In a new Nature Communications article, researchers describe a genomic language model (gLM) capable of predicting protein co-regulation and function. The gLM, which was trained on millions of metagenomic scaffolds, has learned to interpret the language of genes, revealing the intricate dance of protein regulation and enzymatic functions. This approach is a leap forward in our understanding of the genomic blueprint and its regulatory networks.

CITATION

Hwang, Y., Cornman, A.L., Kellogg, E.H. et al. Genomic language model predicts protein co-regulation and function. Nat Commun 15, 2880 (2024). https://doi.org/10.1038/s41467-024-46947-9