时间：2010年5月27日，星期四， 4:00 p.m.
Professor, Michael Ng
Department of Mathematics, Hong Kong Baptist University
Semi-supervised Mining Functional Modules in Yeast PPI Networks
In the literature, there are fruitful algorithmic approaches for identification functional modules in protein-protein interactions (PPI) networks. The main aim of this talk is to present semi-supervised learning strategies to identify functional modules from PPI networks with the aid of Gene Ontology. The strategies include (i) encoding the functional pairs into the existing PPI networks and (ii) using the functional pairs as constraints to learn functional modules in the PPI. Experimental results on Yeast PPI networks and GO have shown that the semi-supervised learning methods perform quite well.