Predicting Blood-Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework.

Overview

1. School of Materials Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea
2. Department of Geriatrics, Ludwik Rydygier Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun, 9 Skłodowskiej Curie Str., 85-094 Bydgoszcz, Poland
3. Department of Toxicology and Bromatology, Ludwik Rydygier Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun, 2 Jurasza Str., 85-089 Bydgoszcz, Poland
4. Department of Organic and Physical Chemistry, Medical University of Warsaw, 1 Banacha Str., 02-097 Warsaw, Poland

Abstract

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.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• github.com/theochem/b3db, at github.com; found in “Data Availability Statement”

Data Availability Statement

Additional information is available from the corresponding author upon reasonable request. All raw data are freely available at https://github.com/theochem/B3DB (accessed on 10 March 2026).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 7 keywords, 1 funder, 32 references.

Cite

This paper

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

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1021/acs.jcim.5c02891

Overrepresentation Bias Leads to Performance Overestimation in Blood-Brain Barrier Permeability Prediction Models: Characterization and Mitigation.

Journal: Journal of chemical information and modeling

In common: methods / tools, 4 references

[2] doi:10.1021/acs.jmedchem.6c00035

The Discovery of TNG456: A Highly Potent, Selective, Brain-Penetrant MTA-Cooperative PRMT5 Inhibitor for the Treatment of <i>MTAP</i>-Deleted Cancers.

Journal: Journal of medicinal chemistry

In common: 4 references

[3] doi:10.1016/j.isci.2026.117147 [code]

Penetrating potential evaluation of cyclotriphosphazenes target blood-brain barrier via computational toxicology methods.

Journal: iScience

In common: methods / tools, 3 references

[4] doi:10.1016/j.apsb.2026.05.021 [code]

Design, preclinical evaluation, and multicenter phase 1 clinical study of HZ-A-018 for relapsed or refractory central nervous system lymphoma.

Journal: Acta pharmaceutica Sinica. B

In common: github.com/theochem/b3db

[5] doi:10.1016/j.namjnl.2026.100121 [code]

Predicting blood-brain barrier permeability of chemicals by machine learning modeling.

Journal: NAM journal

In common: 3 references

[6] doi:10.1172/jci.insight.198298

Development and characterization of triazole-based WDR5 inhibitors for the treatment of glioblastoma.

Journal: JCI insight

In common: 2 references

[7] doi:10.3390/ijms27167240

1-Piperidine Propionic Acid Inhibits PAR2/SerpinB3 Signaling and Reduces Glioblastoma Tumor Aggressiveness.

Journal: International journal of molecular sciences

In common: 2 references

[8] doi:10.1097/md.0000000000050324

Transcriptomic integration reveals immune heterogeneity in vascular dementia and identifies ELF2 as a candidate therapeutic target.

Journal: Medicine

In common: 2 references

[9] doi:10.3390/ph19081319 [code]

DeepBBB: A Data-Composition-Aware Graph Screening Workflow for BBB-Focused CNS Library Construction and Prospective PAMPA-BBB Evaluation.

Journal: Pharmaceuticals (Basel, Switzerland)

In common: 2 references

[10] doi:10.3390/jcm15176501 [code]

Saliency-Curated Deep Learning for Predicting Receptor Status in Breast Cancer Brain Metastases.

Journal: Journal of clinical medicine

In common: 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.