Figure 1. Fine-tuning antibody language model on receptor specificity prediction tasks.

(A) Antibody language model-based specificity classifiers for SARS-CoV-2 S protein and influenza hemagglutinin were trained by (B) fine-tuning pre-trained antibody language models on specificity classification tasks, and (C) using supervised support vector machine classifiers on pre-trained model embeddings of BCR sequences. (D) The performance of the classifiers was evaluated on the cross-validation accuracy of receptor specificity prediction and comparison between longitudinal time points of repertoire datasets for SARS-CoV-2 and influenza vaccination.