Octanol-Water Partition Coefficient log Kow

Graph-Convolutional Neural Net

Graph-convolutional neural network for the prediction of the octanol-water partition coefficient

Neuronal network including 2 hidden layers with 128 and 64 neurons, trained over 40 epochs

curated dataset of Mansouri et al. (initially 14,050 chemicals) - containing 13,889 chemicals

10,000 chemicals

Data augmentation strategy was applied to enlarge the number of input features for training of the neural network.