Using Emerging Pattern Based Projected Clustering and Gene Expression Data for Cancer Detection

Using gene expression data for cancer detection is one of the famous research topics in bioinformatics. Theoretically, gene expression data is capable to detect all types of early cancer development in molecular level. Traditional clustering and pattern mining algorithm are either inadequate to handle high dimensional gene expression data effectively or the results obtained are not easy to understand. We proposed emerging pattern based projected clustering (EPPC) approaches to cope with the cancer detection problem. Previous result shows that easy understandable clusters are obtained. In this paper, the dimension projection process of EPPC is further studied and experimental results showed that the resulting clusters obtained by EPPC give comparable accuracy in classification when compared with ORCLUS. .

• Type: Conference
• Year: 2004
• Where: APBC
• Authors: Larry T. H. Yu, Fu-Lai Chung, Stephen Chi-fai Chan, Simon M. C. Yuen
• Keywords: APBC 2004, APBC 2007, Cancer Detection, Dimensional Gene Expression, Gene Expression Data