Figure 6.

MI-based scores of clustering solutions with 5 clusters. Efficiency frontiers for solutions with 5 clusters, obtained by the K-means, the SOM, the sIB and the Click clustering algorithms. The clusters are obtained over the Yeast cell-cycle dataset with 800 genes and 72 experimental time-conditions. The scores are depicted on the MI-based Homogeneity-Separation plane.

Priness et al. BMC Bioinformatics 2007 8:111   doi:10.1186/1471-2105-8-111
Download authors' original image