Reposted by Sarah Alamdari
Our work led by Talal Widatalla on aligning protein generative models to experimental fitness with ProteinDPO is now published in @natmethods.nature.com!
New in the published paper includes stabilizing mutations to H5 hemagglutinin, a component of flu vaccines.
www.nature.com/articles/s41...
nature.com
Aligning protein-generative models to experimental fitness with ProteinDPO - Nature Methods
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 mode...