University of Minnesota
University Relations

Minnesota Supercomputing Institute

Log out of MyMSI

Research Abstracts Online
January 2008 - March 2009

University of Minnesota Twin Cities
Institute of Technology
Department of Computer Science and Engineering

PI: Rui Kuang

Mining Clinical and Genetic Markers of Human Disease

This project introduces a graph-based semi-supervised feature classification algorithm to identify discriminative patterns by learning on bipartite graphs built from clinical variables, gene expressions, and single nucleotide polymorphisms. Instead of performing feature selection or data-mining association analysis, this algorithm directly classifies the feature nodes in a bipartite graph as positive, negative, or neutral with network propagation, which captures the interactions between both samples and features (clinical and genetic variables) by exploring the global structure of the graph. Although optimized for classifying the features, the algorithm can also simultaneously classify the test samples for disease prognosis/diagnosis.

Group Members

Changjin Hong, Graduate Student
Ba Ryun Hwang, Graduate Student
Taehyun Hwang, Graduate Student
Ze Tian, Graduate Student
Loc Tran, Graduate Student