Bryan Naidenov

This paper introduces a gene-language model that generates whole-genome vector representations from bacterial species, achieving state-of-the-art accuracy in antibiotic resistance prediction.

The paper predicts antibiotic resistance in Elizabethkingia using pan-genomic analysis and machine learning, achieving high F1 scores for clindamycin and vancomycin resistance.

The paper uses nanopore sequencing to identify antimicrobial resistance genes in Mannheimia haemolytica strains and validates their resistance phenotypes.