J. Devillers

Use of Intercommunicating Hybrid Systems in QSAR.

CTIS, 3 Chemin de la Graviere, 69140 Rillieux la Pape, France. E-mail: jde-ctis@imaginet.fr

It is now well admitted that certain complex problems in QSAR cannot be solved by a single technique alone. Each approach presents particular properties that make them suited for specific applications and not for others. The strengths and weaknesses of these different techniques have been the central driving force behind the creation of intercommunicating hybrid systems where two or more techniques are combined in order to overcome the limitations of each approach and create a synergy between them in order to provide valuable modeling tools. The notion of intercommunicating hybrid system covers not only the mixing and matching of different linear and/or nonlinear statistical techniques for deriving powerful QSAR models. This concept also deals with the integration of statistical and graphical tools with conventional computing systems such as spreadsheets and databases for data mining, optimal test series design, and so on. In this context, through different examples of application the principles, advantages, and limitations of intercommunicating hybrid systems showing different levels of complexity are presented.

Back to Program Page
Back to Main Page