Predicting functional types of antimicrobial peptides with pseudo amino acid composition and multi-label k-nearest neighbor algorithm
WANG Xiao
YANG Peng-peng
WANG Rong
LI Hui
Abstract：In order to solve the problem that most of the existing computational methods can only predict one functional type of antibacterial peptides,a computational prediction method was developed for predic-tion of multiple functional types of antibacterial peptides based on the pseudo amino acid composition (PseAAC)and multi-label k-nearest neighbor(MLkNN)algorithm.It used the PseAAC to extract feature vector of antimicrobial peptide sequence,introduced the MLkNN algorithm as the prediction engine,and predicted a variety function type of antibacterial peptides simultaneously.Experimental results showed that the proposed method significantly improved the prediction performance,and it provided a useful tool for the further research in this field.
Keywords：antimicrobial peptidepseudo amino acid composition (PseAAC)multi-label classificationmulti-label k-nearest neighbor(MLkNN)algorithm
Publication Date：2015-10-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：3( 85-87 )