Brain Penetration Predictor

Welcome to the Brain Penetration Predictor, a program for the prediction of pharmacokinetic parameters which are involved in the brain penetration, Kp,brain (brain-to-plasma concentration ratio) and Kp,uu,brain (unbound brain-to-plasma concentration ratio). We correct calculated Kp,brain using the predicted representative values of P-gp net efflux ratio (NER) in BCEC, Kp,uu,brain is calculated using predicted fu,p (fraction unbound in plasma) and fu,brain (fraction unbound in brain homogenate) from corrected Kp,brain .

How to use

  1. Select a molecule as a MOL file
    • You can upload only single MOL file, for the single molecule.
    • In preparing the input file, use Open Babel1 (http://openbabel.org/wiki/Main_Page) with "Make dative bonds" and "Generate 2D coordinates" checked.
  2. Enter acidic and basic pKa
    • Leave the input field blank if pKa does not exist.
    • To calculate pKa for the single molecule, use Marvin Sketch2 (ChemAxon). Select MarvinSketch menu: Tools > Protonation > pKa. Details of the pKa Plugin is shown in https://docs.chemaxon.com/display/docs/pKa+Plugin
  3. Enter LogP
    • Optional. LogP is calculated by RDKit3 if the input field is blank.
  4. Click the "Proceed" button

The model information

Model Type Output Dataset Accuracy Method Descriptor
P-gp NER_human 3 class
  • Low (1-1.4)
  • Middle (1.4-9.8)
  • High (> 9.8)
Watanabe et al. 4 Kappa: 0.45 GB5
  • Mordred 6
  • jCompoundMapper 7
fu,p rat Regression fu,p value Watanabe et al. 4
  • MSE: 1.70
  • R2: 0.51
GB5
  • Mordred 6
  • jCompoundMapper 7
fu,brain mammal Regression fu,brain value Watanabe et al. 4
  • MSE: 1.48
  • R2: 0.58
GB5
  • Mordred 6
  • jCompoundMapper 7
Parameter Output Dataset Accuracy Method Details
Kp,brain rat Kp,brain value Watanabe et al 4 MSE:1.21 Corrected Kp,brain using the representative value of P-gp NER based on predicted class by P-gp NER prediction model Watanabe et al. 4
Kp,uu,brain rat Kp,uu,brain value Watanabe et al 4 MSE:1.55 Kp,uu,brain is calculated from corrected Kp,brain using predicted fu,p and fu,brain Watanabe et al. 4

References

  1. O'Boyle, N. M.; Banck, M.; James, C. A.; Morley, C.; Vandermeersch, T.; Hutchison, G. R. Open Babel: An open chemical toolbox. J. Cheminform. 2011; 3:33.
  2. https://chemaxon.com/products/marvin
  3. https://www.rdkit.org/docs/index.html
  4. Watanabe,R.; Esaki, T.; Ohashi, R.; Kuroda, M.; Kawashima, H.; Komura,H.; Natsume-Kitatani, Y.; Mizuguchi, K. Development of an in silico prediction model for P?glycoprotein efflux potential in brain capillary endothelial cells toward the prediction of brain penetration. J. Med. Chem. 2021; 64(5):2725-2738.
  5. Friedman, H. J. Greedy function approximation: A gradient boosting machine. IMS 1999 Reitz Lecture, 1999 Machine Learn. 2001; 45(1):5-32.
  6. Moriwaki, H.; Tian, Y. S.; Kawashita, N.; Takagi, T. Mordred: a molecular descriptor calculator. J. Cheminform. 2018; 10(1):4.
  7. Hinselmann, G.; Rosenbaum, L.; Jahn, A.; Fechner, N.; Zell, A. jCompoundMapper: An open source Java library and command-line tool for chemical fingerprints. J. Cheminform. 2011; 3:3.