Unveiling meropenem resistance and co-resistance patterns in Klebsiella pneumoniae and Acinetobacter baumannii: a global genome analysis using ML/DL and association mining

The increasing prevalence of meropenem-resistant gram-negative bacteria has led to higher treatment failure and mortality rates. The global availability of bacterial WGS data with antimicrobial resistance phenotypes enables large-scale analyses to explore resistance determinants. This study investigated meropenem resistance mechanisms in multidrug-resistant Klebsiella pneumoniae (KP) and Acinetobacter baumannii (AB) isolates using advanced data analytics. We analysed AMR genes and mutations from 2,411 KP and 375 AB isolates. Notable differences were observed in the proportions of genes contributing to the meropenem resistance mechanism categories between KP and AB, including carbapenemases (4% in KP, 23% in AB), antibiotic efflux (30%, 60%), target alteration (23%, 12%), and reduced permeability (18%, 3%). Mutation frequencies also varied, with antibiotic efflux (26%, 67%), target alteration (64%, 5%), and reduced permeability (7%, 15%). Using ML/DL and association mining approaches, we identified key features such as bla_KPC-2, bla_KPC-3, ble_MBL, and aac(6')-Ib9 in KP, and bla_OXA-23, Abau_gyrA_FLO|Ser81Leu, and Abau_OprD_IMP|Asn411Asp in AB. The co-occurrences of AAC genes and gyrA mutation suggest co-resistance to meropenem, aminoglycosides, and fluoroquinolones, while oprD mutations may indicate a shared resistance potential. These results offer additional insights into the complexity of meropenem resistance and its associated factors.