Belfield, S. J.; Cronin, M. T. D.; Enoch, S. J.; Firman, J. W. Guidance for Good Practice in the Application of Machine Learning in Development of Toxicological Quantitative Structure-Activity Relationships (QSARs). PLOS ONE, 2023, 18, e0282924.

Compound

pIGC50: 40-h Tetrahymena toxicity as log(1/IGC50) [log(L/mmol)] i

Value	Source or prediction
3.34	experimental value
2.73	RF: QSAR model for Tetrahymena pyriformis growth inhibition using the RF algorithm (Training set)
1.8	RF: QSAR model for Tetrahymena pyriformis growth inhibition using the RF algorithm (10-fold cross-validation)
3.33	SVM: QSAR model for Tetrahymena pyriformis growth inhibition using the SVM algorithm (Training set)
2.24	SVM: QSAR model for Tetrahymena pyriformis growth inhibition using the SVM algorithm (10-fold cross-validation)
2.62	KNN: QSAR model for Tetrahymena pyriformis growth inhibition using the KNN algorithm (Training set)
1.6	KNN: QSAR model for Tetrahymena pyriformis growth inhibition using the KNN algorithm (10-fold cross-validation)
3.31	XGB: QSAR model for Tetrahymena pyriformis growth inhibition using the XGB algorithm (Training set)
2.17	XGB: QSAR model for Tetrahymena pyriformis growth inhibition using the XGB algorithm (10-fold cross-validation)
3.12	SNN: QSAR model for Tetrahymena pyriformis growth inhibition using the SNN algorithm (Training set)
3.07	SNN: QSAR model for Tetrahymena pyriformis growth inhibition using the SNN algorithm (10-fold cross-validation)
3.18	DNN: QSAR model for Tetrahymena pyriformis growth inhibition using the DNN algorithm (Training set)
3.05	DNN: QSAR model for Tetrahymena pyriformis growth inhibition using the DNN algorithm (10-fold cross-validation)