Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

A Comparison Study on SVM MDR and D-MDR for Detecting Gene-Gene Interaction in Continuous Data

연속형자료의 유전자 상호작용 규명을 위한 SVM MDR과 D-MDR의 방법 비교

  • Received : 20110100
  • Accepted : 20110500
  • Published : 2011.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

We have used a multifactor dimensionality reduction(MDR) method to study the major gene interaction effect in general; however, without application of the MDR method in continuous data. In light of this, many methods have been suggested such as Expanded MDR, Dummy MDR and SVM MDR. In this paper, we compare the two methods of SVM MDR and D-MDR. In addition, we identify the gene-gene interaction effect of single nucleotide polymorphisms(SNPs) associated with economic traits in Hanwoo(Korean cattle). Lastly, we discuss a new method in consideration of the advantages that the other methods present.

유전학에서 유전자 상호작용효과 규명을 위한 방법으로 비모수적인 방법인 Multifactor Dimensionality Reduction(MDR) 방법이 제안되어 현재까지 사용되고 있다. MDR 방법은 이분형 자료에 적합한 방법으로 연속형 자료에는 적용할 수 없는 단점이 있다. 이러한 한계를 극복하기 위해서 Dummy MDR(D-MDR) 방법 그리고 SVM을 활용한 MDR(SVM MDR) 방법 등이 제안 되었다. 본 논문에서는 연속형 자료에 적용 가능한 SVM MDR 방법과 D-MDR 방법을 비교하고, 실제 한우 데이터에 두 방법에 적용한다. 그리고 각 방법의 적용결과를 바탕으로 한우의 종합경제형질에 영향을 주는 유전자 상호작용 조합을 규명한다. 그리고 마지막으로 기존의 SVM MDR 방법과 D-MDR 방법의 장단점 비교를 통해서 추후 새로운 연구방향을 제시한다.

Keywords

References

  1. Cho, D. (2010). Mixed-effects LS-SVM for longitudinal data, Journal of Korean Data & Information Science Society, 21, 363-369.
  2. Chung, Y. J., Lee, S. Y. and Park, T. S. (2005). Multifactor dimensionality reduction in the presence of missing observations, 2005 Proceedings of the Autumn Conference, Korea Statistical Society, 31-36.
  3. Good, P. (2000). Permutation Test: A practical guide to resampling method for testing hypotheses, Springer-Verlag Berlin and Heidelberg GmbH & Co., New York.
  4. Lee, H. G. (2009a). Power of multifactor dimensionality reduction with dummy variable and detecting best gene interaction, M.S. Thesis, 1-53.
  5. Lee, J. Y. and Lee, J. H. (2010). Support vector machine and multifactor dimensionality reduction for detecting major gene interactions of continuous data, Journal of Korean Data & Information Science Society, 21, 1271-1280.
  6. Lee, Y. S. (2009b). Study on the identification of candidate genes and their haplotypes that are associated with growth and carcass traits in the QTL region of BTA6 in a Hanwoo population, Ph. D. Thesis, 1-94.
  7. Ritchie, M. D., Hahn, L. W., Roodi, N., Bailey, L. R., Dupont, W. D., Parl, F. F. and Moore, J. H. (2001). Multifactor-dimensionality reduction reveals high-order interactions among estrogen- metabolism genes in sporadic breast cancer, American Journal of Human Genetics, 69, 138-147. https://doi.org/10.1086/321276
  8. Scholkopf, B. and Smola, A. J. (2001). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press.
  9. Shim, J., Park, H. and Seok, K. H. (2009). Variance function estimation with LS-SVM for replicated data, Journal of Korean Data & Information Science Society, 20, 925-931
  10. Snelling, W. M., Casas, E., Stone, R. T., Keele, J. W., Harhay, G. P., Benett, G. L. and Smith, T. P. L. (2005). Linkage mapping bovine EST-based SNP, BioMed Central Genomics, 6, 74-84.
  11. Vapnik, V. (1998). Statistical Learning Theory, John Wiley & Sons, New York.
  12. Tan, P., Steinbach, M. and Kumar, V. (2006). Introduction to Data Mining, Addison-Wesley, New-York.