An investigation into pharmaceutically relevant mutagenicity data and the influence on Ames predictive potential

Table 7 Performance for PLS and random forest models for the other set.

	Set A		Set B
Trained on 100% Set A
PLS 1-component	0.72	→	0.73
PLS 1-component, 9 descriptors	0.67	→	0.73
Random Forest	0.68*	→	0.72
Trained on 100% Set B
PLS 1-component all descriptors	0.65	←	0.80
PLS 1-component 9 descriptors	0.68	←	0.77
Random Forest	0.71	←	0.84*

All of Set A or Set B is used as the training set, and the other is used as the test set.
*performance when out-of-bag

ISSN: 1758-2946