Computer-Aided Discovery of Synergistic Drug-Nanoparticle Combinations for Enhanced Antimicrobial Activity

Area of Science:

• Biotechnology
• Infectious Diseases
• Materials Science

Background:

• Antibiotic resistance is a major global health threat due to limited new drug discovery and evolving resistance mechanisms.
• Combination therapies involving antibiotics and nanoparticles (NPs) show promise against multidrug-resistant (MDR) bacteria.

Purpose of the Study:

• To develop an innovative machine learning (ML)-reinforced genetic algorithm (GA) approach for identifying synergistic drug-NP combinations with enhanced antimicrobial activity.
• To predict the minimal concentration (MC) and zone of inhibition (ZOI) for drug-NP combinations.

Main Methods:

• Compiled datasets to train CatBoost regression models for predicting MC and ZOI, achieving R² scores of 0.86 and 0.77.
• Employed an ML-reinforced GA to identify synergistic antimicrobial NPs.
• Validated the approach by reproducing previous experimental findings.

Main Results:

• The ML-GA approach successfully identified synergistic drug-NP combinations.
• Gold nanoparticles (Au NPs) demonstrated high synergy with chloramphenicol.
• The combination achieved a minimum bactericidal concentration (MBC) of 71.74 ng/mL against Salmonella typhimurium with a fractional inhibitory concentration index of 6.23 × 10⁻³.

Conclusions:

• The study presents an effective strategy for discovering synergistic antibiotic-nanoparticle combinations.
• This approach offers a promising method for combating drug-resistant pathogens.
• The findings advance targeted antimicrobial therapies against resistant infections.