Data mining in drug design

The relationships between the chemical structure of a compound and its biological activity are highly complex. In this situation, the accumulation of data and the extraction of information and knowledge from these data to make predictions is essential for efficient drug design and development. With novel techniques like combinatorial chemistry and high-throughput screening data are gathered at an enormous rate. The processing of this huge amount of data can only be handled by automatic methods. A wide range of methods, statistical and pattern recognition methods, neural networks and genetic algorithms are available and are already used in drug design. The range of methods will be illustrated with some applications from our research group.