut MEDLINE: Phytochemicals. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Development of Data Utilization Technology for Natural Product Research.
Abstract (Originalsprache)
BACKGROUND The present study aimed to measure bioavailability (BA) indicators, including epithelial barrier function, apparent permeability ( P app ) 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), R 2 Train is 0.86, root mean square error (RMSE) Train is 55.25, R 2 Test is 0.63 and RMSE Test is 74.77, respectively. Regarding the P app , the model demonstrated strong performance on the training set with RMSE Train of 4.54 × 10 −6 and R 2 Train of 0.95 with the test set results (RMSE Test = 6.23 × 10 −6 and R 2 Test = 0.91). For the efflux ratio, the modle explains 92% of the variance with RMSE Train of 0.39, R 2 Train of 0.92, R 2 Test of 0.85 and RMSE Test of 0.71. CONCLUSION The present study suggests that a prediction system for bioavailability, including TEER, P app 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Food Science and Biotechnology, Sejong University, Seoul, South Korea.
- Center for Natural Product Systems Biology, Gangneung Institute of Natural Products, Korea Institute of Science and Technology, Gangneung, South Korea.
- Natural Product Applied Science, KIST School, University of Science and Technology, Gangneung, South Korea.
ORCID-Profile: Kyungsu Kang, Soon-Mi Shim
Förderung
- Development of Data Utilization Technology for Natural Product Research
Zitieren
APA
Lee, K. W., Lee, D. H., Na, I. S., Kim, J. W., Lee, N. Y., Park, J. S., Park, K., Nguyen, C. H. B., Kang, K., & Shim, S. M. (2025). Developing a quantitative structure–property relationships (QSPR) model using Caco‐2 cell bioavailability indicators (BA) to predict the BA of phytochemicals. Journal of the Science of Food and Agriculture. https://doi.org/10.1002/jsfa.14400
Vancouver
Lee KW, Lee DH, Na IS, Kim JW, Lee NY, Park JS, et al. Developing a quantitative structure–property relationships (QSPR) model using Caco‐2 cell bioavailability indicators (BA) to predict the BA of phytochemicals. Journal of the Science of Food and Agriculture. 2025. doi:10.1002/jsfa.14400
BibTeX
@article{Lee2025,
author = {Lee, Kang-Woo and Lee, Dong-Ho and Na, In-Su and Kim, Jin-Woo and Lee, Na-Yeon and Park, Jin-Soo and Park, Keunwan and Nguyen, Chau Hoang Bao and Kang, Kyungsu and Shim, Soon-Mi},
title = {Developing a quantitative structure–property relationships (QSPR) model using Caco‐2 cell bioavailability indicators (BA) to predict the BA of phytochemicals},
journal = {Journal of the Science of Food and Agriculture},
year = {2025},
doi = {10.1002/jsfa.14400}
}
EUVIMED