Institute for Protein Design

Removing T-cell Epitopes with Computational Protein Design

May 22, 2014

King, C. et al. PNAS Early Edition (2014)


GFP was chosen for an experimental proof of concept. Shown here is the Rosetta design model for GFP deimmunization. (A) Published coordinates of sfGFP crystal structure. (B) Close-up view of immunodominant epitope. (C) Rosetta deimmunization design of (B). Cyan – design mutations; green – sfGFP; magenta – predicted epitopes.

Baker lab members combine machine learning with computational design to demonstrate immune silencing of protein targets in a recently published PNAS paper entitled “Removing T-cell epitopes with computational protein design”. Proteins represent the fastest-growing class of pharmaceuticals for a diverse range of clinical application. Computational design of new proteins has the potential to create a novel class of therapeutics with tunable biophysical properties. Immune responses, however, can make protein therapeutics ineffective or even dangerous. In this paper, Baker lab researchers describe a general computational protein design method for reducing immunogenicity by eliminating known and predicted T-cell epitopes without disrupting protein structure and function. We show that the method recapitulates previous experimental results on immunogenicity reduction, and we use it to disrupt T-cell epitopes in GFP and Pseudomonas exotoxin A without disrupting function.