AUTHOR=Khabaz Hosein , Rahimi-Nasrabadi Mehdi , Keihan Amir Homayoun 

TITLE=Hierarchical machine learning model predicts antimicrobial peptide activity against Staphylococcus aureus

JOURNAL=Frontiers in Molecular Biosciences

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2023.1238509

DOI=10.3389/fmolb.2023.1238509

ISSN=2296-889X

ABSTRACT=Staphylococcus aureus is a dangerous pathogen which causes a vast selection of infections. Antimicrobial peptides have been demonstrated as new hope for developing antibiotic agents against multi-drug resistance bacteria such as Staphylococcus aureus. Yet, most of studies on developing classification tools on antimicrobial peptides activities doesn't focus on any specific specie and therefore their applications are limited.Here by using an up-to-date dataset we have developed a hierarchical machine learning model for classifying peptides with antimicrobial activity against Staphylococcus aurous. The first-level model to classifies peptides into AMPs and non-AMPs. The second-level model to classifies AMPs into those active against Staphylococcus aurous and those not active against this specie.Results: Results from both classifiers demonstrate the effectiveness of the hierarchical approach. A comprehensive set of physicochemical and linguistic-based features have been used and after feature selection steps, only some physicochemical properties were selected. The final model showed a f1 score of 0.80, recall of 0.86, balanced accuracy of 0.80 and specificity of 0.73 on test set.The susceptibility to a single AMP is highly varied among different target species. Therefore, it can't be concluded that AMP candidates suggested by AMP/non-AMP classifiers are able to show suitable activity against a specific specie. Here we addressed this issue by creating a hierarchical machine learning model which can be used in practical applications for extracting potential antimicrobial peptides against Staphylococcus aureus from peptide libraries.