Description

This web server ranks proteins found in NRDB40 (from PairsDB) against a query sequence of amino acids using the Rankprop algorithm (PDF).
For an example output see here

Methods

Rankprop is a ranking algorithm that exploits the global network structure of similarity relationships among proteins in a database by performing a diffusion operation on a protein similarity network with weighted edges The method employed on this server is based on the following publications:

[1] Iain Melvin, Jason Weston, Christina Leslie, and William Stafford Noble RANKPROP: a web server for protein remote homology detection Bioinformatics (2008)
[2] William Stafford Noble, Rui Kuang, Christina Leslie and Jason Weston Identifying remote protein homologs by network propagation FEBS Journal, Volume 272 Issue 20 Page 5119, October, 2005
[3] J. Weston, A. Eliseeff, D. Zhou, C. Leslie and W. Stafford Noble Protein ranking: from local to global structure in the protein similarity network Proceedings of the National Academy of Science. 101(17):6559-6563, 2004
[4] Jason Weston, Rui Kuang, Christina Leslie and William Stafford Noble Protein Ranking by Semi-Supervised Network Propagation BMC Bioinformatics, 2004

Source Code

A snapshot of the web server source is available here
Source for the experiments is available here.
The current Torch5 implementation of the Rankprop algorithm can be found here.
The website requires the source for the experiments to be installed along with supporting software such as Torch5 (The Machine Learning toolbox).

Credits

The Rankprop server was created by Iain Melvin, Jason Weston, Rui Kuang, Christina Leslie and William Stafford Noble.

This web server was supported by National Institute of Health grant GM74257.

This work was also funded in part by award EIA-0312706 from the National Science Foundation.

Jason Weston and Iain Melvin also thank NEC Laboratories America, Princeton, where they work, for their support of this project.

[back to main page]