Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

The Blood-brain Barrier

The Blood-brain Barrier

You might also read

Related Articles

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

Sort by

Same author

Environmental Effects via Frozen Density Embedding in Real-Time Time-Dependent Dirac-Kohn-Sham Theory: Solvation of Lead Halides.

Journal of chemical theory and computation·2026

Same author

Vibrational relaxation rate coefficients in CS-He collisions up to the dissociation limit: mixed quantum-classical calculations and neural network predictions.

Physical chemistry chemical physics : PCCP·2026

Same author

Advancing spatial-omics through Pyxis, vendor-neutral software for ion mobility mass spectrometry imaging data analysis.

Analytical and bioanalytical chemistry·2025

Same author

Selection of short Gadd45β-binding peptides through a synergistic computational and biophysical approach.

Protein science : a publication of the Protein Society·2025

Same author

Transferable and Transparent Energy Decomposition-Based Machine Learning Models for Computing Accurate Reaction Energetics.

Journal of chemical theory and computation·2025

Same author

Towards sustainable lipidomics: computational screening and experimental validation of chloroform-free alternatives for lipid extraction.

Analytical and bioanalytical chemistry·2025

Same journal

PSDTA: An Approach to Drug-Target Binding Affinity Prediction by Integrating Physicochemical and Structural Information to Reduce Feature Redundancy.

Journal of chemical information and modeling·2026

Same journal

M-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21.

Journal of chemical information and modeling·2026

Same journal

Advancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities.

Journal of chemical information and modeling·2026

Same journal

A Unified Molecular Graph and Protein Language Model Framework for Predicting Human Drug-Hormone Receptor Interactions with Structure-Aware Validation.

Journal of chemical information and modeling·2026

Same journal

Intricate Role of Cholesterol in Membrane Fusion.

Journal of chemical information and modeling·2026

Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 17, 2025

Author Spotlight: A Personalized Approach Towards Investigating Alzheimer's Disease Using an In Vitro Blood-Brain Barrier Model

Author Spotlight: A Personalized Approach Towards Investigating Alzheimer's Disease Using an In Vitro Blood-Brain Barrier Model

Published on: October 20, 2023

DeepGRID: Deep Learning Using GRID Descriptors for BBB Prediction.

Loriano Storchi¹, Gabriele Cruciani², Simon Cross³

¹Dipartimento di Farmacia, Università G. D'Annunzio, Via dei Vestini 31, 66100 Chieti, Italy.

Journal of Chemical Information and Modeling

|August 28, 2023

Summary

This summary is machine-generated.

Deep Learning models using novel GRID-derived AI (GrAId) descriptors and Convolutional Neural Networks (CNNs) accurately predict blood-brain barrier permeation. This DeepGRID approach offers a rotationally, conformationally, and alignment-independent method for drug design.

More Related Videos

High-resolution Confocal Imaging of the Blood-brain Barrier: Imaging, 3D Reconstruction, and Quantification of Transcytosis

High-resolution Confocal Imaging of the Blood-brain Barrier: Imaging, 3D Reconstruction, and Quantification of Transcytosis

Published on: November 16, 2017

A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents

A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents

Published on: July 16, 2020

Related Experiment Videos

Last Updated: Jul 17, 2025

Author Spotlight: A Personalized Approach Towards Investigating Alzheimer's Disease Using an In Vitro Blood-Brain Barrier Model

Author Spotlight: A Personalized Approach Towards Investigating Alzheimer's Disease Using an In Vitro Blood-Brain Barrier Model

Published on: October 20, 2023

High-resolution Confocal Imaging of the Blood-brain Barrier: Imaging, 3D Reconstruction, and Quantification of Transcytosis

High-resolution Confocal Imaging of the Blood-brain Barrier: Imaging, 3D Reconstruction, and Quantification of Transcytosis

Published on: November 16, 2017

A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents

A High-Throughput Image-Guided Stereotactic Neuronavigation and Focused Ultrasound System for Blood-Brain Barrier Opening in Rodents

Published on: July 16, 2020

Area of Science:

Computational chemistry
Cheminformatics
Machine learning

Background:

Blood-brain barrier (BBB) permeation is crucial for central nervous system (CNS) drug development.
Traditional methods like VolSurf used GRID Molecular Interaction Fields (MIFs) with Partial Least Squares (PLS) for modeling BBB permeation.
Developing accurate predictive models for BBB permeation remains a challenge.

Purpose of the Study:

To introduce DeepGRID, a novel Deep Learning approach combining GRID-derived AI (GrAId) descriptors with Convolutional Neural Networks (CNNs).
To develop rotationally, conformationally, and alignment-independent models for predicting blood-brain barrier permeation.
To compare the performance of DeepGRID models against traditional methods like VolSurf with PLS and Random Forest (RF).

Main Methods:

Development of GRID-derived AI (GrAId) descriptors, a modification of GRID MIFs.
Integration of GrAId descriptors with CNNs to create DeepGRID models.
Application of DeepGRID for both regression and classification tasks related to BBB permeation.
Comparison with models using hand-crafted VolSurf descriptors and PLS/RF algorithms.

Main Results:

DeepGRID and RF regression models demonstrated superior performance in predicting BBB permeation, with the highest percentage of compounds within a 2-fold geometric mean fold error.
For classification tasks on smaller datasets, all models performed well with ROC AUC values around 0.9.
On a larger dataset, the DeepGRID classifier achieved the highest AUC (0.87), outperforming RF (0.84) and the original VolSurf model (0.83).

Conclusions:

DeepGRID represents a significant advancement in modeling BBB permeation using Deep Learning.
The rotationally, conformationally, and alignment-independent nature of DeepGRID enhances its utility in drug discovery.
DeepGRID offers a powerful and accurate alternative for predicting BBB permeation compared to existing methods.