Table 2 Rough set theory rules generated with maximum support from large training dataset. The first rule describes antibacterial sequences. The accuracy of this rule is 97.8% (446/456) for the peptides that met the conditions from either the dataset from Xiao, et al [50] or the dataset from Fernandes, et al. [64]

From: Antimicrobial peptide similarity and classification through rough set theory using physicochemical boundaries