Uniform Coverage Design for Molecule Selection

• Activity Number: 235
• Type: Invited
• Date/Time: Tuesday, August 13, 2002 : 2:00 PM to 3:50 PM
• Sponsor: Technometrics
• Author(s): Raymond Lam*+ and Stanley Young and William Welch
• Affiliation(s): GlaxoSmithKline, Inc. and GlaxoSmithKline, Inc. and University of Waterloo
• Keywords: Drug discovery ; High throughput screening ; Space-filling design ; Projection ; Binning ; Exchange algorithm

Abstract

In screening for drug discovery, chemists often select a large subset of molecules from a very large database (e.g., select thousands of molecules from hundreds of thousands). To generate diverse leads for drug optimization, highly active compounds in several structurally different chemical classes are sought.

Molecules can be characterized by numerical descriptors, and the chosen subset should cover the descriptor space, or subspaces formed by several descriptors. In high dimensional space, nearly all data sets are sparse, and it is not possible to densely cover a high-dimensional space with thousands of design points. After reviewing the main approaches in the literature, we propose a method that concentrates on low-dimensional subspaces, a criterion for uniformity of coverage, and a fast exchange algorithm to optimize the criterion. These methods are illustrated using a National Cancer Institute database.