Abstract
Evolutionary algorithms have been widely adopted for solving many of the complex tasks involved in drug design. Here, applications to two different tasks are reviewed: combinatorial library design and deriving quantitative structure-activity relationship (QSAR) models. Combinatorial libraries are the result of combinatorial synthesis whereby robotics is used to synthesise large numbers of compounds in parallel. Many more compounds could be made than can be handled in practice; thus, methods are required for selecting appropriate subsets of compounds. The large numbers involved make this problem well suited to the application of optimisation techniques such as evolutionary algorithms. QSARs attempt to relate a numerical description of molecular structure to known biological activity. Large numbers of easily computable molecular descriptors are now available that could be used to derive models; however, when more descriptors are available than observations, or compounds, overfitting of the data can result where the models generated have poor predictive ability. Thus evolutionary algorithms have successfully been applied to select descriptors that give rise to good QSAR models.
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Editor information
Rights and permissions
About this chapter
Cite this chapter
Gillet, V.J. Applications of Evolutionary Computation in Drug Design. In: Johnston, R.L. (eds) Applications of Evolutionary Computation in Chemistry. Structure and Bonding, vol 110. Springer, Berlin, Heidelberg. https://doi.org/10.1007/b13935
Download citation
DOI: https://doi.org/10.1007/b13935
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40258-9
Online ISBN: 978-3-540-44882-2
eBook Packages: Springer Book Archive