Normalization before clustering is often needed for proximity indices, such as Euclidian distance, which are sensitive to differences in the magnitude or scales of the attributes. The goal is to equalize the size or magnitude and the variability of these features. This can also be seen as a way to adjust the relative weighting of the attributes. In this context, we present a first large scale data driven comparative study of three normalization procedures applied to cancer gene expression data. The results are presented in terms of the recovering of the true cluster structure as found by five different clustering algorithms.