AUTHOR=Li Xuefei , Lin Jingxia , Hu Yongfei , Zhou Jiajian 

TITLE=PARMAP: A Pan-Genome-Based Computational Framework for Predicting Antimicrobial Resistance

JOURNAL=Frontiers in Microbiology

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2020.578795

DOI=10.3389/fmicb.2020.578795

ISSN=1664-302X

ABSTRACT=Antimicrobial resistance (AMR) has emerged as one of the most urgent global threats to public health. Accurate detection of AMR phenotypes is critical for reducing the spread of antimicrobial-resistant strains. Here, we developed PARMAP to predict AMR phenotypes and identify AMR associated genetic alterations based on the pan-genome of a bacterial species by utilizing machine learning algorithms. PARMAP accurately predicted AMR in Neisseria gonorrhoeae by integrative analysis of the pan-genome of 1597 strains. Furthermore, PARMAP analysis revealed diverse AMR mechanisms in Neisseria gonorrhoeae with resistant of ciprofloxacin. It identified 328 genetic alterations associated with 23 known AMR genes and discovered lots of new AMR associated genetic alterations. Additionally, PARMAP accurately predicted AMR in Mycobacterium tuberculosis and Escherichia coli, showing the robustness of our method. These results demonstrated that PARMAP accurately predicts antibiotic resistance of a strain population and prioritizes genetic alterations associated with AMR using whole-genome sequences; thus, it will be widely used in mechanistic studies of AMR in other human pathogens.