Discovery of antibiotics in the archaeome using deep learning

Area of Science:

• Microbiology
• Biotechnology
• Drug Discovery

Background:

• Antimicrobial resistance (AMR) is a critical global health threat, necessitating the development of new antibiotics.
• Archaea, a distinct domain of life, represent an underexplored source for novel antimicrobial compounds.

Purpose of the Study:

• To systematically explore the archaeome for novel antibiotic candidates using deep learning.
• To identify and characterize new molecules with potential antimicrobial activity.

Main Methods:

• Deep learning analysis of 233 archaeal proteomes.
• Identification and synthesis of potential antimicrobial peptides (archaeasins).
• In vitro and in vivo testing of synthesized compounds.

Main Results:

• 12,623 potential antimicrobial molecules (archaeasins) were identified.
• 80 archaeasins were synthesized, with 93% showing in vitro antimicrobial activity.
• Archaeasin-73 demonstrated significant in vivo efficacy in mouse models, comparable to polymyxin B.

Conclusions:

• Archaea are a valuable reservoir for discovering next-generation antibiotics.
• Archaeasins possess unique features and potent antimicrobial properties.
• Deep learning is an effective tool for exploring the archaeome for drug discovery.