Hans-Christof Gasser

This paper introduces CAPE-Beam, a decoding strategy for ProteinMPNN that reduces CTL immunogenicity risk by limiting designs to kmers not presented to CTLs or subject to central tolerance.

The paper integrates MHC Class I visibility targets into the ProteinMPNN protein design process to reduce immune visibility while preserving structure.

The paper develops a machine learning method to modify protein immune-visibility to CTLs, showing it can alter HIV Nef's visibility while preserving sequence diversity.