基因组测序和人工智能在细菌耐药研究领域的应用进展OA

With the rapid global spread of antimicrobial-resistant bacteria,the swift identification,tracking,and risk assessment of antimicrobial resistance genes(ARGs)have become priorities in public health and biosafety.Traditional resistance detection relies on culture-based and phenotypic assays,which are time-consuming and insufficient for fully characterizing the diversity of ARGs and their distribution and transmission across ecological niches.In recent years,the rapid advancement of genomics,particularly whole-genome sequencing(WGS)and metagenomic next-generation sequencing(mNGS),has provided unique micro-level insights into resistance mechanisms and ARGs dissemination.Meanwhile,the integration of artificial intelligence(AI)has offered powerful new tools for analyzing large-scale genomic data and predicting resistance phenotypes,driving the development of intelligent models in antimicrobial resistance research.This review summarizes recent progress in applying genomic sequencing and AI to antimicrobial resistance studies,outlines their fundamental principles and key technological pathways,and highlights applications in ARGs identification,functional prediction,and transmission risk assessment.By integrating machine learning with multi-omics data analysis,researchers can more accurately identify ARGs and gain deeper understanding of their ecological distribution and transmission patterns,offering critical methodological references and research insights.The deep integration of genomic sequencing and AI is propelling antimicrobial resistance research into a new era characterized by data-driven approaches and intelligent decision-making.In the future,this synergistic model is expected to play a key role in resistance surveillance,transmission interruption,and precision interventions,providing robust scientific support for achieving the goals of"One Health.".