Network-regularized bi-clique finding for tumor stratification Conference Paper uri icon

abstract

  • Copyright © 2014 ACM. Complex diseases such as cancer are known to be highly het- erogeneous which results in tumor subtypes that show vary-ing behavior, including different survival time, treatment responses, and recurrence rates. One important problem in biomedical research is to identify tumor subtypes as well as specific genetic markers associated with corresponding subtypes. This tumor stratification problem has been stud-ied using computational approaches, including traditional clustering and bi-clustering algorithms based on available genomic data. In this study we discuss the issues and chal-lenges in existing computational approaches for tumor stratification. We show that the problem can be formulated as finding densely connected sub-graphs (bi-cliques) in a bi- partite graph representation of genomic data. We propose a novel algorithm that takes advantage of prior biology knowl- edge through gene-gene interaction network to find such sub-graphs, which helps simultaneously identify both tumor sub-types and their corresponding genetic markers. Our experi- mental results show that our proposed method outperforms current state-of-the-art methods for tumor stratification.

author list (cited authors)

  • Adl, A. A., & Qian, X.

citation count

  • 0

publication date

  • September 2014