本論文主要的目的是對於酵母菌中與調節細胞週期有關的基因的參數進行統計分析。我們以 Spellman 所找到的 800 個與調節細胞週期有關的基因，和 MIPS 資料庫中功能與調節細胞週期及 DNA 過程有關的 687 個基因為分類標準。進而應用統計方法與模型對酵母菌中與調節細胞週期有關的基因的參數進行分析，且在分析過程中主要考慮的四個參數分別是，基因在進行轉錄前需與多少個轉錄因子結合的個數及 alpha-factor、cdc15、cdc28 同步化實驗下各個基因與 104 個已知的基因在某些頻率的相關性。經過我們的分析後可以得知，轉錄因子的結合個數在兩個子群中，可以幾何分佈配適，但若是想單獨利用隱藏式馬可夫模型去做為調節細胞週期基因與非調節細胞週期基因的分類標準是不夠的。此外我們亦得知，在某些頻率的相關性是一個不錯的分類指標。最後我們發現，MIPS 資料庫中與細胞週期及 DNA 過程有關的 687 基因包含 Spellman 所找到的 800 個調節細胞週期基因在分類中所隱含的資訊。

In this thesis, the main objective is to perform statistical analysis of parameters yeast cell cycle regulated genes. We have known that there are 800 cell cycle regulated genes from Spellman et al. [9] (Spellman’s 800) and 687 cell cycle regulated genes from MIPS database (MIPS’s 687). We analyze yeast cell cycle regulated genes with statistical methods and models. The four main index statistics considered are as follow: 1. numbers of triscription factors bind to promoters, 2. coherence of genes with 104 known regulated genes (KRG)
in alpha-factor experiment, 3. coherence of genes with 104 KRG in cdc15 experiment, 4. coherence of genes with 104 KRG in cdc28 experiment. Although, binding numbers can be
fitted to geometric distribution in two subgroups of genes, we found that it is infeasible to classify the cell cycle regulated genes by only using HMM, and the coherence method also improve Spellman classification results if the standard is MIPS database or the 104 KRG. Finally, the cell cycle classification criterion in MIPS’s 687 genes are found to include the information given by Spellman’s 800.

1 Introduction
2 Data description
3 Hidden markov model
4 Spectrum analysis
5 Logistic and discriminant analysis
6 Conclusion References
References
Figures and tables

[1] R. J. Cho, and et al. A genome-wide transcriptional analysis of the mitotic cell cycle. Mol. Biol. of the Cell, 2:65-73, 1998.

[2] Maria C. Costanzo, Jennifer D. Hogan, and et al. The Yeast Proteome Database (YPD) and Caenorhabditis elegans Proteome Database (WormPD): comprehensive resources for the organization and comparison of model organism protein information. Nucleic Acids Research, 28:73-76, 2000.

[3] Tong Ihn Lee, Nicola J. Rinaldi, and et al. Transcriptional regulatory networks in saccharomyces cerevisiae. Science, 298:799-804, 2002.

[4] Bryan Lemon and R. Tjian. Orchestrated response: a symphony of transcription factors for gene control. Genes & Development, 14:2551-2569, 2000.

[5] S. E. Levinson. An introduction to the application of the theory of probabilistic functions of a markov process to automatic speech recognition. Bell System Tech.,
62:1035-1074, 1983.

[6] Iain L. MacDonald,and Walter Zucchini. Hidden Markov and other models for discrete-valued time series. CHAPMAN & HALL, 53-105, 1997, London.

[7] Douglas C. Montgomery, Elizabeth A. Peck, G. Geo rey Vining. Introduction to linear regression analysis. WILEY-INTERSCIENCE, 444-449, 2001, United States
of America.

[8] Alvin C. Rencher. Methods of multivariate analysis. WILEY-INTERSCIENCE, 300-302, 2002, United States of America.

[9] P. S. Spellman, G. Sherlock, and et al. Comprehensive identification of cell cycleregulated genes of the yeast saccharomyces cerevisia by microarray hybridization.
Mol. Biol. of the Cell, 9:3273-3297, 1998.

[10] W. S. Wei. Time series analysis. Addison Wesley, 207-329, 1997, New York.