<![CDATA[Introduction: Antimicrobial resistance (AMR) remains a critical global issue. By 2050, it is projected to cause around 10 million deaths if current trends persist. Traditional antimicrobial discovery struggles to keep up with rapidly evolving resistance due to its lengthy process, high cost, and high failure rate. Developing a single drug can take over a decade of research and cost millions of dollars. These challenges demand more efficient approaches, with artificial intelligence (AI) offering a promising path to accelerate and improve antibiotic development. Methods: GoogleScholar, PubMed, ScienceDirect, and Scopus were systematically searched following the PRISMA 2020, yielding 13 eligible studies. All included in vitro validation, and four extended to in vivo investigations. Risk of bias was evaluated using the QUIN (in vitro) and the SYRCLE (in vivo) tools. Discussion: Across studies, AI supported multiple stages of antibiotic discovery, including target identification, lead compound optimization, also enhancement of pre-clinical testing. In target identification, two studies revealed novel antibacterial targets distinct from classical pathways. During lead optimization, applied in most studies, AI-generated compounds demonstrated strong antimicrobial activity and low MIC values against broad-spectrum and multi-drug resistant bacteria. Four in vivo studies further showed that these de novo antibiotics exhibited superior antimicrobial efficacy to current standard therapies. Finally, in preclinical testing, AI models accurately predicted cytotoxicity and hemolysis, later confirmed experimentally. Conclusion: AI has markedly improved efficiency and accuracy in antibiotic development. While continued model refinement, validation, and ethical oversight remain crucial, AI-integrated pharmaceutical research indicates growing maturity and transformative potential.]]>
Copyrights © 2025
