PAULYAcute Fish Toxicity log LC50
GNNGraph-Convolutional Neural Net
Graph-Convolutional Neural Net for the Prediction of Acute Fish Toxicity log LC50
Neural Network including 2 hidden layers with 16 neurons located in each layer, trained by the early stopping approach. The unit of the LC50 values is mol/L (given as log value).
Dataset of Schüürmann et al. - contains 691 chemicals
539 Chemicals
Data augmentation strategy was applied to enlarge the number of input features for training of the neural net.
The neural net predicts the excess toxicity log Te. Log LC50 acute is predicted by the use of log Te and log LC50 narcosis. The log LC50 narcosis value is estimated by log Kow (predicted by a GNN).