Computational and AI-enabled Targeting of Microbial Antimicrobial Resistance and Virulence

Antimicrobial resistance (AMR) is weakening the effectiveness of first-line treatments in human and veterinary medicine and increasing the need for new therapeutic strategies. Conventional antimicrobial discovery is slow, costly, and often affected by late-stage failures related to limited in vivo relevance, toxicity, poor cellular uptake, or rapid resistance development. Computational biology and artificial intelligence (AI) can accelerate this process by identifying pathogen vulnerabilities that influence growth, virulence, and transmission, mining microbiome datasets for therapeutic candidates, and predicting how treatments affect microbial communities, hosts, and resistance development.This Research Topic aims to highlight computational and AI/ML approaches for identifying, prioritizing, validating, and evaluating antimicrobial and anti-virulence strategies. We welcome studies integrating genomics, metagenomics, transcriptomics, proteomics, metabolomics, single-cell analysis, systems biology, structure-based methods, and compound-screening approaches. Particular interest will be given to work addressing virulence regulation, quorum sensing, biofilm formation, host–pathogen–microbiome interactions, stress responses, tissue tropism, within-host evolution, and treatment response. Studies linking computational predictions to clinically relevant phenotypes, including cytotoxicity, immune escape, colonization fitness, transmission, persistence, relapse, dysbiosis, loss of colonization resistance, microbiome resilience, and pathogen expansion after therapy, are especially encouraged. Contributions that unite antimicrobial lethality, virulence modulation, microbiome effects, and resistance emergence within a common computational framework are also welcome.To gather further insights into computational and AI-enabled strategies for addressing microbial AMR and virulence, we welcome articles addressing, but not limited to, the following themes: Target identification and prioritization:- AI-guided prioritization of targets based on essentiality, virulence contribution, resistance liability, and microbiome relevance- Integrative omics and systems-biology analyses identifying druggable regulators of quorum sensing, toxin secretion, adhesion, invasion, immune evasion, and inflammation- Computational discovery and validation of anti-virulence strategies that may reduce selection for resistance Microbiome-derived antimicrobial discovery:- AI/ML mining of microbiome datasets for bacteriocins, phage-derived tools, competitive metabolites, biosynthetic gene clusters, and community-derived inhibitory activities- Prediction of antimicrobial or anti-virulence candidates from host-associated and environmental microbiomes Compound discovery and screening:- AI/ML prediction of compounds that inhibit biofilm formation or reduce biofilm-associated tolerance- Structure-based discovery of inhibitors targeting virulence enzymes, secretion systems, and toxin–receptor interactions- AI-assisted identification of synergistic antimicrobial, anti-virulence, phage, and microbiome-directed combinations- Optimization and prediction of antimicrobial potency, selectivity, toxicity, membrane permeability, and intracellular exposure Resistance, efficacy, and microbiome effects:- AI prediction of AMR emergence and spread, including resistome and mobilome dynamics, horizontal gene transfer, plasmids, phages, integrons, and resistance reservoirs- Models predicting antimicrobial efficacy, virulence expression, persistence, relapse, and treatment response in polymicrobial and host–microbiome–pathogen systems- Prediction of off-target effects on commensals, loss of colonization resistance, dysbiosis, pathogen expansion, C. difficile risk, and microbiome recovery or resilience Validation and methodological standards:- Multi-omics and single-cell characterization of persistence, phenotypic heterogeneity, and relapse-associated states- Benchmarking datasets, evaluation metrics, reproducibility standards, and microbiome-aware safety and translational endpoints for AI-based antimicrobial research Topic editors: Dario Fernández Do Porto, Eun-Jeong Yoon, Adrian Gustavo Turjanski, Jielu Yan Source: https://www.frontiersin.org/research-topics/83645/computational-and-ai-enabled-targeting-of-microbial-antimicrobial-resistance-and-virulence