Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

The Blood-brain Barrier00:49

The Blood-brain Barrier

Overview
Physiological Barriers01:25

Physiological Barriers

Physiological barriers are semi-permeable cellular structures restricting drug diffusion into intracellular compartments and tissues. There are six types of physiological barriers: blood endothelial, cell membrane, blood-brain, blood-cerebrospinal fluid (CSF), blood-placenta, and blood-testis barriers.
The blood endothelial barrier is the most porous of these. It allows all small ionized, un-ionized, and lipophilic molecules to pass through the endothelial lining into the interstitial space...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Flavonoids as Modulators of the p53-Bcl-2 Axis in Cancer: Molecular Mechanisms and Therapeutic Implications.

Pharmaceutics·2026
Same author

Molecular Docking of Natural Compounds as DPP-4 Inhibitors in Type 2 Diabetes: A Comprehensive Review.

Pharmaceutics·2026
Same author

BPC-157 and Its Novel Hybrid Analogs as Inhibitors of Acetylcholinesterase.

International journal of molecular sciences·2026
Same author

Machine Learning-Based Prediction of Stacking Fault Energy in High-Manganese Steels: A Comparative Study of Ensemble and Kernel Methods.

Materials (Basel, Switzerland)·2026
Same author

Receptor Binding, Functional Activity, and Cell Viability Assessment of Novel Marine-Based Hybrid Peptides from <i>Raja porosa</i>.

Marine drugs·2026
Same author

Prediction of Hole Expansion Ratio in Advanced High-Strength Steels Using Physics-Informed Machine Learning.

Materials (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jun 27, 2026

A Human Blood-Brain Interface Model to Study Barrier Crossings by Pathogens or Medicines and Their Interactions with the Brain
07:52

A Human Blood-Brain Interface Model to Study Barrier Crossings by Pathogens or Medicines and Their Interactions with the Brain

Published on: April 9, 2019

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

Saurabh Tiwari1, Katarzyna Mądra-Gackowska2, Marcin Gackowski3

  • 1School of Materials Science and Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea.

Pharmaceutics
|June 26, 2026
PubMed
Summary

This study developed a machine learning model to predict blood-brain barrier (BBB) permeability, aiding CNS drug discovery. The model accurately forecasts drug penetration, reducing experimental screening needs.

Keywords:
B3DBCNS drug designSHAP interpretabilityblood–brain barriergradient boostingmachine learningmordred descriptors

More Related Videos

An In Vivo Blood-brain Barrier Permeability Assay in Mice Using Fluorescently Labeled Tracers
09:35

An In Vivo Blood-brain Barrier Permeability Assay in Mice Using Fluorescently Labeled Tracers

Published on: February 26, 2018

Use of the MicroSiM (&#181;SiM) Barrier Tissue Platform for Modeling the Blood-Brain Barrier
09:10

Use of the MicroSiM (µSiM) Barrier Tissue Platform for Modeling the Blood-Brain Barrier

Published on: January 12, 2024

Related Experiment Videos

Last Updated: Jun 27, 2026

A Human Blood-Brain Interface Model to Study Barrier Crossings by Pathogens or Medicines and Their Interactions with the Brain
07:52

A Human Blood-Brain Interface Model to Study Barrier Crossings by Pathogens or Medicines and Their Interactions with the Brain

Published on: April 9, 2019

An In Vivo Blood-brain Barrier Permeability Assay in Mice Using Fluorescently Labeled Tracers
09:35

An In Vivo Blood-brain Barrier Permeability Assay in Mice Using Fluorescently Labeled Tracers

Published on: February 26, 2018

Use of the MicroSiM (&#181;SiM) Barrier Tissue Platform for Modeling the Blood-Brain Barrier
09:10

Use of the MicroSiM (µSiM) Barrier Tissue Platform for Modeling the Blood-Brain Barrier

Published on: January 12, 2024

Area of Science:

  • Pharmacology
  • Computational Chemistry
  • Drug Discovery

Background:

  • The blood-brain barrier (BBB) impedes central nervous system (CNS) drug development.
  • Accurate prediction of BBB permeability is crucial for early-stage drug screening.

Purpose of the Study:

  • To develop and validate a machine learning system for predicting blood-brain barrier (BBB) penetration.
  • To reduce the experimental workload in CNS drug discovery through reliable computational predictions.

Main Methods:

  • Utilized the B3DB experimental database with 7807 chemicals for BBB+ / BBB- annotations and 1058 compounds with in vivo log BB values.
  • Calculated 40 selected 2D chemical descriptors from SMILES notation using the Mordred library.
  • Employed stratified five-fold cross-validation to benchmark nine machine learning methods.

Main Results:

  • Gradient boosting achieved the best regression performance (R² = 0.6043) on a held-out test set.
  • The classifier achieved high performance on internal (AUC-ROC = 0.9476) and external (AUC-ROC = 0.9137) validation sets.
  • SHAP analysis identified topological polar surface area, lipophilicity, and ionization as key predictors of BBB permeability.

Conclusions:

  • The developed machine learning system offers a reliable method for predicting BBB permeability.
  • This approach can significantly aid in the early stages of central nervous system drug discovery.