Summary: Radial Clustergrams: Visualizing the Aggregate Properties of Hierarchical Clusters
Dimitris K. Agrafiotis,* Deepak Bandyopadhyay, and Michael Farnum
Johnson & Johnson Pharmaceutical Research & Development, L.L.C., 665 Stockton Drive,
Exton, Pennsylvania 19341
Received October 3, 2006
A new radial space-filling method for visualizing cluster hierarchies is presented. The method, referred to
as a radial clustergram, arranges the clusters into a series of layers, each representing a different level of the
tree. It uses adjacency of nodes instead of links to represent parent-child relationships and allocates sufficient
screen real estate to each node to allow effective visualization of cluster properties through color-coding.
Radial clustergrams combine the most appealing features of other cluster visualization techniques but avoid
their pitfalls. Compared to classical dendrograms and hyperbolic trees, they make much more efficient use
of space; compared to treemaps, they are more effective in conveying hierarchical structure and displaying
properties of nodes higher in the tree. A fisheye lens is used to focus on areas of interest, without losing
sight of the global context. The utility of the method is demonstrated using examples from the fields of
molecular diversity and conformational analysis.
Clustering is a common technique used to partition a set
of data points into groups (clusters), so that the points in
each group share some common characteristicsstypically
proximity according to some distance or similarity measure.