EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of human intestinal passive membrane permeability using physiologically informed machine learning models

Reiji Negoya, Atsushi Kambayashi

European Journal of Pharmaceutics and Biopharmaceutics · 2027-01 · 230 · 115291

DOI: 10.1016/j.ejpb.2026.115291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Pharmaceutics and Biopharmaceutics, 2027-01. Verfasst von Reiji Negoya und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Pharmaceutical Sciences, Tokyo University of Science, Tokyo, Japan. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting human intestinal passive membrane permeability (Peff) is essential for reliable application of physiologically based biopharmaceutics models (PBBMs). Although in vitro cell-based assays and animal studies are widely used, their predictive performance is often limited by inter-laboratory variability and species differences. Furthermore, accurate prediction of intrinsic permeability requires consideration of physiological factors, particularly correction for the unstirred water layer (UWL) and exclusion of transporter-mediated transport. We developed machine learning models to predict human jejunal Peff directly from chemical structure using a physiologically curated dataset derived from in vivo human jejunal permeability data. The dataset was refined by excluding transporter substrates and correcting for UWL resistance to estimate intrinsic cellular permeability (Pcell). To maximize predictive performance while maintaining robustness with a limited dataset, two feature selection strategies were evaluated: a data-driven approach to identify novel structure-permeability relationships and a hypothesis-driven approach based on established physicochemical principles. The practical applicability of the developed models was assessed by incorporating the predicted Peff values into a PBBM. The data-driven model demonstrated superior generalization performance and accurately reproduced observed human plasma concentration-time profiles. These findings demonstrate that the proposed approach can robustly predict intrinsic human intestinal membrane permeability from chemical structure alone.

Schlagwörter

Stichwörter der Autor:innen

Intestinal permeabilityMachine learningPassive diffusionPhysiologically based biopharmaceutics modelQuantitative structure–activity relationship

Autor:innen und Institutionen

  • Faculty of Pharmaceutical Sciences, Tokyo University of Science, Tokyo, Japan.
  • Faculty of Pharmaceutical Sciences, Tokyo University of Science, Tokyo, Japan. Electronic address: kambayashi@rs.tus.ac.jp.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Negoya, R., & Kambayashi, A. (2027). Prediction of human intestinal passive membrane permeability using physiologically informed machine learning models. European Journal of Pharmaceutics and Biopharmaceutics, 230, 115291. https://doi.org/10.1016/j.ejpb.2026.115291

Vancouver

Negoya R, Kambayashi A. Prediction of human intestinal passive membrane permeability using physiologically informed machine learning models. European Journal of Pharmaceutics and Biopharmaceutics. 2027;230:115291. doi:10.1016/j.ejpb.2026.115291

BibTeX
@article{Negoya2027,
  author = {Negoya, Reiji and Kambayashi, Atsushi},
  title = {Prediction of human intestinal passive membrane permeability using physiologically informed machine learning models},
  journal = {European Journal of Pharmaceutics and Biopharmaceutics},
  year = {2027},
  volume = {230},
  pages = {115291},
  doi = {10.1016/j.ejpb.2026.115291}
}
Kostenlos starten →