臺灣博碩士論文加值系統

基因表現將DNA序列中的資訊轉換成RNA或蛋白質。在細胞中基因經由其表現的產物交互作用形成了基因調控網路(GRN)。我們提出一個具有一隱藏層之同時回歸類神經網路(SRNN)模型類似於基因調控網路原理。經由使用時間序列基因表現資料，我們提出模型且以模型選擇演算法去推論目標基因的調控基因。為了比較，我們也以線性和Hopfield神經網路模型為基礎預測目標基因的調控子。為能客觀地評估調控子辨識程序，時間序列基因表現資料將由已知調控性質的人造基因調控網路和動力特性所生成。

Gene expression translates information encoded in DNA sequences to produce RNA or proteins. Genes in a living cell interacting with each other through expression products gives rise to the genetic regulatory network (GRN). We present a one hidden layer simultaneous recurrent neural network (SRNN) model formally resembling the principals of GRN. Using time series gene expression data, we apply the model and model selection algorithms to infer regulators of target genes. To make comparisons, we also predict regulators of target genes based on linear and Hopfield neural network models. To objectively evaluate the regulator identification procedure, the time series gene expression data are generated by an independent artificial GRN with well-defined regulatory and kinetic properties.

1. Introduction ………………………………………………………1
2. Method ………………………………………………………………3
2.1. Background …………………………………………3
2.2. SRNN model of GRN …………………………………3
2.3. The regulators of a target gene ………………4
2.4. Selection algorithms………………………………5
3. Results ………………………………………………………………8
4. Discussion …………………………………………………………11
Reference ………………………………………………………………20
Appendix ………………………………………………………………22

1. Bansal, M., G.D. Gatta, and D. di Bernardo, Inference of gene regulatory networks and compound mode of action from time course gene exxpression profiles. Bioinformatics, 2006. 22(7): p. 815-22.
2. Mendes, P., W. Sha, and K. Ye, Artifical gene networks for objective comparison of analysis algorithms. Bioinformaatics, 2003. 19 Suppl 2: p. ii122-9.
3. Nam, D., S.H. Yoon, and J.F. Kim, Ensemble learning of genetic networks from time-series expression data. Bioinformatics, 2007. 23(23): p. 3225-31.
4. Vohradsky, J., Neural model of the genetic network. J Biol Chem, 2001. 276(39): p. 36168-73.
5. Zou, M. and S.D. Conzen, A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time course microarray data. Bioinformatics, 2005. 21(1): p. 71-9.
6. de Jong, H., Modeling and simulation of genetic regulatory systems: a literature review. J Comput Biol, 2002. 9(1): p. 67-103.
7. Hopfield, J.J., Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA, 1982. 79(8): p. 2554-8.
8. Bose, N.K. and P. Liang, Neural network fundamentals with graphs, algorithms, and applications. Series In Electrical And Computer Engineering 1996, Hightstown, NJ: Mcgraw-Hill.
9. Vu, T.T. and J. Vohradsky, Nonlinear differential equation model for quantification of transcriptional regulation applied to microarray data of Saccharomyces cerevisiae. Nucleic Acids Res, 2007. 35(1): p. 279-87.
10. Vohradsky, J., Neural network model of gene expression. Faseb J, 2001. 15(3): p. 846-54.
11. Vohradsky, J. and C.J. Thompson, Systems level analysis of protein synthesis patterns associated with bacterial growth and metabolic transitions. Proteomics, 2006. 6(3): p. 785-93.
12. Hornik, K., M. Stinchcombe, and H. White, Multilayer feedforward networks are universal approximators. Neural Networks, 1989. 2(5): p. 359-366.
13. Kohavi, R. and G.H. John, Wrappers for feature subset selection Artificial Intelligence 1997. 97(1-2): p. 273-324.