PAULYWater solubility log Sw
GNNGraph-Convolutional Neural Net
Graph-convolutional neural network for prediction of the water solubility
Model type: Neural network - Graph Convolutional Neural Network, 2 layers (64, 128 neurons)
Basic data set: curated data set from Sorkun et al. with additional data from various compilations - a total of 9,800 chemicals
Training set: 6,860 data points
A data augmentation strategy is used to increase the number of input features for the neural network.