Figure 4.

Effect of the number of microarray experiments on the compendium data subset with 537 genes. Using YPD as the evaluation criterion, we compared the median z-scores using different numbers of experiments and different clustering algorithms (hierarchical average-link and complete-link using correlation, model-based clustering algorithms MCLUST and IMM on standardized data) on the compendium data subset with 537 genes and 258 experiments at 40 clusters. The median z-scores (and hence, proportions of co-regulated genes) increase as the number of experiments increases, and MCLUST produces relatively high median z-scores. We observed very similar results using ChIP data as the evaluation criterion.