MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MIXED MODEL, PREDICTING THE OCTANOL-WATER PARTITION COEFFICIENT OF A PURE ORGANIC COMPOUND, CAPABLE OF FORMING AN ANN OUTPUTTING THE OCTANOL-WATER PARTITION COEFFICIENT

摘要

PURPOSE: A MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) mixed model, predicting the octanol-water partition coefficient of a pure organic compound, is provided to form an ANN outputting the octanol-water partition coefficient, thereby improving prediction performance.;CONSTITUTION: A molecule descriptor value about the octanol-water partition coefficient of a hydrocarbon series organic compound is prepared. Experimental data is separated into a training set and a test set. An optimum MLRM(Multiple Linear Regression Model) for the training set is explored. The predicted performance of the optimum MLRM is tested on the test set. After an optimum ANNM(Artificial Neural Network Model) divides every samples into three sets, it is explored. If the absolute value of the difference of a octanol-water partition coefficient prediction value, figured out by the MLRM and the ANNM, is greater than an over-suitability preventing standard value, the octanol-water partition coefficient prediction value by the MLRM is selected as an octanol-water partition coefficient value.;COPYRIGHT KIPO 2012