From DNA Micro-arrays to Disease Classification: An Unsupervised Clustering Approach

Authors:	Bittanti Sergio, Politecnico di Milano, Italy Garatti Simone, Politecnico di Milano, Italy Liberati Diego, CNR - IEIIT, Italy
Topic:	8.2 Modelling & Control of Biomedical Systems
Session:	Biomedical Engineering / Biomedical Signal Processing I
Keywords:	Data analysis for biomedical diagnosis, Bioinformatics, Data-mining, Clustering

Abstract

DNA micro-arrays provide thousands of genomic expressions on the same subject. A main issue is then to find the subset of genes whose degeneration is responsible of a certain type of cancer. In this paper, starting from a paradigmatic classification problem of two kinds of Leukaemia, we discuss the use of data-mining techniques in such a context. Particular attention is devoted not only to the classification methods but also to all the data analysis steps including data pre-processing and information retrieval.