Protein secondary structure prediction based on stochastic-rule learning

  • Hiroshi Mamitsuka
  • Kenji Yamanishi
Technical Papers Approximate Learning
Part of the Lecture Notes in Computer Science book series (LNCS, volume 743)


This paper proposes a new strategy for predicting α-helix regions for any given protein sequence, on the basis of the theory of learning stochastic rules. We confine our study to the problem of predicting where α-helix regions are located in a given protein sequence, rather than the conventional three-state prediction problem, i.e., that of predicting to which among the three-states (α-helix, β-sheet, or coil) each of the amino acids in the sequence corresponds.

Our strategy consists of three steps: generation of training examples, learning, and prediction.

In the learning phase, we construct a rule for secondary-structure prediction from training examples. Here a rule is represented not as a deterministic rule but as a stochastic rule, i.e., a probability distribution which assigns, to each region in a sequence, a probability that it corresponds to α-helix. Each stochastic rule used here is further represented as the product of a number of stochastic rules with finite partitioning developed by Yamanishi. Optimal stochastic rules with finite partitioning are obtained from training examples by Laplace estimation of real-valued parameters and by model selection based on the minimum description length (MDL) principle. We allow our stochastic rules to make use of not only the characters themselves of amino acids but also their physico-chemical properties (i.e., numerical attributes, e.g. hydrophobicity, molecular weight, etc).

In the prediction phase, when given a test sequence, the likelihood that any given region (i.e., any subsequence of amino acids) in the test sequence corresponds to α-helix is calculated with the stochastic rules constructed in the learning phase.

We evaluate the predictive performance of our strategy from experimental viewpoints. In generating training examples, examples of α-helix regions are drawn from hemoglobin sequences alone. Experimental results show that the prediction accuracy rate of our prediction strategy was 94.8% for hemoglobin α- chain (1HBSα), 68.5% for parvalbumin β (1CDP), and 73.6% for lysozyme c (1LYM), a significant rate over the rate achieved with the Garnier-Osguthorpe-Robson's (GOR) method.


Protein Data Bank Test Sequence Learning Phase Minimum Description Length Test Region 
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]
    P.Y. Chou and G.D. Fasman. Conformational parameters for amino adds in helical, β-sheet, and random coil regions calculated from proteins. Biochemistry, 13(2):211–221, 1974.PubMedGoogle Scholar
  2. [2]
    P.Y. Chou and G.D. Fasman. Prediction of protein conformation. Biochemistry, 13(2):222–245, 1974.PubMedGoogle Scholar
  3. [3]
    J. Garnier, D.J. Osguthorpe, and B. Robson. Analysis of the accuracy and implication of simple methods for predicting the secondary structure of globular proteins. J.Mol.Biol., 120:97–120, 1978.PubMedGoogle Scholar
  4. [4]
    J.F. Gibrat, J. Garnier, and B. Robson. Further developments of protein secondary structure prediction using information theory. J.Mol.Biol., 198:425–443, 1987.PubMedGoogle Scholar
  5. [5]
    N.Qian and T.J.Sejnowski. Predicting the secondary structure of globular proteins using neural network models. J.Mol.Biol., 202:865–884, 1988.PubMedGoogle Scholar
  6. [6]
    H. Bohr, J. Bohr, S. Brunek, M.J.R. Cotterill, B. Lautrup, L. Norskov, H.O. Olsen, and B.S.Petersen. Protein secondary structure and homology by neural networks. FEBS Letters, 241(1,2):223–228, 1988.PubMedGoogle Scholar
  7. [7]
    R.D. King and M.J.E. Sternberg. Machine learning approach for the prediction of protein secondary structure. J.Mol.Biol., 216:441–457, 1990.PubMedGoogle Scholar
  8. [8]
    K. Yamanishi. A learning criterion for stochastic rules. In Proceedings of the Third Annual Workshop on Computational Learning Theory, pages 67–81. Morgan Kaufmann, 1990. To appear in Machine Learning.Google Scholar
  9. [9]
    J. Rissanen. Modeling by shortest data description. Automatica, 14:465–471, 1978.CrossRefGoogle Scholar
  10. [10]
    J. Rissanen. Stochastic complexity in statistical inquiry, volume 15 of Comp. Sci. 1989. World Scientific.Google Scholar
  11. [11]
    F. Schreiber. The bayes laplace statistics of the multinomial distributions. AEU, 39(5):293–298, 1985.Google Scholar
  12. [12]
    J.L. Fauchere and V. Pliska. Hydrophobic parameters of amino acid side chains from the partitioning of N-acetyl-amino acid amides. Eur.J.Med.Chem.Chim.Ther., 18:369–375, 1983.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Hiroshi Mamitsuka
    • 1
  • Kenji Yamanishi
    • 1
  1. 1.C&C Information Technology Research Labs.NEC CorporationKanagawaJapan

Personalised recommendations