What does domain-specific pretraining buy? A 170,000-parameter plant peptide language model against the ESM-2 scaling curve
Kelly L. Vomo-Donfack, Melissa Aberbache, Ali Cantez, Adryel Hoszu, Grégory GINOT, Verónica G. Doblas, Ian Morilla
The paper trains a domain-specific plant peptide language model and compares its performance to generalist models, finding domain pretraining provides significant efficiency gains.
bioRxiv · Oct 20, 2026 · PreprintPlant Biology