Artificial intelligence

Abstract: The article considers the gene ranking algorithm for the microarray data. The rank vector is estimated by classifications of the random data samples. At each iteration the ranks of genes participating in the successful classification become higher. Unlike other methods of feature selection the proposed algorithm allows to increase the generality of the classification models by the construction of the balanced training samples and to take into account the descriptiveness of the gene combinations by the subsets estimation.

Keywords: feature ranking, biomarker, classification, gene expression

References:

1. Liu X. An entropy-based gene selection method for cancer classification using microarray data / X. Liu,
2. A. Krishnan, A. Mondry // BMC Bioinformatics. – 2005. – Vol. 6, No 76.
3. Novoselov NA Methods for analysis of gene expression data. Overview and prospects for development
4. (Novoselova, NA Methods for gene expression analysis. Survey and perspective directions) / N. Novoselov,
5. IE Tom. - LAMBERT Academic Publishing GmbH & Co. - 2012. - 68 p. - ISBN 978-3-659-16145-2.
6. Dougherty E.R. Performance of feature selection methods / E.R. Dougherty, J. Hua, C. Sima // Curr
7. Genomics. – 2009. – Vol. 10. – P. 365-374.
8. Wang Y. Gene selection from microarray data for cancer classification a machine learning approach /
9. Y. Wang, I.V. Tetko, M.A. Hall // Comp Biol Chem. – 2005. – Vol. 29. – P. 37-46.
10. Kohavi R. Wrapper for feature subset selection / R. Kohavi, G. John // Artificial Intelligence. – 1997. –
11. Vol. 97, No 1-2. – P. 273-324.
12. An efficient and robust statistical modeling approach to discover differentially expressed genes using
13. genomic expression profiles / [Thomas J.G., Olson J.M., Tapscott S.J., Zhao L.P.] // Genome
14. Res. -2001. – Vol. 11. – P. 1227-1236.
15. Antoniadis A. Effective dimension reduction methods for tumor classification using gene expression
16. data / A. Antoniadis, S. Lambert-Lacroix, F. Leblanc // Bioinformatics. – 2003. – Vol. 19. – P. 563-570.
17. Filter versus wrapper gene selection approaches in DNA microarray domains / [Inza I., Larranaga P.,
18. Blanco R., Cerrolaza, A.] // Artif. Intell. Med. – 2004. – Vol. 31, No 2. – P. 91-103.
19. Xiong M. Biomarker identification by feature wrappers / M. Xiong, Z. Fang, J. Zhao // Genome
20. Research. -2001. – Vol. 11. – P. 1878-1887.
21. Saeys Y. A review of feature selection techniques in bioinformatics / Y. Saeys, I. Inza, P. Larranaga //
22. Bioinformatics. – 2007. – Vol. 23. – P. 2507-2517.
23. Diagnosis of multiple cancer types by shrunken centroids of gene expression / [Tibshirani R., Hastie T.,
24. Narasimhan B., Chu G.] // Proc Natl Acad Sci U S A. – 2002. – Vol. 99. – P. 6567-6572.
25. Molecular classification of Cancer:class discovery and class prediction by gene expression monitoring /
26. [Golub T.R., Slonim D.K., Tamayo P. et al.] // Nature. – 1999. – Vol. 286. – P. 531-537.
27. Dudoit S. Comparison of discrimination methods for the classification of tumors using gene expression
28. data / S. Dudoit, J. Fridlyand, T. Speed // J Am Stat Assoc. - 2002. – Vol. 97. – P. 77-87.
29. Whitehead Institute Center for Genomic Research: cancer genomics [Электронный ресурс]. – Режим
30. доступа : http://www-genome.wi.mit.edu/cancer
31. Optimization Based Tumor Classification from Microarray Gene Expression Data / [Dagliyan O., Uney-
32. Yuksektepe F., Kavakli I.H., Turkay M.] ; [Электронный ресурс] // PLoS ONE. – 2011. – No 6(2). –
33. Режим доступа : e14579. doi:10.1371/journal.pone.0014579.
34. Optimization models for cancer classification extracting gene interaction information from microarray
35. expression data / [Antonov A., Tetko I.V., Mader M.T. et al.] // Bioinformatics. – 2004. – Vol. 20. –
36. P. 644-652.
37. Dettling M. Supervised clustering of genes / M. Dettling, P. Buhlmann [Электронный ресурс] //
38. Genome Biol. – 2002. – Vol. 3. – Режим доступа : research0069.1–0069.15.
39. Biomarker discovery in microarray gene expression data with gaussian processes / [Chu W., Ghahramani
40. Z., Falciani F., Wild D.L.] // Bioinformatics. – 2005. – Vol. 21. – P. 3385-3393.
41. Yang A.J. Bayesian variable selection for disease classification using gene expression data / A.J. Yang,
42. X.Y. Song // Bioinformatics. – 2010. – Vol. 26. – P. 215-222.
43. Gene selection from microarray data for cancer classification – a machine learning approach / [Y. Wang
44. et al.] // Comput. Biol. Chem. – 2005. – Vol. 29, No 1. – P. 37-46.