Methods to enhance the perfomance of similarity searching

COMP 102

Jérôme Hert, hert@cgl.ucsf.edu1, David J. Wilton2, and Peter Willett, p.willett@sheffield.ac.uk2. (1) Department of Pharmaceutical Chemistry, University of California, San Francisco, 1700 4th Street, QB3 Building Room 509, San Francisco, CA 94143-2550, (2) Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom
Fingerprint-based similarity searching is well established for virtual screening applications. This paper investigates alternative ligand-based approaches in which we test the hypothesis that fusing the outputs of similarity searches based on a single bioactive reference structure and on its nearest neighbors is more effective than a similarity search involving just the reference structure. This "turbo similarity searching" approach was evaluated using different similarity measures, and datasets and was found to provide a simple way to improve the performance of simulated virtual screening searches.
 

Molecular Similarity and Indexing Methods
1:00 PM-4:00 PM, Monday, 11 September 2006 Moscone Center -- Room 224/226, Oral

Division of Computers in Chemistry

The 232nd ACS National Meeting, San Francisco, CA, September 10-14, 2006