Fig. 5From: Analysis of the benefits of imputation models over traditional QSAR models for toxicity predictionPerformance of imputation models. A Ames dataset. B Tox21 dataset. Each box summarizes the MCC scores of 20 independent runs of the model on the test set with identical hyperparameters but different random seeds. The XGB models (best performing single task model) are included as a benchmark. Only the best performing Feature Net model (XGB-FN) is included in this plot.Back to article page