James Henderson, Yuta Nagano, Martina Milighetti, and Andreas Tiffeau-Mayer
PNAS 121 (42) e2408696121
The specificity of cellular immune responses is determined by the binding of T cell receptors (TCRs) to diverse ligands, yet due to their vast diversity, most TCRs lack experimentally validated binding partners. To overcome this gap requires understanding the recognition code linking receptors and ligands. Here, we introduce an information theoretic approach to rank TCR features by their relevance to predicting specificity and bound how accurately T cell specificity can be predicted from partial information. By identifying informative features, our work provides a rational basis for prioritizing matches in TCR databases and for developing machine learning models to predict TCR–ligand interactions.
Read the full article at: www.pnas.org
Complexity Digest 