Jacob D. Galson

FAbCon is a generative antibody-specific language model that improves antigen binding prediction and antibody design with increasing model size.

This paper enhances antibody language models by integrating structural information through a contrastive learning approach, improving binding prediction accuracy and data efficiency.

This paper introduces AntiBERTa, a language model for BCR sequences, showing it can predict paratope positions better than existing tools.

AbDiver enables comparison of therapeutic antibody sequences to natural antibody diversity, aiding in rational design by identifying mutation patterns and relevant sequence matches.

The paper introduces a method to identify novel cross-clonotype antibodies by clustering based on predicted paratope features, validated on a Pertussis toxoid dataset.

This paper introduces a Bayesian model to identify vaccine-specific BCR sequences by analyzing B cell receptor repertoires across time and individuals, achieving 69% sensitivity.