One of the main problems of drug design is that it is quite hard to discover compounds that have all the required properties to become a drug (efficacy against the disease, good biological... Show moreOne of the main problems of drug design is that it is quite hard to discover compounds that have all the required properties to become a drug (efficacy against the disease, good biological availability, low toxicity). This thesis describes the use of data mining and interactive evolutionary algorithms to design novel classes of molecules. Using data mining, we split a 250,000 compound database into ring systems, substituents and linkers. We then counted the occurrence of the different fragments, as well as their co-occurrence. Our resulting lists of common and uncommon chemical substructures and substructure combinations can be used to increase the diversity of drug screening libraries and hence increase their chance to yield new drugs. We also developed a computer program, the Molecule Evoluator. This program uses an interactive evolutionary algorithm to propose novel molecules or molecule modifications. Using the Molecule Evoluator, our chemists were able to discover three novel classes of compounds, resulting in the synthesis of eight new compounds. Four of these proved to bind to biogenic amine targets such as the norepinephrine transport protein and the alpha-adrenergic receptors. So, our computer methods offer inspiration to chemists, helping them to get new ideas for drug molecules. Show less
