A contextualised protein language model reveals the functional syntax of bacterial evolution
Maciej Wiatrak, David C. Abelson, Roman Mikhaylenko, Ramon Viñas Torné, Maria Ntemourtsidou, Adam M. Dinan, Divya Arora, Samuel Horsfield, John A. Lees, Maria Brbić, Aaron Weimann, R. Andres Floto
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.
bioRxiv · Jul 20, 2025 · PreprintMicrobiology✦ In-depth digest