Flash optimization of drug combinations for Acinetobacter baumannii with IDentif.AI-AMR

Area of Science:

• Microbiology
• Infectious Diseases
• Pharmacology

Background:

• Antimicrobial resistance (AMR) is a critical global health concern, particularly with Gram-negative bacteria like Acinetobacter baumannii.
• Acinetobacter baumannii causes nosocomial infections and exhibits resistance to over 90% of standard antimicrobial treatments, leading to high mortality rates.
• Developing novel antimicrobial strategies is challenging due to the rapid evolution of resistance.

Purpose of the Study:

• To establish a sustainable workflow for rapidly designing optimal antimicrobial drug combinations against Acinetobacter baumannii.
• To identify effective drug combinations using the IDentif.AI-AMR platform against clinical isolates of Acinetobacter baumannii.

Main Methods:

• Utilized the IDentif.AI-AMR platform to screen combinations of nine US FDA-approved drugs against four Acinetobacter baumannii clinical isolates.
• Evaluated the inhibitory efficacy and synergy of identified drug combinations.

Main Results:

• IDentif.AI identified ampicillin-sulbactam/cefiderocol and cefiderocol/polymyxin B/rifampicin combinations with high bacterial inhibition (93.89% and 92.23%, respectively).
• Polymyxin B combined with rifampicin demonstrated broad efficacy and strong synergy across all tested isolates.
• These combinations show potential to diversify treatment options for Acinetobacter baumannii infections.

Conclusions:

• IDentif.AI-AMR platform can rapidly identify effective antimicrobial drug combinations against multidrug-resistant Acinetobacter baumannii.
• Identified combinations, particularly polymyxin B/rifampicin, represent promising alternative therapeutic strategies.
• The study highlights the potential of AI-driven approaches to combat antimicrobial resistance.