Matching and Visualization of Multiple Overlapping Clusterings of Microarray Data

• Published in: 2007 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology pp. 121 - 126
• Main Authors: Krumpelman, C., Ghosh, J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-04-2007
• Subjects: Algorithm design and analysis; Bioinformatics; Biological processes; Clustering algorithms; Computational biology; Computational intelligence; Data visualization; Density measurement; Hamming distance; Labeling
• ISBN: 1424407109; 9781424407101
• DOI: 10.1109/CIBCB.2007.4221213

Algorithms have been recently developed for clustering microarray data that allow elements - usually genes - to belong to more than one cluster. The labellings that these algorithms produce are intuitively closer to the reality of biological processes, but are more difficult to analyze by traditional means. In this paper, we introduce an algorithm for aligning the results of overlapping clusterings and for visualizing the results. We demonstrate the utility of the visualization, and provide an example of the application of the alignment technique to constructing an overlapping clustering ensemble