The emergence of new infection and drug resistance has become one of the greatest threats to global health, demanding radical innovation in our research and groundbreaking therapeutic strategies and diagnostic. The integration of lab results and AI methodologies has been proposed as highly beneficial towards the identification of microbes and of new antimicrobials in a broad spectrum of biological and chemical sources. Also, AI models can help elucidate the susceptibility endpoint parameters of the peptides towards specific pathogens.
Ultimately, AI-informed pipelines aim to identify candidates with enhanced properties exhibiting relevant activities and minimal toxicity to human cells.

This research topic focuses on the application of artificial intelligence to combat antimicrobial resistance and deepen the knowledge of the biology of infections. We seek research and reviews that present tangible, AI+wet lab fused solutions in the fight against superbugs: from the algorithmic design and discovery of innovative antimicrobials (such as multifunctional peptides or drug-peptide hybrids) to the optimisation of treatment combinations, reduction of toxicity through computational models and the identification of microbes for diagnostic purposes.

We invite contributions that showcase hybrid workflows integrating in vitro, in vivo and in silico approaches for accelerated, translational antimicrobial pipelines. Research including but not limited to:
• Bioinformatics approaches for screening innovative peptide reservoirs, e.g. peptidomes from extinct organisms and human defensins, microbiome and secretome.
• AI-guided identification and design of new antimicrobial peptides (AMPs) and peptide-drug hybrids, leveraging deep learning and LLMs to mine sequence-function relationships and expand innovative peptide libraries.
• Machine learning-based pathogen identification technology and laboratory automation.
• Optimization of functional drug and peptide properties—such as toxicity, selectivity, and efficacy—using machine learning-driven predictive modeling and multi-objective optimization.
• In silico discovery and prioritization of synergistic combinations (e.g., peptide-antibiotic, peptide-peptide) effective against multi-resistant microbial strains.
• Development and integration of AI-driven pipelines for multi-omics data analysis in the context of infection modelling, therapeutic targeting and diagnostic.
• Automated mining of biomedical literature to predict novel uses of existing compounds against resistant pathogens.

Are you interested in contributing a manuscript to this Research Topic?

Paving AI Routes to Fight Resistant Infections: Fusing Experimental and Computational Efforts