|
Table 2.
Performance of the proposed classiiers
RDA
SVM
SvM-RDA
55,6%
58,7%
61,8%
The results achieved using the proposed strategies are prom-
ising. The recognition rates obtained using these algorithms
(55,6%-61,8%) are comparable to those described in literature
(48.8%-61.2%).
Table 3.
Comparison between different methods
Method
Recognition ratio
SVM [5]
56,0%
HKNN [14]
57,4%
DIMLP-B [15]
61,2%
RS1_HKNN_K25 [13]
60,3%
RBFN [16]
51,2%
MLP [17]
48,8%
SvM-RDA (this paper)
61,8%
The obtained results are very encouraging. Our results im
-
proved the recognition ratio achieved by other methods proposed
in literature, however, some extra experiments are needed,
especially to consider other approaches to the multi-class SvM.
References
1. Baldi P., Brunak S., Chauvin Y., Andersen C., Nielsen H.
(2000): Assessing the accuracy of prediction algorithms for
classiication: an overview. Bioinformatics 16, pp. 412-424.
2. Prevost L., Qudot L., Moises A., Michel-Sendis Ch., Mil
-
gram M. (2005): Hybrid generative/disciminative classiier
for unconstrained character recognition. Pattern Recogni
-
tion Letters 26, pp. 1840-1848.
3. Chang. C.C., Lin C.J. (2001): LIBSvM: a library for support
vector machines. Software available at: http://www.csie.
ntu.edu.tw/~cjlin/libsvm
4. Chothia C. (1992): One thousand families for the molecular
biologist. Nature 357, pp. 543-544.
5. Ding C.H., Dubchak I. (2001): Multi-class protein fold rec
-
ognition using support vector machines and neural net-
works. Bioinformatics 17, pp. 349-358.
6. Dubchak I., Muchnik I. Holbrook S.R., Kim S.H. (1995):
Prediction of protein folding class using global description
of amino acid sequence. Proc. Natl. Acad. Sci. USA 92,
pp. 8700-8704.
7. Dubchak I., Muchnik I., Kim S.H. (1997): Protein folding
class predictor for SCOP: approach based on global de-
scriptors. Proceedings ISMB.
8. Lo Conte L., Ailey B., Hubbard T.J.P., Brenner S.E., Murzin
A.G., Chothia C. (2000): SCOP: a structural classiica
-
tion of protein database. Nucleic Acids Res. 28, pp. 257-
-259.
9. Shen H.B., Chou K.C. (2006): Ensemble classiier for pro
-
tein fold pattern recognition. Bioinformatics 22, pp. 1717-
-1722.
10. vapnik v. (1995): The Nature of Statistical Learning Theory.
Springer, New York.
11. vural v., Dy J.G. (2004): A hierarchical method for multi-
-class support vector machines, Proceedings of the twenty-
-irst ICML, July 04-08, 2004, Banff, Alberta, Canada,
p. 105.
12. Wang L., Shen X. (2006): Multi-category support vector
machines, feature selection and solution path. Statistica
Sinica 16, pp. 617-633.
13. Nanni L. (2006): A novel ensemble of classiiers for protein
fold recognition. Neurocomputing 69, pp. 2434-2437.
14. Okun O. (2004): Protein fold recognition with k-local hyper
-
plane distance nearest neighbor algorithm. In: Proceedings
of the Second European Workshop on Data Mining and
Text Mining in Bioinformatics, 24 September, Pisa, Italy,
pp. 51-57.
15. Bologna G., Appel R.D. (2002): A comparison study on pro
-
tein fold recognition. In: Proceedings of the ninth ICONIP,
Singapore, 18-22 November, vol. 5, pp. 2492-2496.
16. Pal N.R., Chakraborty D. (2003): Some new features for
protein fold recognition. In: Artiicial Neural Networks and
Neural Information Processing ICANN/ICONIP vol. 2714,
Turkey, Istanbul, June 26-29, pp. 1176-1183.
17. Chung I.F., Huang C.-D., Shen Y.-H., Lin C.-T. (2003): Re-
cognition of structure classiication of protein folding by
NN and SvM hierarchical learning architecture. In: Artii
-
cial Neural Networks and Neural Information Processing–
–ICANN/ICONIP, 26-29 June, Istanbul, Turkey, pp. 1159-
-1167.
18. Hobohm U., Sander C. (1994): Enlarged representative set
of Proteins. Protein Sci. 3, pp. 522-524.
19. Hobohm U., Scharf, M.. Schneider R., Sander C. (1992):
Selection of a representative set of structures from the
Brookhaven Protein Bank. Protein Sci. 1, pp. 409-417.
20. Stąpor K. (2005): Automatic classiication of objects (in Po-
lish). Academic Publishing House Exit, Warsaw.
21. Quinn G.P., Keough M.J. (2002): Experimental design and
data analysis for biologists. Cambridge University Press.
22. Rychlewski L., Bujnicki, J. Fischer D. (2003): Protein Fold-
Recognition and Experimental Structure Determination. In:
J. Seckbach, E. Rubin (eds.): The New Avenues in Bioin
-
formatics.
Bioinf
or
ma
tics
BIO-ALGORITHMS AND MED-SYSTEMS
JOURNAL EDITED BY JAGIELLONIAN UNIVERSITY – MEDICAL COLLEGE
Vol. 7, No. 13, 2011, pp. 71-76
Do'stlaringiz bilan baham: |
