Background: Antimicrobial resistance (AMR) among ESKAPE pathogens—Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter spp.—represents a major global health threat and accounts for a substantial proportion of healthcare-associated infections. Their genomic plasticity and adaptive regulatory responses facilitate the rapid emergence and dissemination of resistance and virulence determinants. Artificial intelligence (AI) has emerged as a powerful approach for analyzing large-scale biological datasets and identifying molecular signatures associated with antimicrobial resistance and pathogenicity. Objectives: This review examines AI-driven frameworks for predictive target discovery in ESKAPE pathogens, focusing on approaches that leverage genomic and transcriptomic data and extend toward the integration of additional omics layers within network-based and systems-level modeling frameworks. We discuss how AI methods are evolving beyond phenotypic prediction toward more biologically interpretable inference for prioritizing resistance mechanisms, virulence determinants, and candidate antimicrobial targets. Conclusions and Future Directions: Current AI applications exploit genomic, transcriptomic, and network-level data to prioritize resistance and virulence determinants and to support antimicrobial discovery, including small molecules and antimicrobial peptides. However, integrative multi-layer modeling and comprehensive experimental validation remain limited. Future advances will depend on improved integration of complementary biological data, enhanced model interpretability, and robust translational validation frameworks to enable clinically actionable AI-guided novel pathogen-targeted next-generation diagnostics, therapeutic and stewardship strategies against ESKAPE pathogens.

Background: The fitness costs (FCs) of antimicrobial resistance (AMR) are crucial issues in antimicrobial resistance (AMR) onset, spread, and, consequently, public health. In Staphylococcus aureus, AMR can induce significant FCs due to slow growth, low competitiveness, and virulence. Here, we investigated the genomics and FCs emerging for progressively acquiring daptomycin (DAP) and glycopeptide (GLY) reduced susceptibility in MRSA. Methods: Genomics was carried out using Illumina-MiSeq Whole-genome sequencing and bioinformatics. The biological FCs of isogenic MRSA strain pairs progressively acquiring DAP and GLY-reduced susceptibility, under DAP/GLY mono or combined therapy, were performed by in-vitro independent and competitive mixed growth, phenotypic in-vitro virulence analysis, and in-vivo G. mellonella larvae killing. Results: Genomics evidenced four different extremely resistant high-risk clones, i.e., ST-5 N315 HA-MRSA, ST-398 LA-MRSA, ST-22 USA-100 HA-EMRSA-15, and ST-1 MW2 CA-MRSA. In-vitro fitness assays revealed slow growth, lower competitiveness, and reduced virulence, predominantly in Galleria mellonella killing ability, in DAP-S hGISA, DAP-R GSSA, DAP-R hGISA, and DAP-R GISA strains. Conclusions: The occurrence of glycopeptide and daptomycin reduced susceptibility conferred increasing FCs, paid as a gradual reduction in virulence, competitiveness, and slow growth performance.

Background: Persistence represents a critical evolutionary reservoir for the development of antimicrobial resistance in Acinetobacter baumannii (Ab). Understanding the basal mechanisms that enable this survival strategy is crucial for elucidating how high-risk clones evolve resistance during therapy. Methods: High-dose colistin time-kill assays were performed in ten ST2 clinical colistin-susceptible (COL-S) Carbapenem-Resistant Ab (CRAB) developing in vivo stable and full-colistin resistance to detect persisters. Genomics and basal transcriptomics of chromosomal/plasmid toxin–antitoxin systems (T/As) were performed, as duplicates for each sample, in two ST2 COL-S CRAB to investigate the genomics and basal T/A transcriptomic backgrounds. Results: Phenotypically, all strains showed a persistent subpopulation (~1% survival at 8 h) under 5× COL MIC exposure. Genomics identified 10 type-II and one type-IV T/A systems. Basal transcriptomics revealed active expression patterns mainly of GNAT superfamily T/A systems, with consistently low toxin mRNA levels associated with toxin- or antitoxin-directed asRNAs in chromosomal modules. This architecture defined new dual-combined regulatory models in which asRNAs acted as primary T/A mRNA balance modulators, putatively impacting on the T/A mRNA ratio. Conversely, the plasmid-encoded BrnT/A module showed a highly balanced expression. Conclusions: Our findings revealed, for the first time, the role of the type-II GNAT T/A superfamily as putative molecular switchers via a fine-tuning transcript balance regulation, impacting the transition from a metabolically active cell state to a dormant one in developing colistin persistence and in vivo resistance CRAB.

Background/Objectives: Antimicrobial resistance (AMR), driven by high-risk bacterial pathogens, is a major healthcare threat. This scoping review mapped artificial intelligence/machine learning (AI/ML) and computational approaches integrated with whole-genome sequencing (WGS), genomic surveillance, rapid typing, epidemiological data, or clinical metadata for early warning of AMR outbreak clones. Methods: Following PRISMA-ScR guidance and the Population–Concept–Context (PCC) framework, PubMed/MEDLINE, Scopus, and Web of Science were searched for English-language studies published between 2010 and 2026. Eligible studies addressed AI/ML or computational approaches for AMR outbreak detection, clone surveillance, transmission analysis, or infection prevention and control (IPC). Results: Thirty-eight studies were grouped into five domains: genomic surveillance; rapid typing; resistance, risk-factor, and lineage prediction; transmission reconstruction; and IPC-oriented genomic epidemiology. AI/ML supported automation, isolate prioritization, typing triage, prediction, transmission modelling, and electronic health record (EHR)-linked route identification. Conclusions: AI/ML may enhance WGS-based AMR surveillance, but validation, dataset dependence, heterogeneity, and limited IPC outcome reporting remain key gaps.

Background: Colistin (Col) resistance and heteroresistance in extensively drug-resistant (XDR) Acinetobacter baumannii severely limit therapeutic options. We investigated the activity and mechanism of human albumin nanoparticles (haNPs) as colistin potentiators against genetically characterized clinical isolates. Methods: Sixteen clinical isolates were analyzed. Col MICs were determined by broth microdilution, and heteroresistance by population analysis profiling. Potentiation of Col activity was assessed using both Col-loaded haNPs (Col/haNPs) and free Col co-administered with empty haNPs, alongside the proton motive force (PMF) uncoupler carbonyl cyanide 3-chlorophenylhydrazone (CCCP). Assays included checkerboard synergy (FICI), membrane potential analysis (DiOC₂(3)), intracellular Col quantification (UPLC–MS/MS), zeta potential measurements, transmission electron microscopy (TEM), protein leakage, and ROS detection. Results: Heteroresistance was detected in 9/16 isolates. Col/haNPs reduced Col MICs by 4–64-fold in resistant strains and shifted MICs to ≤2 mg/L in most heteroresistant isolates. Empty haNPs displayed no intrinsic antibacterial activity yet selectively potentiated Col, with strong synergy (FICI down to 0.035). Membrane depolarization and increased intracellular Col accumulation under haNP-treated conditions paralleled the effects of CCCP, indicating that haNPs elicit a CCCP-like functional response. These findings are compatible with perturbation of membrane energetics and possible downstream effects on PMF-dependent transport processes. TEM and surface charge analyses supported direct nanoparticle–envelope interaction and progressive membrane disruption. Conclusions: haNPs enhance Col activity across genetically diverse A. baumannii isolates, with particularly strong effects in heteroresistant strains. The combined effects of PMF modulation, increased intracellular drug availability, and envelope interaction provide a mechanistic rationale for the use of albumin-based nanoparticles, either as Col carriers or in combination with free drug, to overcome Col resistance and heteroresistance.

Background: In Staphylococcus aureus, antimicrobial resistance (AMR) imposes significant fitness costs (FCs), including reduced growth rate, interbacterial competitiveness, and virulence. However, the FC molecular basis remains poorly understood. This study investigated the FC omic basis and compensatory adaptations in high-risk HA-, LA-, and CA-MRSA, acquiring mono- or cross-resistance to second-line daptomycin (DAP) and dalbavancin (DAL), as well as reduced susceptibility (RS) to first-line glycopeptides, i.e., vancomycin and teicoplanin (GLYs, i.e., VAN, TEC), related to the specific mechanism of action (MOA)-related AMR-mechanisms and genomic backgrounds, paying increasing FCs. Methods: The FC omic basis associated with mono- or cross- DAP-/DAL-R and GLY-RS were investigated by integrated omics. This study focused on core-genome essential (EG) and accessory virulence gene (VG) SNPomics and transcriptomics by Illumina MiSeq whole-genome sequencing, RNA-seq, and bioinformatic analysis. Results: Moderate impact nsSNPs were identified in EGs related to vital cellular functions and VGs. Comparative EG transcriptomics revealed differential expressions and key dysregulations—via asRNAs—prevalently affecting the protein synthesis and cell-envelope EG clusters, as well as the VG cluster. Conclusions: Our data, firstly, underlined the EG and VG mutation- and transcription-driven omic-based FC burden and the compensatory adaptations associated with the emergence of mono-DAP-R, cross-DAP-R/hGISA, and DAP-R/DAL-R/GISA, linked to specific MOA-related AMR-mechanisms and genomic backgrounds in high-risk HA-, LA-, and CA-MRSA.