Table 2. Area under the ROC curves (Fig 5).

The curves were based on the discrimination of all binders from non-binders, and of only strong binders from non-binders.

Model	All binders		Strong binders
	Training	Validation	Training	Validation
Rüdiger, et al. [15]	0.80	0.81	0.85	0.86
Limbo [16]	0.77	0.77	0.85	0.82
ChaperISM [21]	0.81	0.82	0.87	0.87
Paladin	0.76	0.75	0.82	0.83
Raw Terms	0.63	0.65	0.67	0.74