Skip to main content
Log in

Prediction of contact numbers of amino acid residues using a neural network regression algorithm

  • Published:
Biophysics Aims and scope Submit manuscript

Abstract

The profile of contact numbers of amino acid residues in proteins contains important information about the protein structure and is connected with the accessibility of residues to solvent. Here we propose a method for predicting the profile of contact numbers of residues in protein from its amino acid sequence. The method is based on regression using a neural network algorithm. The algorithm predicts two types of profiles, namely, the total number of contacts and the number of close contacts with the neighbors in the chain. The Pearson coefficient of correlation between the actual and predicted values of total contact numbers amounted to 0.526–0.703. As for the number of close contacts, this coefficient was higher (0.662–0.743) for all the considered threshold contact distances (6, 8, 10, and 12 Å). The program for prediction of contact numbers CONNP is available at http://wwwmgs2.bionet.nsc.ru/reloaded.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. K. Nishikawa and O. Ooi, Int. J. Pept. Protein. Res. 16(1), 19 (1980).

    Google Scholar 

  2. M. A. Rodionov, S. G. Galaktionov, and A. A. Akhrem, Dokl. Akad. Nauk SSSR 261(2), 756 (1981).

    Google Scholar 

  3. A. Rost and C. Sander, Proteins 20(3), 216 (1994).

    Article  Google Scholar 

  4. K. Nishikawa and Y. Matsuo, Protein Eng. 6(8), 811 (1993).

    Article  Google Scholar 

  5. P. Fariselli, O. Olmea, A. Valencia, and R. Casadio, Proteins 45(5), 157 (2001).

    Article  Google Scholar 

  6. P. Fariselli and R. Casadio, Proceedings of the International Conference of Intelligence Systems in Molecular Biology, 8, 146 (2000).

    Google Scholar 

  7. G. Pollastri, P. Baldi, P. Fariselli, and R. Casadio, Proteins 47(2), 142 (2002).

    Article  Google Scholar 

  8. A. R. Kinjo, K. Horimoto, and K. Nishikawa, Proteins 58(1), 158 (2005).

    Article  Google Scholar 

  9. Z. Yuan, BMC Bioinformatics 6, 248 (2005).

    Article  Google Scholar 

  10. A. R. Kinjo and K. Nishikawa, BMC Bioinformatics 7, 401 (2006).

    Article  Google Scholar 

  11. S. Ahmad, M. M. Gromiha, and A. Sarai, Proteins 50(4), 629 (2003).

    Article  Google Scholar 

  12. D. O. Jones, J. Mol. Biol. 292(2), 195 (1999).

    Article  Google Scholar 

  13. H. M. Berman, J. Westbrook, Z. Feng, et al., Nucleic Acids Res. 28(1), 235 (2000).

    Article  Google Scholar 

  14. A. Andreeva, D. Howorth, S. E. Brenner, et al., Nucleic Acids Res. 32 (Database issue), D226 (2204).

    Article  Google Scholar 

  15. S. K. Riis and A. Krogh, J. Comput. Biol. 3, 163 (1996).

    Article  Google Scholar 

  16. P. Baldi and S. Brunak, Bioinformatics: The Machine Learning Approach, 2nd edition (MIT, Cambridge, MA, 2001).

    MATH  Google Scholar 

  17. S. F. Altschul, T. L. Madden, A. A. Schaffer, et al., Nucleic Acids Res. 25(17), 3389 (1997).

    Article  Google Scholar 

  18. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, in Parallel Distributed Processing, Ed. by D. E. Rumelhart and J. L. McClelland (MIT, Cambridge, MA, 1986), Vol. 1, pp. 318–362.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to D. A. Afonnikov.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Afonnikov, D.A., Morozov, A.V. & Kolchanov, N.A. Prediction of contact numbers of amino acid residues using a neural network regression algorithm. BIOPHYSICS 51 (Suppl 1), 56–60 (2006). https://doi.org/10.1134/S0006350906070128

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0006350906070128

Key words

Navigation