The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Two-Stage Logistic Regression for Cancer Classi cation and Prediction from Copy-Numbe Changes in cDNA Microarray-Based Comparative Genomic Hybridization

  • Kim, Mi-Jung (Institute for Mathematical Sciences, Yonsei University)
  • Received : 20110600
  • Accepted : 20110800
  • Published : 2011.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

cDNA microarray-based comparative genomic hybridization(CGH) data includes low-intensity spots and thus a statistical strategy is needed to detect subtle differences between different cancer classes. In this study, genes displaying a high frequency of alteration in one of the different classes were selected among the pre-selected genes that show relatively large variations between genes compared to total variations. Utilizing copy-number changes of the selected genes, this study suggests a statistical approach to predict patients' classes with increased performance by pre-classifying patients with similar genetic alteration scores. Two-stage logistic regression model(TLRM) was suggested to pre-classify homogeneous patients and predict patients' classes for cancer prediction; a decision tree(DT) was combined with logistic regression on the set of informative genes. TLRM was constructed in cDNA microarray-based CGH data from the Cancer Metastasis Research Center(CMRC) at Yonsei University; it predicted the patients' clinical diagnoses with perfect matches (except for one patient among the high-risk and low-risk classified patients where the performance of predictions is critical due to the high sensitivity and specificity requirements for clinical treatments. Accuracy validated by leave-one-out cross-validation(LOOCV) was 83.3% while other classification methods of CART and DT performed as comparisons showed worse performances than TLRM.

Keywords

References

  1. Breiman, L., Friedman, J. H., Olshen, R. A. and Stone, C. J. (1984). Classification and Regression Tree, Champmans & Hall.
  2. Cheng, C., Kimmel, R., Neiman, P. and Zhao, L. (2003). Array rank order regression analysis for the detection of gene copy-number changes in human cancer, Genomics, 82, 122-129. https://doi.org/10.1016/S0888-7543(03)00122-8
  3. Inoue, H., Matsuyama, A., Mimori, K., Ueo, H. and Mori, M. (2002). Prognostic score of Gastric Cancer Determined by cDNA Microarray, Clinical Cancer Research, 8, 3475-3479.
  4. Kawaguchi, K., Honda, M., Yamashita, T., Shirota, Y. and Kaneco, S. (2005). Differential gene alteration among hepatoma cell lines demonstrated by cDNA microarray-based comparative genomic hybridization, Biochemical and Biophysical Research Communications, 329, 370-380. https://doi.org/10.1016/j.bbrc.2005.01.128
  5. Kim, M. (2009). Reproducible gene selection algorithm with random effect model in cDNA microarray-based CGH data, Expert Systems with Applications, 36, 11589-11594. https://doi.org/10.1016/j.eswa.2009.03.034
  6. Kim, M. and Chung, H. C. (2009). Standardized genetic alteration score and predicted score for predicting recurrence status of gastric cancer, Journal of Cancer Research and Clinical Oncology, 135, 1501-1512. https://doi.org/10.1007/s00432-009-0597-1
  7. Liu, K. H. and Huang, D. S. (2008). Cancer classification using Rotation Forest, Computers in Biology and Medicine, 38, 601-610. https://doi.org/10.1016/j.compbiomed.2008.02.007
  8. Mestre-Escorihuela, C., Rubio-Moscardo, F., Richter, J. A., Siebert, R., Climent, J., Fresquet, V., Beltran, E., Agirre, X., Marugan, I., Marin, M., Rosenwald, A., Sugimoto, K. J., Wheat, L. M., Karran, E. L., Garcia, J. F., Sanchez, L., Prosper, F., Staudt, L. M., Pinkel, D., Dyer, M. J. and Martinez-Climent, J. A. (2007). Homozygous deletions localize novel tumor suppressor gene in B-cell lymphoma, Blood, 109, 271-280. https://doi.org/10.1182/blood-2006-06-026500
  9. Park, C. H., Jeong, H. J., Choi, Y. H., Kim, S. C., Jeong, H. C., Park, K. H., Lee, G. E., Kim, T. S., Yang, S. W., Ahn, S. W., Kim, Y. S., Rha, S. Y. and Chung, H. C. (2006). Systematic analysis of cDNA microarray-based CGH, International Journal of Molecular Medicine, 17, 261-267.
  10. Pinkel, D. and Albertson, D. G. (2005). Array comparative genomic hybridization and its applications in cancer, Nature Genetics, 37, S11-S17. https://doi.org/10.1038/ng1569
  11. Squire, J. A., Pei, J., Marrano, P., Beheshti, B., Bayani, J., Lim, G., Moldovan, L. and Zielenska, M. (2003). High-resolution mapping of amplifications and deletions in pediatric osteosarcoma by use of CGH analysis of cDNA microarrays, Genes Chromosomes and Cancer, 38, 215-225. https://doi.org/10.1002/gcc.10273
  12. Yang, S. H., Seo, M. Y., Jeong, H. A., Jeung, H. C., Shin, J., Kim, S. C., Noh, S. H., Chung, H. C. and Rha, S. Y. (2005). Gene copy number change events at chromosome 20 and their association with recurrence in gastric cancer patients, Clinical Cancer Research, 11, 612-620.
  13. Yang, Y. H., Dudoit, S., Luu, P., Lin, D., Peng, V., Ngai, J. and Speed, T. (2002). Normalization for cDNA microarray data: A robust composite method addressing single and multiple slide systematic variation, Nucleic Acids Research, 30, e15. https://doi.org/10.1093/nar/30.4.e15