Bacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methods

Simple item page
dc.citation.firstpage1723en_US
dc.citation.issueNumber6en_US
dc.citation.journalTitleJournal of Chemical Information and Modelingen_US
dc.citation.lastpage1733en_US
dc.citation.volumeNumber63en_US
dc.contributor.authorTeimouri, Hamiden_US
dc.contributor.authorMedvedeva, Angelaen_US
dc.contributor.authorKolomeisky, Anatoly B.en_US
dc.contributor.orgCenter for Theoretical Biological Physicsen_US
dc.date.accessioned2023-05-02T18:37:01Zen_US
dc.date.available2023-05-02T18:37:01Zen_US
dc.date.issued2023en_US
dc.description.abstractThere are several classes of short peptide molecules, known as antimicrobial peptides (AMPs), which are produced during the immune responses of living organisms against various infections. In recent years, substantial progress has been achieved in applying machine-learning methods to predict the activities of AMPs against bacteria. In most investigated cases, however, the outcome is not bacterium-specific since the specific features of bacteria, such as chemical composition and structure of membranes, are not considered. To overcome this problem, we developed a new computational approach that allowed us to train several supervised machine-learning models using a specific set of data associated with peptides targeting E. coli bacteria. LASSO regression and Support Vector Machine techniques have been utilized to select, among more than 1500 physicochemical descriptors, the most important features that can be used to classify a peptide as antimicrobial or ineffective against E. coli. We then performed the classification of active versus inactive AMPs using the Support Vector classifiers, Logistic Regression, and Random Forest methods. This computational study allows us to make recommendations of how to design more efficient antibacterial drug therapies.en_US
dc.identifier.citationTeimouri, Hamid, Medvedeva, Angela and Kolomeisky, Anatoly B.. "Bacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methods." <i>Journal of Chemical Information and Modeling,</i> 63, no. 6 (2023) American Chemical Society: 1723-1733. https://doi.org/10.1021/acs.jcim.2c01551.en_US
dc.identifier.doihttps://doi.org/10.1021/acs.jcim.2c01551en_US
dc.identifier.urihttps://hdl.handle.net/1911/114868en_US
dc.language.isoengen_US
dc.publisherAmerican Chemical Societyen_US
dc.rightsThis is an author's peer-reviewed final manuscript, as accepted by the publisher. The published article is copyrighted by the American Chemical Society.en_US
dc.titleBacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methodsen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpost-printen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
machine_learning_single_bacteria.pdf
Size:
574.56 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Faculty Publications
Chemical and Biomolecular Engineering Publications
Chemistry Publications
Physics and Astronomy Publications