Classification of Blood-Brain Barrier Permeation by Kohonen's Self-Organizing Neural Network (KohNN) and Support Vector Machine (SVM)

Kohonen's self-organizing neural network (KohNN) method and support vector machine (SVM) classification method were used to build blood-brain barrier permeation prediction model, respectively. Based on five 2D property autocorrelation descriptors, several models have been built which were able to classify BBB penetration and nonpenetration compounds with the accuracy of over 96%.