A0256
Title: Row-constrained supersaturated designs for high-throughput screening
Authors: Stephen Wright - Miami University-Oxford (United States)
Isaac Williams - Miami University-Oxford (United States)
Rick Page - Miami University-Oxford (United States)
Andor Kiss - Miami University-Oxford (United States)
Surendra Bikram Silwal - Miami University-Oxford (United States)
Maria Weese - Miami University (United States)
David Edwards - Virginia Commonwealth University (United States)
Byran Smucker - Henry Ford Health Systems (United States) [presenting]
Abstract: High-throughput screening is widely used across many areas of science, perhaps most prominently in drug discovery. A statistically principled approach is proposed to these screening experiments, using the machinery of supersaturated designs and the Lasso. To accommodate limitations on the number of biological entities that can be pooled in a single microplate well, a new class of row-constrained supersaturated designs is presented. A computational procedure is developed to construct these designs, the effect of the constraint is studied on design quality, and it is shown via simulation that the proposed method is statistically superior to existing methods. Results of several applications of these designs are also shown in a system measuring the inhibition of metallo-beta-lactamase.
