Metagenomic sequencing of blood samples from patients with bloodstream infections for antimicrobial resistance prediction

This project includes metagenomic sequencing data from whole blood samples collected from 40 patients with confirmed bloodstream infections. The study aimed to evaluate the performance of machine learning models in predicting antimicrobial resistance (AMR) directly from genomic content, without the need for culturing. DNA was extracted following host depletion and sequenced on the MGI G99 platform. The resulting data were used to reconstruct microbial genomes, identify dominant pathogens, and generate in silico antibiograms. This dataset provides a resource for studying pathogen composition, genomic determinants of AMR, and the development of rapid diagnostics based on clinical metagenomics.