Abstract
Modifications for improving the prediction quality in a previously described adaptive algorithm of automated annotation (A 4) were considered. First, the direct use of the basis statistic η ensures a higher prediction quality than the use of a previously proposed statistic γ. Second, the quality is improved when only some of the found similar sequences, rather than all of them, are used for prediction, since this reduces the data noise.
Similar content being viewed by others
References
A. M. Leontovich, L. I. Brodsky, V. A. Drachev, and V. K. Nikolaev, Bioinformatics 18(6), 838 (2002).
M. A. Andrade, N. P. Brown, C. Leroy, et al., Bioinformatics 15, 391 (1999).
W. Fleischmann, S. Moller, A. Gateau, and R. Apweiler, Bioinformatics 15(3), 228 (1999).
E. Kretschmann, W. Fleischmann, and R. Apweiler, Bioinformatics 17(10), 920 (2001).
C. A. Wilson, J. Kreychman, and M. Gerstein, J. Mol. Biol. 297, 233 (2000).
H. Hegyi and M. Gerstein, Genome Res. 11(10), 1632 (2001).
S. F. Altschul, D. J. Gish, W. Miller, et al., J. Mol. Biol. 215, 403 (1990).
S. F. Altschul and B. W. Ericson, Bull. Math. Biol. 48, 603 (1986).
A. M. Leontovich, L. I. Brodskii, and A. E. Gorbalene, Biopolim. Kletka 6(6), 14 (1990).
R. Durbin, S. Eddy, A. Krogh, and G. Mitchison, Biological Sequence Analysis. Probabilistic Models of Proteins and Nuclear Acids (Cambridge University Press, 1998).
R. E. Barlow, J. M. Bartholomew, J. M. Bremner, and H. D. Brunk, Statistical Inference Under Order Restrictions (John Wiley & Sons, New York, 1972).
P. Bork and A. Bairoch, Trends Gen. 12(10), (1996).
Author information
Authors and Affiliations
Additional information
Original Russian Text © A.M. Leontovich, K.Yu. Tokmachev, 2006, published in Biofizika, 2006, Vol. 51, No. 4, pp. 593–601.
Rights and permissions
About this article
Cite this article
Leontovich, A.M., Tokmachev, K.Y. Ways to improve the prediction quality in the adaptive algorithm of automated annotation (A 4). BIOPHYSICS 51, 527–534 (2006). https://doi.org/10.1134/S0006350906040038
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1134/S0006350906040038