DESIGNING COMBINATORIAL LIBRARY MIXTURES USING A GENETIC ALGORITHM

The design of combinatorial mixture libraries should take account of a number of factors. This paper describes the application of a genetic algorithm to optimizing the diversity of libraries while minimizing th e effort that will be needed to deconvolute the biological kits by mas s-spectroscopic techniques. It differs from previous applications of g enetic algorithms to combinatorial library design in that each chromos ome encodes an entire library with the result that properties of the l ibrary are optimized. Our method is such that it is easily extensible to optimizing the distributions of any number of physical or other pro perties of the library. The method allows for the combinatorial constr aint inherent in mixtures that every substituent at each diversity sit e must occur in combination with every substituent at every other site . We present results showing that the genetic algorithm can produce go od library designs in a timely manner.