Combinatorial Library Design Using a Multiobjective Genetic Algorithm
Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom
Early results from screening combinatorial libraries have been disappointing with libraries either failing to deliver the improved hit rates that were expected or resulting in hits with characteristics that make them undesirable as lead compounds. Consequently, the focus in library design has shifted towards designing libraries that are optimised on multiple properties simultaneously. For example, in diverse libraries it is important that the physicochemical properties of the libraries are also optimised so that compounds contained within the library constitute good start points for further optimisation. In focused library design, in addition to matching constraints related to the target molecule, other criteria are often required during lead optimisation, for example, bioavailability and low cost. Many approaches to multiobjective library design are based on the use of a weighted-sum fitness function, however, there are several limitations associated with this approach. MoSELECT is a recent development of the earlier SELECT program for combinatorial library design that overcomes many of the limitations of the weighted-sum approach. MoSELECT is based on a MOGA (MultiObjective Genetic Algorithm) and is able to suggest a family of solutions to multiobjective library design all of which are equally valid in terms of their overall fitness. MoSELECT allows the relationships between the different objectives to be explored with competing objectives easily identified. The library designer can then make an informed choice on which solution(s) to explore. Examples will be given of both diverse and focused library designs.
Daylight Chemical Information