Self-adaptive Mutation in Molecular Evolution

This study is focused on an evolutionary algorithm for automated de novo drug design. It discusses how to improve the mutation operator of such an algorithm. By introducing a weighted mutation scheme it tries to improve the performance of the algorithm as well as facilitating for the use of self-adaptation. The two questions which this study tries to answer are: Does introduction of di erent weights for each type of mutation make a di erence in the performance of the algorithm? Can self-adaptation help choosing good parameters for the algorithm and maybe improve the performance? The proposed methodology is evaluated in a case-study on automated drug design where we aim to nd molecular structures that could serve as inhibitors of Lipoxygenase, which is involved in the metabolism of fatty acids (and thus simply the fats we are eating).