Predicting Antibacterial Peptides by the Concept of Chou's Pseudo-amino Acid Composition and Machine Learning Methods

Microbial resistance to antibiotics is a rising concern among health care professionals, driving them to search for alternative therapies. In the past few years, antimicrobial peptides (AMPs) have attracted a lot of attention as a substitute for conventional antibiotics. Antimicrobial peptides have a broad spectrum of activity and can act as antibacterial, antifungal, antiviral and sometimes even as anticancer drugs. The antibacterial peptides have little sequence homology, despite common properties. Since there is a need to develop a computational method for predicting the antibacterial peptides, in the present study, we have applied the concept of Chou's pseudo-amino acid composition (PseAAC) and machine learning methods for their classification. Our results demonstrate that using the concept of PseAAC and applying Support Vector Machine (SVM) can provide useful information to predict antibacterial peptides.