Discovering genome expression patterns with self-organizing neural networks

Abstract

Self-organizing neural networks represent a family of useful clusteringbased classification methods in several application domains. One such technique is the Kohonen Self-Organizing Feature Map (SOM) (Kohonen, 2001), which has become one of the most successful approaches to analysing genomic expression data. This model is relatively easy to implement and evaluate, computationally inexpensive and scalable. In addition, it exhibits significant advantages in comparison to other options. For instance, unlike hierarchical clustering it facilitates an automatic detection and inspection of clusters. Unlike Bayesian-based clustering it does not require prior hypotheses or knowledge about the data under consideration. Compared to the k-means clustering algorithm, the SOM exemplifies a robust and structured classification process. - [Introduction]