Header logo is

Graph kernels for disease outcome prediction from protein-protein interaction networks

2007

Conference Paper

ei


It is widely believed that comparing discrepancies in the protein-protein interaction (PPI) networks of individuals will become an important tool in understanding and preventing diseases. Currently PPI networks for individuals are not available, but gene expression data is becoming easier to obtain and allows us to represent individuals by a co-integrated gene expression/protein interaction network. Two major problems hamper the application of graph kernels – state-of-the-art methods for whole-graph comparison – to compare PPI networks. First, these methods do not scale to graphs of the size of a PPI network. Second, missing edges in these interaction networks are biologically relevant for detecting discrepancies, yet, these methods do not take this into account. In this article we present graph kernels for biological network comparison that are fast to compute and take into account missing interactions. We evaluate their practical performance on two datasets of co-integrated gene expression/PPI networks.

Author(s): Borgwardt, KM. and Vishwanathan, SVN. and Schraudolph, N. and Kriegel, H-P.
Pages: 4-15
Year: 2007
Month: January
Day: 0
Editors: Altman, R.B. A.K. Dunker, L. Hunter, T. Murray, T.E. Klein
Publisher: World Scientific

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: Pacific Symposium on Biocomputing (PSB 2007)
Event Place: Maui, Hawaii

Address: Hackensack, NJ, USA
Digital: 0
ISBN: 978-981-270417-7

Links: PDF

BibTex

@inproceedings{BorgwardtVSK2007,
  title = {Graph kernels for disease outcome prediction from protein-protein interaction networks},
  author = {Borgwardt, KM. and Vishwanathan, SVN. and Schraudolph, N. and Kriegel, H-P.},
  pages = {4-15},
  editors = {Altman, R.B.  A.K. Dunker, L. Hunter, T. Murray, T.E. Klein},
  publisher = {World Scientific},
  address = {Hackensack, NJ, USA},
  month = jan,
  year = {2007},
  month_numeric = {1}
}