| Abstract
| - The use of classification trees for modeling and predicting the passage of molecules through the blood−brain barrier was evaluated. The models were built and evaluated using a data set of 147 molecules extractedfrom the literature. In the first step, single classification trees were built and evaluated for their predictiveabilities. In the second step, attempts were made to improve the predictive abilities using a set of 150classification trees in a boosting approach. Two boosting algorithms, discrete and real adaptive boosting,were used and compared. High-predictive classification trees were obtained for the data set used, and themodels could be improved with boosting. In the context of this research, discrete adaptive boosting givesslightly better results than real adaptive boosting.
|
