統計分析之於酵母菌發酵的微陣列

Abstract

在此論文中，我們將以統計的方法來研究microarray資料。microarray的優點在於其可以很快速、且同時獲取許多的生物資訊，但缺點則為其準確性不是很高。因此，我們做了四次實驗，以統計方法來分析此四次實驗以避免有不正確的訊息。在此研究中我們總共必須去分析超過六千個基因，因此，我們必須先把一些準確性不高、變化性不大的基因過濾掉。而後我們想知道剩下沒被過濾掉的基因所表現的型態，因此，我們使用了兩種不同的分類方法來對這些沒過濾的基因做分類。最後，我們亦將觀察分完群的基因與葡萄糖消耗兩者之間的關係。對於我們在此研究所感興趣的基因，可以使用RT-PCR來更加以確認這些基因的一致性。

In this study, we will analyze the microarray data by several statistical methods. The advantage of microarray is that we can gain much information at the one time. However, its disadvantage is that it is not very precise. Hence, we need to do four times of experiments to avoid some false signals. The numbers of genes are over than six thousands. Therefore, we will filter some genes first. We wonder what the unfiltered genes look like, so we will cluster unfiltered genes by two clustering methods and will choose a better one by some viewpoints. Finally, we will investigate the relationships between genes in groups and glucose consumptions. The experiment data by RT-PCR can be studied to confirm the profiles of gene expressions that are interesting in this study in the future.