Skip to main content

Table 1 Schematic Data table representing the training data set before feature correlation analysis. The three sections of the table are the sequences from iAMP-2 L training set [50], the features derived from the 544 amino acid properties in the AAindex1 [63], and the classification label of antibacterial activity from the positive or negative training data set. an denotes a sequence, bn indicates the sum of the sequence for an AAindex1 property, cn indicates the mean and dn indicates the maximum sum of three adjacent residues in the sequence

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

Sequence Sum of Mean of Window of Antibacterial Activity
A1 …A544 A1 …A544 A1 …A544
a1 (b1)1…(b1)544 (c1)1…(c1)544 (d1)1…(d1)544 Active
a1274 (b1274)1…(b1274)544 (c1274)1…(c1274)544 (d1274)1…(d1274)544 Active
a1,275 (b1,275)1…(b1,275)544 (c1,275)1…(c1,275)544 (d1,275)1…(d1,275)544 Inactive
a 2714 (b 2714)1…(b 2714)544 (c 2714)1…(c 2714)544 (d 2714)1…(d 2714)544 Inactive