S. Y. Kung
Genomic bioinformatics represents a natural convergence of life sciences, computer sciences, and device technologies. A single DNA chip can simultaneously provide critical information on thousands of gene expression levels. Thus it is recognized to be the most critical technology for future drug design and disease classification. In order to capitalize on the massive data offered by genomic microarray technology, the key challenge is to effectively analyze and classify the vast amount of information. It is expected that a major breakthrough may be achieved by effective techniques based on pattern recognition and machine learning. Therefore, this tutorial aims to cover the fundamental machine learning techniques for genomic bioinformatics. It will address the following key issues: (i) Understanding biological coherence models; (ii) machine learning techniques for cluster discovery; (iii) multi-modal fusion; and (iv) applications to real gene expression data.