Performance for 1st degree unclassifiable peptides, further split into 2nd degree classifiable and unclassifiable peptides employing the simplified machine learning approach with understandable attributes (ML-simple) for prediction of IVIG binding*.

*Comparison of AUC and accuracy when the classifier was 10-fold cross-validated on peptides of the 1st degree unclassifiable set or on its peptide subsets that the first one classified correctly (2nd degree classifiable) or incorrectly (2nd degree unclassifiable), respectively. All classifiers used the interpretable attributes and logistic regression.