Maciej Wiatrak

This paper trains species-specific transformer models for bacterial genomic surveillance, showing they can cluster genomes, identify emerging lineages, and predict antibiotic resistance gene uptake.

Trained on over 1.3 million bacterial genomes represented as ordered protein sequences, the transformer foundation model Bacformer predicts protein interactions, operons, essentiality, and phenotypes while generating trait-conditioned synthetic proteomes.

A uniformly processed set of 2,440,377 bacterial and archaeal genomes with search tools and annotations, plus an AI-mined peptide set yielding ATB20, active in a mouse skin infection model.

This study introduces GeneBac, a deep learning model that predicts antibiotic resistance from bacterial genomic sequences, showing accurate MIC prediction and variant effect assessment.