Prediction of Photosensitizers Activity in Photodynamic Therapy Using Artificial Neural Networks: A 3D—QSAR Study

  • Rozália Vanyúr
  • Károly Héberger
  • István Kövesdi
  • Judit Jakus
Conference paper
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)


Biological activity in photodynamic therapy was predicted from the molecular structure of pyropheophorbide derivatives using artificial neural networks (ANN). First, the structure of molecules was optimized and various descriptors were calculated. ANN architecture was optimized while suitable descriptors were selected applying a novel variable selection method.

The reliability of models was tested by cross-validation and randomization of biological activity data. Models are able to predict biological activity from the molecular structure of the phorbide derivatives with a leave-one-out crossvalidation Q2 of 0.956. The size of the substituents is decisive in the third direction (perpendicular to the main plain of the molecules).


Artificial Neural Network Photodynamic Therapy Variable Selection Method Artificial Neural Network Architecture Photosensitizer Activity 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    HyperChem version 4.0, HyperCube Inc., Canada, 1997.Google Scholar
  2. [2]
    IsisBase 1.2 for desktop, Molecular Design Limited, 1996.Google Scholar
  3. [3]
    Héberger K., Borosy A. Comparison of Chemometric Methods for Prediction of Rate Constants and Activation Energies of Radical addition reactions. J. Chemometrics 1999; 13:473–489.CrossRefGoogle Scholar
  4. [4]
    3DNET version 1.0, CompElit Ltd., Hungary, 1998.Google Scholar
  5. [5]
    Todeschini R., Gramatica P. New 3D Molecular Descriptors: The WHIM theory and QSAR Applications Perspectives in Drug Discovery and Design, 1998; 9/10/11:355–380.Google Scholar
  6. [6]
    Kier LB. Sharpe Indices of Other of One and Three from Molecule Graf. Quant. Struct.-Act. Relat, 1986; 5:1–7.Google Scholar
  7. [7]
    Broto P., Moreau G., Vandycke C, Molecular-structures — Perception, auto-correlation descriptor and SAR studies — System of atomic contributions for the calculation of the normal-octanol water partition-coefficients. Eur. J. Med. Chem. 1984; 19:71–78.Google Scholar
  8. [8]
    Masters T., Practical neural network recipes in C++. Academic Press, Inc., 1996.Google Scholar
  9. [9]
    Henderson BW., Bellnier DA., Greco WR., Sharma A., Pandey RK., Vanghan LA., Weishaupt KR. and Dougherty TJ. An in vivo quantitative structure-activity relationship for a congeneric series of pyropheophorbide derivatives as photosensitizers for photodynamic therapy. Cancer Res. 1997; 57:4000–4007.Google Scholar

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • Rozália Vanyúr
    • 1
  • Károly Héberger
    • 1
  • István Kövesdi
    • 2
  • Judit Jakus
    • 1
  1. 1.Institute of Chemistry, Chemical Research CenterHungarian Academy of SciencesBudapestHungary
  2. 2.EGIS Pharmaceutical Company Ltd.BudapestHungary

Personalised recommendations