Living Models pairs Gemma 4 E4B with BOTANIC-1 to identify crop mutations

AI lab Living Models has paired Gemma 4 E4B with BOTANIC-1, a genomic language model, to speed up identifying the DNA responsible for climate-resilient crops—a process that traditionally required years of physical breeding.

Under this architecture, Gemma processes the genomic data and feeds filtered candidate sequences to BOTANIC-1, which evaluates evolutionary impact to pinpoint causal mutations. In a recent test, the pipeline identified a target melon yield mutation in an afternoon of computation, ranking it first out of 2,494 candidate possibilities.