Computer Assisted Peptide Design and Optimization with Topology Preserving Neural Networks

  • Jörg D. Wichard
  • Sebastian Bandholtz
  • Carsten Grötzinger
  • Ronald Kühne
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6114)


We propose a non-standard neural network called TPNN which offers the direct mapping from a peptide sequence to a property of interest in order to model the quantitative structure activity relation. The peptide sequence serves as a template for the network topology. The building blocks of the network are single cells which correspond one-to-one to the amino acids of the peptide. The network training is based on gradient descent techniques, which rely on the efficient calculation of the gradient by back-propagation. The TPNN together with a GA-based exploration of the combinatorial peptide space is a new method for peptide design and optimization. We demonstrate the feasibility of this method in the drug discovery process.


Training Sample Training Error Cellular Neural Network Quantitative Structure Activity Relation Metabolic Stability 
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.
    Ogorzałek, M., Merkwirth, C., Wichard, J.: Pattern recognition using finite-iteration cellular systems. In: Proceedings of the 9th International Workshop on Cellular Neural Networks and Their Applications, pp. 57–60 (2005)Google Scholar
  2. 2.
    Merkwirth, C., Lengauer, T.: Automatic generation of complementary descriptors with molecular graph networks. Journal of Chemical Information and Modeling 45(5), 1159–1168 (2005)CrossRefGoogle Scholar
  3. 3.
    Merkwirth, C., Ogorzałek, M.: Applying CNN to cheminformatics. In: Proceedings of the ISCAS, pp. 2918–2921 (2007)Google Scholar
  4. 4.
    Goulon, A., Picot, T., Duprat, A., Dreyfus, G.: Predicting activities without computing descriptors: Graph machines for QSAR. SAR and QSAR in Environmental Research 18, 141–153 (2007)CrossRefGoogle Scholar
  5. 5.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  6. 6.
    Hansen, L., Salamon, P.: Neural network ensembles. IEEE Trans. on Pattern Analysis and Machine Intelligence 12(10), 993–1001 (1990)CrossRefGoogle Scholar
  7. 7.
    Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias/variance dilemma. Neural Computation 4, 1–58 (1992)CrossRefGoogle Scholar
  8. 8.
    Perrone, M.P., Cooper, L.N.: When networks disagree: Ensemble methods for hybrid neural networks. In: Mammone, R.J. (ed.) Neural Networks for Speech and Image Processing, pp. 126–142. Chapman-Hall, Boca Raton (1993)Google Scholar
  9. 9.
    Holland, J.H.: Adaptation in natural and artificial systems. MIT Press, Cambridge (1975)Google Scholar
  10. 10.
    Goldberg, D.: Genetic Algorithms in Search, Optimization and Machine Learning. Kluwer Academic Publishers, Boston (1989)zbMATHGoogle Scholar
  11. 11.
    Fredriksson, R., Lagerström, M., Lundin, L., Schiöth, H.: The G-protein-coupled receptors in the human genome form five main families. Phylogenetic analysis, paralogon groups, and fingerprints. Mol. Pharmacol. 63, 1256–1272 (2003)Google Scholar
  12. 12.
    Hopkins, A., Groom, C.: The druggable genome. Nature Reviews Drug Discovery 1(9), 727–730 (2002)CrossRefGoogle Scholar
  13. 13.
    Filmore, D.: It’s a GPCR world. Modern Drug Discovery 7(11), 24–28 (2004)Google Scholar
  14. 14.
    Palczewski, K., Kumasaka, T., Hori, T., Behnke, C.A., Motoshima, H., Fox, B., Trong, I.L., Teller, D., Okada, T., Stenkamp, R., Yamamoto, M., Miyano, M.: Crystal structure of rhodopsin: A G protein-coupled receptor. Science 289(5480), 739–745 (2000)CrossRefGoogle Scholar
  15. 15.
    Teller, D., Okada, T., Behnke, C., Palczewski, K., Stenkamp, R.: Advances in determination of a high-resolution three-dimensional structure of rhodopsin, a model of G-protein-coupled receptors. Biochemistry 40, 7761–7772 (2001)CrossRefGoogle Scholar
  16. 16.
    Rasmussen, S., Choi, H., Rosenbaum, D., Kobilka, T., Thian, F., Edwards, P., Burghammer, M., Ratnala, V., Sanishvili, R., Fischetti, R., Schertler, G., Weis, W., Kobilka, B.: Crystal structure of the human β-2 adrenergic G-protein-coupled receptor. Nature 450, 383–387 (2007)CrossRefGoogle Scholar
  17. 17.
    Jaakola, V., Griffith, M., Hanson, M., Cherezov, V., Chien, E., Lane, J., IJzerman, A., Stevens, R.: The 2.6 Angstrom Crystal Structure of a Human A2A Adenosine Receptor Bound to an Antagonist. Science 322(5905), 1211–1217 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jörg D. Wichard
    • 1
  • Sebastian Bandholtz
    • 2
  • Carsten Grötzinger
    • 2
  • Ronald Kühne
    • 1
  1. 1.FMP BerlinBerlinGermany
  2. 2.Charité, Department of Hepatology and GastroenterologyBerlinGermany

Personalised recommendations