More about HKUST
DNA Microarray Data Clustering and Biclustering
Speaker: Prof. Hong Yan Department of Electronic Engineering City University of Hong Kong Title: "DNA Microarray Data Clustering and Biclustering" Date: Monday, 6 February 2006 Time: 4:00pm - 5:00pm Venue: Lecture Theatre F (Leung Yat Sing Lecture Theatre, near lift nos. 25/26) HKUST ABSTRACT: The DNA microarray allows the measurement of expression levels of thousands of genes simultaneously. Microarray data analysis is a challenging problem and has attracted enormous interests from researchers in science and engineering. Microarray data can be represented as a matrix, in which rows correspond to genes and columns to conditions or time points. In clustering, we perform classification along either the row or the column direction, while in biclustering we perform classification along both row and column directions. In this seminar, I shall present our recent work on microarray data clustering and biclustering. We have develop a competitive learning based method to find natural clusters in the data and use partial knowledge as constraints to improve the stability of the clustering results. For time-series data, we have developed an autoregressive model based technique to analyse the spectral similarity between gene expression profiles. This method has identified gene regulations at different frequencies, in a way similar to frequency division in communication systems. Biclustering is often associated with the stigma of being inherently intractable in general because of its computational complexity. We have recently developed a hyperplane model for solving this problem. By separating different types of biclusters and filtering out irrelevant data, our method can reduce the computational complexity substantially and extract large biclusters. The method has been applied to medical diagnosis using microarray data. ******************** Biography: Hong Yan received his Ph.D. degree from Yale University. He has been Professor of Imaging Science at the University of Sydney and currently is Professor of Computer Engineering at City University of Hong Kong. His research interests include image processing, pattern recognition and bioinformatics. Professor Yan is elected a Fellow of the Institute of Electrical and Electronic Engineers (IEEE) for contributions to image recognition techniques and applications and a Fellow of the International Association for Pattern Recognition (IAPR) for contributions to document image analysis. He is also a Fellow of the Institution of Engineers, Australia (IEAust) and a member of the International Society for Computational Biology (ISCB).