We propose an approach to design drug-like molecules based on structural similarity. A molecular evolutionary algorithm was used for designing molecules. First, fragments derived from an active molecule were utilized as seed structures. Then, the structures of initial generation were generated by randomly adding a fragment for each seed structure. These molecules were evolved in accordance with evolutional operations such as crossover, mutation, and selection.<br/>Computational experiments were carried out to evaluate the performance of our approach. Active molecules (reference molecules) were taken from public database, and fragments obtained from each reference molecule were used as seed structures. The result of computational experiments shows that the approach is useful to design drug-like molecules with new molecular frameworks.

<i>In-silico</i> design of drug-like molecules by a fragment-based molecular evolutionary approach

251st National Meeting (2016)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.

In-silico design of drug-like molecules by a fragment-based molecular evolutionary approach