Artificial intelligence-driven antimicrobial peptide discovery

TL;DR

This paper reviews how artificial intelligence techniques are transforming antimicrobial peptide discovery by enabling the prediction, generation, and optimization of novel peptides to combat antimicrobial resistance.

Contribution

It provides a comprehensive overview of recent AI methods for AMP discovery, emphasizing discrimination and generation approaches and their potential for targeted peptide design.

Findings

AI enables accurate prediction of peptide activity and toxicity.

Generative models facilitate de novo and analogue peptide creation.

Controlled generation techniques improve peptide property optimization.

Abstract

Antimicrobial peptides (AMPs) emerge as promising agents against antimicrobial resistance, providing an alternative to conventional antibiotics. Artificial intelligence (AI) revolutionized AMP discovery through both discrimination and generation approaches. The discriminators aid the identification of promising candidates by predicting key peptide properties such as activity and toxicity, while the generators learn the distribution over peptides and enable sampling novel AMP candidates, either de novo, or as analogues of a prototype peptide. Moreover, the controlled generation of AMPs with desired properties is achieved by discriminator-guided filtering, positive-only learning, latent space sampling, as well as conditional and optimized generation. Here we review recent achievements in AI-driven AMP discovery, highlighting the most exciting directions.