Aligning protein-generative models to experimental fitness with ProteinDPO

Abstract

Biological generative models can predict biological functions without task-specific training data but often under-perform specialized models. This is due to a fundamental ‘alignment gap’, where the rules learned during unsupervised training are not related to the function of interest. Here we demonstrate how to provide task-specific information without losing the general knowledge learned during pretraining by using direct preference optimization to align a structure-conditioned protein language model to preferentially generate stable protein sequences. Our aligned model, ProteinDPO, achieves stability prediction competitive to task-specific models and consistently outperforms unsupervised and fine-tuned versions of the model. Notably, ProteinDPO generalizes beyond its training data to enable stabilization and improved binding affinity prediction of large multichain protein complexes. When applied to stabilization of the hemagglutinin trimer, a primary component of influenza vaccines, ~80% of designs achieve increased or similar stability compared with the native hemagglutinin and up to 32 °C improvements from recently emerged mammalian strains. Our results demonstrate how to augment generative models with biophysical information and, more broadly, provide a general framework for the alignment of biological foundation models. This Article demonstrates that direct preference optimization (DPO) can be used to effectively align an unsupervised structure-conditioned language model with biophysical information. The aligned model, ProteinDPO, achieves stability prediction competitive with that of task-specific models and consistently outperforms unsupervised and fine-tuned versions of the model.