The second CAPE paper demonstrates that direct preference optimization (DPO) can be used to fine-tune ProteinMPNN to generate protein designs predicted to be less visible to cytotoxic T lymphocytes, potentially reducing their autoimmunity risk
https://t.co/BZbfC2HiIU
In this paper you can read all about the first steps towards CAPE - a suite of tools for the integration of immune-visibility targets into the computational protein design process
@AlfaroJav In this paper you can read all about the first steps towards CAPE - a suite of tools for the integration of immune-visibility targets into the computational protein design process