fu,p Predictor

Welcome to the fu,p predictor, a program for the prediction of fu,p (Fraction unbound in plasma).

How to use

Upload molecule(s) as an SDF/MOL file and click the “Proceed” button.

  • In preparing the input file, use Open Babel1 (http://openbabel.org/wiki/Main_Page) to generate 2D coordinates.
  • You can include up to 30 compounds in the input file. It takes about 20-30 seconds to complete the calculations for 10 compounds.
  • The user uploaded lists and calculations are retained while the web browser session is active. All the data are deleted on exiting the browser.

The model information

R2 = 0.691
Name Output Dataset R2 or Accuracy Method Descriptors
3-class classification model
  • Low (0.001-0.05)
  • Middle (0.05-0.2)
  • High (0.2-1.0)
Watanabe et al, 2018, Mol. Pharm.
  • Accuracy:0.676
  • True positive rate in low class:0.826
  • Mordred2
  • PaDEL33
Regression model Numerical fu,p value Watanabe et al, 2018, Mol. Pharm. RF
  • Mordred2
  • PaDEL33

For details please refer to Watanabe et al, 2018, Mol. Pharm. (Link of paper)


  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. Moriwaki, H.; Tian, Y. S.; Kawashita, N.; Takagi, T., Mordred: a molecular descriptor calculator. J Cheminform 2018, 10 (1), 4.
  3. Yap, C. W., PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem 2011, 32 (7), 1466-74.