BIBS : Statistical Analysis of Microarray

We consider two well known data sets in the microarray literature: the colon data analyzed initially by Alon et al. and the leukemia data first analyzed in Golub et al. (5). Both data sets consist of absolute measurements from Affymetrix oligonucleotide arrays: the first contains n = 62 tissue samples on p = 2,000 human gene expressions (40 tumors and 22 normal tissues)

(a) Find the first 20 genes which are differentially expressed ?

(b) Cluster the samples into two group (using the 20 differentially expressed genes of question (a). Comment.

• data : Alon

• A comparison of normalization methods for high density oligonucleotide array data based on variance and bias B.M.Bolstad1,R.A.Irizarry,M. Astrand andT.P.Speed BIOINFORMATICS Vol. 19 no. 2 2003 Pages 185‚Äì193
• Should We Abandon the t-Test in the Analysis of Gene Expression Microarray Data: A Comparison of Variance Modeling Strategie. PLoS ONE 5(9). Jeanmougin, M. and de Reynies, A. and Marisa, L. and Paccard, C. and Nuel, G. and Guedj, M.. 2010 http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0012336
• Alon U , Barkai N , Notterman D A , Gish K , Ybarra S, Mack D , Levine A J (1999) Proc Natl Acad Sci USA 96:6745‚Äì6750, http://www.pnas.org/content/99/10/6562.full