Table 6. Rule summary for the 1^st degree classifiable and unclassifiable peptides employing the simplified machine learning approach with understandable attributes (ML-simple) for the prediction of IVIG binding.

Attributea	1st degree classifiable		1st degree unclassifiable
	Low\highb	Classified correctlyc	Low\highb	Classified correctlyc
Aromaticity	High	74.3%	Low	53.3%
Polarity	Low	58.7%	High	27.5%
Frequency of arginine	High	31.5%	Low	34.0%
Frequency of tyrosine	High	20.7%	Low	16.9%
Summary factor 5	High	15.1%	Low	15.2%
Antigenicity	High	7.3%	Low	8.7%
Hydrophobicity	Low	4.7%	High	6.5%
Frequency of histidine	Low	3.9%
Frequency of cysteine			Low	10.4%
Preference for reverse turns			High	10.4%
Occurrence in turns			Low	10.4%
Frequency of alanine			High	8.7%

^aDetails on the attributes are given in File S3 (2. Attributes for Machine Learning).

^bWhether the rules state the value of the attribute should be high or low for a peptide to be binding.

^cThe percentage of binding peptides that were correctly classified by rules containing the attribute. This percentage roughly corresponds to the importance of the attribute.