Evolutionary De Novo Design “GAs have been shown to be capable o f describing extremely complex bahaviour in a range o f application domains, including those o f molecular recognition and design. ” (P. Willett)1

I n the previous Chapters we have addressed some issues related to adaptive optimization

methods and fitness calculation in the context o f drug design tasks, in particular evolutionary

algorithms and artificial neural networks. To close the design cycle depicted in Figure 1.4 we still have to define the molecule generator. This will be the main focus o f this Chapter. We

will highlight only selected approaches, which we have chosen either because they illustrate a general principle, or we have particular experience with these methods. Again the focus will be on evolutionary techniques.