Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness
Sharrol T. Bachas, Goran Rakocevic, David Spencer, Anand V. Sastry, Robel Gemechu Haile, John M. Sutton, George W. Kasun, Andrew L. Stachyra, Jahir M. Gutierrez, Edriss Yassine, Borka Medjo, Vincent Blay, Christa Kohnert, Jennifer T. Stanton, Alexander Brown, , Roberto Spreafico
Language models trained on high-throughput affinity data predict KD of unseen antibody variants across three orders of magnitude, and a "naturalness" score can be optimised alongside affinity.
bioRxiv · Aug 16, 2022 · PreprintBioinformatics