Estimating Octanol-Water Partition Coefficients with an Autocorrelation/Neural Network Model
CTIS, 3 Chemin de la Graviere, 69140 Rillieux la Pape, France. E-mail: email@example.com
A composite backpropagation neural network model (BNN)  was developed for calculating the n-octanol/water partition coefficient (log P) of molecules containing nitrogen, oxygen, halogen, phosphorus, and/or sulfur atoms. Chemicals were described by means of autocorrelation vectors encoding hydrophobicity, molar refractivity, H-bonding acceptor ability, and H-bonding donor ability. A 35/32/1 BNN constituted of four configurations was selected as final model (RMS = 0.37, r = 0.97) because it allowed to obtain the best simulation results (RMS = 0.39, r = 0.98) on an external testing set of 519 molecules. This final model compared favorably with different models based on atom/fragment contribution values and correction factors.
 Devillers, J. (1996). Neural Networks in QSAR and Drug Design. Academic Press, London, p. 284.Back to Program Page