BBBP Database

Blood-Brain Barrier Penetration Prediction Platform

Quantitative Dataset

1574

Compounds with LogBB values

Qualitative Dataset

9316

Compounds with BBB classification only

References

74

Total references

Peptide Dataset

906

Peptide compounds with BBB data

Benchmark Dataset

200

Benchmark data for model evaluation

Small Molecule Dataset

Compounds with BBB Penetration Data

Compound IDSMILESBBB StatusLogBB ValueActions
Loading...
Compound IDSMILESBBB StatusLogBB ValueActions
Loading...

Quantitative Dataset

Compounds with LogBB Values

Quantitative Data (With LogBB Values)
Compound IDSMILESBBB StatusLogBB ValueActions
Loading...

Qualitative Dataset

Compounds with BBB Classification Only

Qualitative Data (Classification Only)
Compound IDSMILESBBB StatusLogBB ValueActions
Loading...

Peptide Dataset

Peptide Compounds with BBB Data

Peptide Data
Compound ID SMILES BBB Status LogBB Value Actions
No peptide data available

Benchmark Dataset

Benchmark Data for Model Evaluation

Benchmark Data
Compound ID SMILES BBB Status LogBB Value Actions
No benchmark data available

Downloads

Access Datasets and Models

Dataset Information

Download complete BBBP datasets in JSON format for research and development purposes.

Note: Academic research use only.

Small Molecule Databases

Compounds with BBB penetration data and molecular properties

Quantitative Dataset
Loading...Compounds
JSONFormat
~1.3 MBFile Size
Qualitative Dataset
Loading...Compounds
JSONFormat
~7.3 MBFile Size

Specialized Databases

Peptide compounds and benchmark datasets for model evaluation

Peptide Dataset
Loading...Compounds
JSONFormat
~1.5 MBFile Size
Benchmark Dataset
Loading...Compounds
JSONFormat
~0.1 MBFile Size
CITATION
BBBP Atlas-2025. Blood-Brain Barrier Penetration (BBBP) Database. CADD Research Group, College of Pharmaceutical Sciences, Zhejiang University. Available at: https://cadd.zju.edu.cn/bbbp/ DOI: 10.12345/bbbp_atlas. (Accessed: YYYY-MM-DD).
Proper scholarly use REQUIRES citation of the BBBP Atlas and the CADD Research Group.
@misc{BBBP Atlas-2025, title = {Blood-Brain Barrier Penetration (BBBP) Database}, author = {CADD Research Group}, organization = {College of Pharmaceutical Sciences, Zhejiang University}, howpublished = {\url{https://cadd.zju.edu.cn/bbbp/}}, year = {2025}, doi = {10.12345/bbbp_atlas}, note = {Accessed: YYYY-MM-DD} }
If you use our BBBP modeling methods, please also cite:
  • Shen C, Zhang X, Deng Y, Gao J, Wang D, Xu L, Pan P, Hou T, Kang Y. Boosting Protein–Ligand Binding Pose Prediction and Virtual Screening Based on Residue–Atom Distance Likelihood Potential and Graph Transformer. J Med Chem, 2022, 65(15), 10691-10706. PubMed
  • Xiong G, Wu Z, Yi J, Fu L, Yang Z, Hsieh C, Yin M, Zeng X, Wu C, Lu A, Chen X, Hou T, Cao D. ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties. Nucleic Acids Res, 2021, 49(W1), W5–W14. PubMed cited over 2554 times
  • Su Q, Wang J, Gou Q, Hu R, Jiang L, Zhang H, Wang T, Liu Y, Shen C, Kang Y, Hsieh CY, Hou T. Robust protein–ligand interaction modeling through integrating physical laws and geometric knowledge for absolute binding free energy calculation. Chem Sci, 2025, 16(12), 5043–5057. PubMed
  • Yi J, Shi S, Fu L, Yang Z, Nie P, Lu A, Wu C, Deng Y, Hsieh C, Zeng X, Hou T, Cao D. OptADMET: a web-based tool for substructure modifications to improve ADMET properties of lead compounds. Nat Protoc, 2024, 19(4), 1105–1121. PubMed

Statistics

Data Analysis and Visualization

0

TOTAL COMPOUNDS

0

BBB+ COMPOUNDS

0

BBB- COMPOUNDS

0

WITH LOGBB

BBB Penetration Distribution
Dataset Composition
LogBB Value Distribution
Molecular Weight Distribution
LogP Distribution
Hydrogen Bond Donors
Hydrogen Bond Acceptors
Polar Surface Area vs LogBB
Molecular Weight vs LogP

Help & Documentation

User Guide and Frequently Asked Questions

Overview

This web server provides a curated, reproducible, and user-friendly platform for predicting blood–brain barrier (BBB) permeability of small molecules using GNN models trained on rigorously processed public data. The platform is designed to support computational chemists, medicinal chemists, and researchers in central nervous system (CNS) drug discovery by enabling rapid in silico assessment of BBB penetration potential.

Unlike many existing BBB prediction resources, this server emphasizes data curation transparency, model interpretability, and standardized evaluation protocols, aligning with best practices recommended for nucleic-acid and cheminformatics resources reported in Nucleic Acids Research.

Quick Start
  1. Prepare molecular input as valid SMILES strings.
  2. Select the prediction task.
  3. Submit the job and review the results on the output page.
Input Format
Single Molecule

Input: One valid SMILES string

Batch Prediction
  • File format: CSV
  • Required column: SMILES

Example:

SMILES
CCOc1ccc2nc(S(N)(=O)=O)sc2c1
Note: Invalid or unparsable SMILES strings will be excluded automatically.
Output Interpretation
Classification Output
  • BBB+ Predicted to penetrate the BBB
  • BBB− Predicted not to penetrate the BBB
Regression Output

logBB Logarithmic brain-to-blood concentration ratio

Higher logBB values and probability confidence indicate increased BBB penetration potential.

Model Applicability Domain

The model is optimized for small organic molecules and peptides typically encountered in drug discovery. Predictions for salts, polymers, or metal complexes may be unreliable.

Frequently Asked Questions
Why do similar molecules sometimes yield different predictions?

Small structural changes can significantly alter molecular properties relevant to BBB permeability.

Are predictions deterministic?

Yes. Given identical input, the model will always return the same result.

Contact Us

Get in Touch with Our Research Team

Contact Information

If you have any questions, please contact:

Prof. Tingjun Hou

Email: tingjunhou@zju.edu.cn

Affiliation: College of Pharmaceutical Sciences, Zhejiang University

Address: Hangzhou, Zhejiang 310058, China

Qun Su

Email: qunsu01@gmail.com

Xin Shen

Email: sx050516@gmail.com

Visit our research group website:

CADD Research Group

BBBP Prediction

Predict Blood-Brain Barrier Penetration for Your Compound

Prediction Mode
Single Prediction

Enter one SMILES string

Batch Prediction

Upload CSV file with SMILES

SMILES Input
Enter a valid SMILES notation of your compound
Quick Examples:
Model Information
Training Data

9117 compounds

Accuracy

External Test: 85%

Algorithm

Graph Transformer