Predicting Blood–Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework
Pharmaceutics · 28.05.2026 · 18 (6) · 670
DOI: 10.3390/pharmaceutics18060670 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pharmaceutics, online erschienen am 28.05.2026. Verfasst von Saurabh Tiwari und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Materials Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
The blood–brain barrier (BBB), which restricts the brain penetration of most small molecules and almost all biologics, continues to be a significant hurdle in the development of drugs for the central nervous system (CNS). During early-stage screening, a reliable computational prediction of BBB permeability, typically expressed as log BB, can help reduce the experimental load.
Methods
We provide a well-validated machine learning system created solely using the B3DB experimental database, which includes 7807 chemicals with BBB+/BBB− annotations and 1058 compounds with in vivo log BB values. Using the Mordred library, a carefully selected set of 40 two-dimensional chemical descriptors was calculated from SMILES notation without the use of artificial data augmentation. Stratified five-fold cross-validation was used to comprehensively benchmark the nine methods used in this study.
Results
On a held-out test set (n = 212), gradient boosting produced the greatest regression performance, with R2 = 0.6043, RMSE = 0.4740 log units, and MAE = 0.3326, which is in line with the upper range recorded for experimental BBB datasets. On an internal test set (n = 1562), the corresponding classifier obtained an AUC-ROC of 0.9476 and a balanced accuracy of 0.8568; on an independent external validation set (n = 175), it achieved an AUC-ROC of 0.9137. Topological polar surface area was found by SHAP analysis to be the primary factor influencing BBB permeability, with lipophilicity and ionization-related characteristics being the second and third most important factors, respectively. Nonlinear relationships in accordance with accepted pharmacokinetic principles were validated using partial dependence analysis.
Conclusion
This study provides a reliable technique for predicting BBB permeability in CNS drug discovery.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Materials Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea.
- Department of Geriatrics, Ludwik Rydygier Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun, 9 Skłodowskiej Curie Str., 85-094 Bydgoszcz, Poland.
- Department of Toxicology and Bromatology, Ludwik Rydygier Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun, 2 Jurasza Str., 85-089 Bydgoszcz, Poland.
- Department of Organic and Physical Chemistry, Medical University of Warsaw, 1 Banacha Str., 02-097 Warsaw, Poland.
ORCID-Profile: Saurabh Tiwari, Katarzyna Mądra-Gackowska, Marcin Gackowski, Nokeun Park, Łukasz Szeleszczuk
Zitieren
APA
Tiwari, S., Mądra-Gackowska, K., Gackowski, M., Park, N., & Szeleszczuk, Ł. (2026). Predicting Blood–Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework. Pharmaceutics, 18(6), 670. https://doi.org/10.3390/pharmaceutics18060670
Vancouver
Tiwari S, Mądra-Gackowska K, Gackowski M, Park N, Szeleszczuk Ł. Predicting Blood–Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework. Pharmaceutics. 2026;18(6):670. doi:10.3390/pharmaceutics18060670
BibTeX
@article{Tiwari2026,
author = {Tiwari, Saurabh and Mądra-Gackowska, Katarzyna and Gackowski, Marcin and Park, Nokeun and Szeleszczuk, Łukasz},
title = {Predicting Blood–Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework},
journal = {Pharmaceutics},
year = {2026},
volume = {18},
number = {6},
pages = {670},
doi = {10.3390/pharmaceutics18060670}
}
EUVIMED