Browsing by Author "Medvedeva, Angela"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Bacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methods
    (American Chemical Society, 2023) Teimouri, Hamid; Medvedeva, Angela; Kolomeisky, Anatoly B.; Center for Theoretical Biological Physics
    There 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.
  • Thumbnail Image
    Item
    Cooperativity in Bacterial Membrane Association Controls the Synergistic Activities of Antimicrobial Peptides
    (American Chemical Society, 2022) Nguyen, Thao N.; Teimouri, Hamid; Medvedeva, Angela; Kolomeisky, Anatoly B.; Center for Theoretical Biological Physics
    Antimicrobial peptides (AMPs), or defence peptides, are compounds naturally produced during immune responses of living organisms against bacterial infections that are currently actively considered as promising alternatives to antibiotics. Recent experimental studies uncovered that in many situations, combinations of different AMPs are much more successful in eliminating the bacterial pathogens than single peptide species. However, the microscopic origin of such synergistic activities remains not fully understood. We present and investigate a possible mechanism of synergy between AMPs. It is based on the idea that due to inter-molecular interactions, the presence of an AMP of one type stimulates the association of an AMP of another type, and this accelerates the overall association to the membrane, eventually killing the bacteria. This approach allows us to fully quantify the synergistic activities of AMPs, and it is successfully applied for several experimental systems. It is found that strong cooperativity can be achieved for relatively weak inter-molecular interactions, suggesting that the application of combinations of AMPs can be further rationally optimized to make it a powerful antibacterial treatment.