Antibiotic Resistance in Bacteria

This paper introduces deepARG, a deep learning method for predicting antibiotic resistance genes from metagenomic data, achieving high precision and recall over traditional methods.

This study develops an XGBoost-based machine learning model to predict minimum inhibitory concentrations for 20 antibiotics in Klebsiella pneumoniae using whole genome sequencing data, achieving 92% overall accuracy.

This study combines real-time genomic and epidemiological analysis to identify and manage KPC-producing Enterobacteriaceae outbreaks, revealing transmission networks and informing infection control.

This study analyzes the genomic features of 141 commensal E. coli from healthy pigs, identifying antimicrobial resistance genes, class 1 integrons, and IS26 elements associated with zoonotic potential.

MetaCherchant analyzes metagenomic data to reconstruct the genomic environment of antibiotic resistance genes, revealing potential transmission mechanisms in gut microbiota.

ARIBA rapidly identifies antimicrobial resistance genes and SNPs from sequencing reads, outperforming existing tools on bacterial datasets.

This study reconstructs genomes of drug-resistant bacteria from human faeces using metagenomic sequencing and self-organising maps, demonstrating the potential for culture-independent pathogen analysis.

The paper identifies 134 distinct Klebsiella capsule synthesis loci from whole-genome data, introduces a novel software tool for locus identification, and proposes a standardized nomenclature.