Automatic Identification of Metastable Conformations via Self-Organized Neural Networks

  • T. Galliat
  • P. Deuflhard
  • R. Roitzsch
  • F. Cordes
Part of the Lecture Notes in Computational Science and Engineering book series (LNCSE, volume 24)


As has been shown recently, the identification of metastable chemical conformations leads to a Perron cluster eigenvalue problem for a reversible Markov operator. Naive discretization of this operator would suffer from combinatorial explosion. As a first remedy, a pre-identification of essential degrees of freedom out of the set of torsion angles had been applied up to now. The present paper suggests a different approach based on neural networks: its idea is to discretize the Markov operator via self-organizing box maps. The thus obtained box decomposition then serves as a prerequisite for the subsequent Perron cluster analysis. Moreover, this approach also permits exploitation of additional structure within embedded simulations. As it turns out, the new method is fully automatic and efficient also in the treatment of biomolecules. This is exemplified by numerical results.


Biochemical conformations cluster analysis molecular dynamics Hybrid Monte-Carlo methods Markov operator Perron cluster analysis Self-Organizing Maps 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan. Automatic subspace clustering of high dimensional data for data mining applications. In Proc. ACM SIGMOD Int. Conf. on Management of Data, pages 94–105, 1998.Google Scholar
  2. 2.
    A. Amadei, A.B.M. Linssen, and H.J.C. Berendsen. Essential dynamics of proteins. Proteins, 17, 1993.Google Scholar
  3. 3.
    P. Deuflhard, M. Dellnitz, O. Junge, and Ch. Schütte. Computation of essential molecular dynamics by subdivision techniques. In [4], pages 98–115.Google Scholar
  4. 4.
    P. Deuflhard, J. Hermans, B. Leimkuhler, A.E. Mark, S. Reich, and R.D. Skeel, editors, Computational Molecular Dynamics: Challenges, Methods, Ideas. Lecture Notes in Computational Science and Engineering, volume 4. Springer, 1998.Google Scholar
  5. 5.
    P. Deuflhard, W. Huisinga, A. Fischer, and Ch. Schütte. Identification of almost invariant aggregates in nearly uncoupled Markov chains. Linear Algebra and its Applications 315, pages 39–59, 2000.CrossRefGoogle Scholar
  6. 6.
    B.S. Duran and P.L. Odell. Cluster Analysis. Springer, Berlin, 1974.Google Scholar
  7. 7.
    U.M. Fayyad, G. Patetsky-Shapiro, P. Smyth, and R. Uthurusamy (Eds.). Advances in Knowledge Discovery and Data Mining. AAAI Press/The MIT Press, California, 1996.Google Scholar
  8. 8.
    A. Fischer. An uncoupling-coupling technique for Markov Chain Monte Carlo methods. Preprint SC-00-04, Konrad-Zuse Zentrum, Berlin. Available via Scholar
  9. 9.
    A. Fischer, F. Cordes, and Ch. Schütte. Hybrid Monte Carlo with adaptive temperature in mixed-canonical ensemble: Efficient conformational analysis of RNA. J. Comp. Chem., 19(15):1689–1697, 1998.CrossRefGoogle Scholar
  10. 10.
    A. Fischer, Ch. Schütte, P. Deuflhard, and F. Cordes. Hierarchical uncoupling-coupling of metastable conformations. ZIB Report 01-03, Konrad-Zuse-Zentrum, Berlin. Available via Scholar
  11. 11.
    N.I. Fisher. Statistical Analysis of Circular Data. University Press, Cambridge, 1993.CrossRefGoogle Scholar
  12. 12.
    T. Galliat and P. Deuflhard. Adaptive hierarchical cluster analysis by self-organizing box maps. ZIB-Report 00-13 (April 2000), Konrad-Zuse-Zentrum, Berlin. Available via, 2000.Google Scholar
  13. 13.
    T. Galliat, W. Huisinga, and P. Deuflhard. Self-organizing maps combined with eigenmode analysis for automated cluster identification. In H. Bothe and R. Rojas, editors, Proceedings of the 2nd International ICSC Symposium on Neural Computation, pages 227–232. ICSC Academic Press, 2000.Google Scholar
  14. 14.
    A. Gelman and D.B. Rubin. Inference from iterative simulation using multiple sequences. Statistical Science, 7:457–511, 1992.Google Scholar
  15. 15.
    A. Gersho and R.M. Gray. Vector Quantization and Signal Compression. Kluwer Academic Publishers, 1992.Google Scholar
  16. 16.
    T.A. Halgren. Merck molecular force field. i–v. J. Comp. Chem., 17(5&6):490–641, 1996.CrossRefGoogle Scholar
  17. 17.
    M. Van Hulle. Faithful Representations and Topographic Maps. John Wiley Sons, Inc., 2000.Google Scholar
  18. 18.
    T. Kohonen. Comparison of SOM point densities based on different criteria. Neural Computation, (ll):2081–2095, 1999.PubMedCrossRefGoogle Scholar
  19. 19.
    T. Kohonen. Self-Organizing Maps. Springer, Berlin, 3rd edition, 2001.CrossRefGoogle Scholar
  20. 20.
    B.D. Ripley. Pattern Recognition and Neural Networks. Cambridge University Press, 1996.Google Scholar
  21. 21.
    Ch. Schütte. Conformational Dynamics: Modelling, Theory, Algorithm, and Application to Biomolecules. Habilitation Thesis, Dept. of Mathematics and Computer Science, Free University of Berlin, 1998. Available as ZIB-Report SC-99-18 via Scholar
  22. 22.
    Ch. Schütte, A. Fischer, W. Huisinga, and P. Deuflhard. A direct approach to conformational dynamics based on hybrid Monte Carlo. J. Comput. Phys., Special Issue on Computational Biophysics, 151:146–168, 1999.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • T. Galliat
    • 1
  • P. Deuflhard
    • 1
    • 2
  • R. Roitzsch
    • 1
  • F. Cordes
    • 1
  1. 1.Konrad-Zuse-Zentrum für Informationstechnik BerlinBerlinGermany
  2. 2.Fachbereich Mathematik und InformatikFreie Universität BerlinBerlinGermany

Personalised recommendations