Antibiotic discovery with artificial intelligence for the treatment of Acinetobacter baumannii infections

Abstract The global challenges presented by multidrug-resistant Acinetobacter baumannii infections have stimulated the development of new treatment strategies. We reported that OmpW is a potential therapeutic target in Acinetobacter baumannii. Here, a library of 11,648 natural compounds was subjected to a primary screening using QSAR models generated from a ChEMBL dataset with >7,000 compounds with their reported MIC values against A. baumannii followed by a structure-based virtual screening against OmpW. In silico ADME evaluation was conducted to assess the drug-likeness of these compounds. The ten highest-ranking compounds were found to bind with an energy score ranging from -7.8 to -7.0 kcal/mol where most of them belonged to curcuminoids. To validate these findings, one lead compound exhibiting promising binding stability as well as favourable pharmacokinetics properties, namely demethoxycurcumin was tested against a panel of A. baumannii strains to determine its antibacterial activity using microdilution and time-kill curve assays. To validate whether the compound binds to the selected target, an OmpW-deficient mutant was also studied and compared to the wild-type. Our results demonstrate that demethoxycurcumin in monotherapy and in combination with colistin is active against all A. baumannii strains. Moreover, an increased bacterial growth was observed in the OmpW-deficient mutant suggesting the importance of OmpW for the compound to exhibit its antibacterial activity. Finally, the compound was found to significantly reduce the interaction of A. baumannii with host cells suggesting its anti-virulence properties. Collectively, this study demonstrates artificial intelligence as a promising strategy for the discovery of curcuminoids as antimicrobial agents for combating A. baumannii infections.