A supervised learning approach to the ensemble clustering of genes

High-throughput techniques have become a primary approach to gathering biological data. These data can be used to explore relationships between genes and guide development of drugs and other research. However, the deluge of data contains an overwhelming amount of unknown information about the organism under study. Therefore, clustering is a common first step in the exploratory analysis of high-throughput biological data. We present a supervised learning approach to clustering that utilises known gene-gene interaction data to improve results for already commonly used clustering techniques. The approach creates an ensemble similarity measure that can be used as input to any clustering technique and provides results with increased biological significance while not altering the clustering method.