If we visualize the data in Fig. 1a in a high-dimensional space, the hidden pattern stands out. Due to the difficulties in visualizing data beyond 3D, we only select columns 32, 41 and 45 in Fig. 1a to form a new data matrix with a 2-column bicluster embedded inside. In this figure, there exists an obvious plane, which provides clues about the hidden bicluster in the data.
Gan et al. BMC Bioinformatics 2008 9:209 doi:10.1186/1471-2105-9-209