單一病毒生物特徵之相關迴歸分析在基因表現量的研究

本篇論文使用Jiang 等人(2006) 微陣列實驗得到的數據圖去探討一個受限圖形的迴歸方法, 推論出一個基因病毒的時間過程表現量曲線。在Chien 等人(2009) 是用Bernstein 多項式去了描述幾何迴歸函數, 這些函數被假定一開始是0, 經一段時間後持續以正值增加。他們分析一個病毒基因的微陣列數據, 以貝氏方法進行模擬研究以及圖解來得到最後的結果。這個方法的其中一個優勢是藉由迴歸函數的資料, 對假設的模型提供了一個有利的評估; 例如假設此病毒的表現量為單峰模式。這個方法的另一個優點是可判斷估計曲線中許多顯著的特徵; 例如病毒發病時間與基因表現量最大的發生時間等。但本篇論文使用MLE 來估計迴歸曲線, 使其估計的方法為MCMC(馬可夫鏈蒙地卡羅), 模擬研究呈現在最後, 我們也有不錯的估計.

關鍵字

迴歸曲線；伯氏多項式；馬可夫鏈蒙地卡羅

並列摘要

Jiang et al (2006) illustrate a shape restricted regression methed in making inference on the time course espression profile of a virus gene, using data from microarry experiments. Chien et al (2009) introduced through Bernstein polynomials so as to take into consideration the geometry of the regression functions, which are assumed to be zero initially, increasing after a while and staying positive later on. They evaluate the performance of the method in a simulation study and illustrate its use by analyzing the microarray data of a virus gene. One advantage of this method is that it offers an assessment of the strength of the evidence provided by the data in favor of hypothesis on the shape of the regression function;for example, the hypothesis that it is unimodal. Another advantage of this approach is that estimates of many salient features of the profile like onset time, inflection point, maximum value, time to maximum value, etc. can be obtained immediately. However, we here use MLE to estimate regression functions associated with MCMC (Markov Chain Monte Carlo) and obtain the good result in simulation study.

並列關鍵字

Bernstein Polynomial ； Regression curve ； Markov chain Monte Carlo

參考文獻

Y. J. (2007). Shape restricted regression with random Bernstein

Notes-Monograph Series, Vol. 54, 187-202

Green, P. G. (1995). Reversible jump Markov chain Monte Carlo

computation and Bayesian model determination. Biometrika 82,

Jiang, S. S., Chang, I. S., Huang, L. W., Chen, P. C., Wen, C. C.,

國際替代計量

單一病毒生物特徵之相關迴歸分析在基因表現量的研究

全文下載

主題瀏覽