Relevant Attribute Discovery in High Dimensional Data Based on Rough Sets and Unsupervised Classification: Application to Leukemia Gene Expressions

Abstract

A pipelined approach using two clustering algorithms in combination with Rough Sets is investigated for the purpose discovering important combination of attributes in high dimensional data. In many domains, the data objects are described in terms of a large number of features, like in gene expression experiments, or in samples characterized by spectral information. The Leader and several k-means algorithms are used as fast procedures for attribute set simplification of the information systems presented to the rough sets algorithms. The data submatrices described in terms of these features are then discretized w.r.t the decision attribute according to different rough set based schemes. From them, the reducts and their derived rules are extracted, which are applied to test data in order to evaluate the resulting classification accuracy. An exploration of this approach (using Leukemia gene expression data) was conducted in a series of experiments within a high-throughput distributed-computing environment. They led to subsets of genes with high discrimination power. Good results were obtained with no preprocessing applied to the data.