Skip to main content
Fig. 2 | Journal of Cheminformatics

Fig. 2

From: Tuning gradient boosting for imbalanced bioassay modelling with custom loss functions

Fig. 2

Summary of the benchmarking results for the MolData datasets. Error bars represent the standard error of the mean (N = 5), while the asterisks denote whether the difference is significant (one indicates α < 0.05, two α < 0.01). The statistical tests with Bonferroni correction are carried out with respect to WCE. We define the differences between loss functions within LightGBM as performance comparisons, while classifier comparisons refer to the benchmarking of the best loss function against the classifiers from Arshadi et al. a Loss function comparison on the Phosphatase dataset. b Comparison between the best loss function and the best models from Arshadi et al. on the Phosphatase dataset c Loss function comparison on the NTPase dataset. d Comparison between the best loss function and the best models from Arshadi et al. on the NTPase dataset

Back to article page