AI-Driven Antimicrobial Peptide Discovery: Mining and Generation DOI Creative Commons
Paulina Szymczak,

Wojciech Zarzecki,

Jiejing Wang

et al.

Accounts of Chemical Research, Journal Year: 2025, Volume and Issue: unknown

Published: June 3, 2025

ConspectusThe escalating threat of antimicrobial resistance (AMR) poses a significant global health crisis, potentially surpassing cancer as leading cause death by 2050. Traditional antibiotic discovery methods have not kept pace with the rapidly evolving mechanisms pathogens, highlighting urgent need for novel therapeutic strategies. In this context, peptides (AMPs) represent promising class therapeutics due to their selectivity toward bacteria and slower induction compared classical, small molecule antibiotics. However, designing effective AMPs remains challenging because vast combinatorial sequence space balance efficacy low toxicity. Addressing issue is paramount importance chemists researchers dedicated developing next-generation agents.Artificial intelligence (AI) presents powerful tool revolutionize AMP discovery. By leveraging AI, we can navigate immense more efficiently, identifying optimal properties. This Account explores emerging application AI in discovery, focusing on two primary strategies: mining, generation, well use discriminative valuable toolbox.AMP mining involves scanning biological sequences identify potential AMPs. Discriminative models are then used predict activity toxicity these peptides. approach has successfully identified numerous candidates, which were subsequently validated experimentally, demonstrating design discovery.AMP other hand, creates peptide learning from existing data through generative modeling. optimizes desired properties, such increased reduced toxicity, producing synthetic that surpass naturally occurring ones. Despite risk generating unrealistic sequences, hold promise accelerating highly diverse AMPs.In Account, describe technical challenges advancements AI-based approaches. We discuss integrating various sources role advanced algorithms refining predictions. Additionally, highlight future only expedite process but also uncover unprecedented paving way therapies.In conclusion, synergy between opens new frontiers fight against AMR. harnessing power both safe, offering hope where AMR no longer looming threat. Our paper underscores transformative drug advocating its continued integration into biomedical research.

Language: Английский

Challenges and applications of artificial intelligence in infectious diseases and antimicrobial resistance DOI Creative Commons
Angela Cesaro, Samuel C. Hoffman, Payel Das

et al.

npj Antimicrobials and Resistance, Journal Year: 2025, Volume and Issue: 3(1)

Published: Jan. 7, 2025

Artificial intelligence (AI) has transformed infectious disease control, enhancing rapid diagnosis and antibiotic discovery. While conventional tests delay diagnosis, AI-driven methods like machine learning deep assist in pathogen detection, resistance prediction, drug These tools improve stewardship identify effective compounds such as antimicrobial peptides small molecules. This review explores AI applications diagnostics, therapy, discovery, emphasizing both strengths areas needing improvement.

Language: Английский

Citations

10
AI-Driven Antimicrobial Peptide Discovery: Mining and Generation DOI Creative Commons
Paulina Szymczak,

Wojciech Zarzecki,

Jiejing Wang

et al.

Accounts of Chemical Research, Journal Year: 2025, Volume and Issue: unknown

Published: June 3, 2025

ConspectusThe escalating threat of antimicrobial resistance (AMR) poses a significant global health crisis, potentially surpassing cancer as leading cause death by 2050. Traditional antibiotic discovery methods have not kept pace with the rapidly evolving mechanisms pathogens, highlighting urgent need for novel therapeutic strategies. In this context, peptides (AMPs) represent promising class therapeutics due to their selectivity toward bacteria and slower induction compared classical, small molecule antibiotics. However, designing effective AMPs remains challenging because vast combinatorial sequence space balance efficacy low toxicity. Addressing issue is paramount importance chemists researchers dedicated developing next-generation agents.Artificial intelligence (AI) presents powerful tool revolutionize AMP discovery. By leveraging AI, we can navigate immense more efficiently, identifying optimal properties. This Account explores emerging application AI in discovery, focusing on two primary strategies: mining, generation, well use discriminative valuable toolbox.AMP mining involves scanning biological sequences identify potential AMPs. Discriminative models are then used predict activity toxicity these peptides. approach has successfully identified numerous candidates, which were subsequently validated experimentally, demonstrating design discovery.AMP other hand, creates peptide learning from existing data through generative modeling. optimizes desired properties, such increased reduced toxicity, producing synthetic that surpass naturally occurring ones. Despite risk generating unrealistic sequences, hold promise accelerating highly diverse AMPs.In Account, describe technical challenges advancements AI-based approaches. We discuss integrating various sources role advanced algorithms refining predictions. Additionally, highlight future only expedite process but also uncover unprecedented paving way therapies.In conclusion, synergy between opens new frontiers fight against AMR. harnessing power both safe, offering hope where AMR no longer looming threat. Our paper underscores transformative drug advocating its continued integration into biomedical research.

Language: Английский

Citations

0