DyAb: sequence-based antibody design and property prediction in a low-data regime
DyAb is a pair-wise representation built on top of a pre-trained protein language model that achieves a Spearman rank correlation of up to 0.85 on binding affinity prediction across monoclonal antibodies targeting three different antigens.
J. Lin, Jennifer L. Hofmann, Andrew Leaver-Fay et al.
· mAbs · 0 citations