This project aims to investigate and develop data mining algorithms for finding the most relevant biomarkers contained in biological datasets. The project has a specific focus on Alzheimer’s disease related data sets, aiming to generate good predictive models for classifying Alzheimer’s disease from control, as well as for predicting data points with the potential to develop Alzheimer’s.
High throughput data generated from microarrays and mass spectrometry from biological samples are very high dimensional data. Examples include DNA microarray data sets with up to 500,000 genes and mass spectrometry data with 300,000 m/z values. While the availability of such data sets will aid in the development of techniques for diagnosis and treatment of diseases, a major challenge involves its analysis to extract useful and meaningful information.
Associate Professor Chiou-Peng Lam
Dr Simon Laws
Professor Ralph Martins
Mr Vinh Dang