Alignment with experimental data improves protein generative modeling

Summary

Nature Methods, Published online: 14 August 2026; doi:10.1038/s41592-026-03138-2 Direct preference optimization (DPO) aligns a pretrained protein language model with experimental stability data, yielding ProteinDPO, a model that scores and generates thermostable protein sequences. Applied to H5N1 influenza hemagglutinin, it achieved large improvements in thermal stability of hemagglutinin while preserving antibody recognition.