Karla M. Castro

This study uses deep learning to design multi-epitope scaffolds mimicking CSP's spatial structure, showing accurate positioning of two epitopes and partial success with the third.

This paper introduces CALM, a model that predicts antibody-antigen binding from sequences using contrastive learning, achieving 7% top-1 retrieval on a test set.

This paper designs small single domain proteins that present three distinct viral epitopes using deep learning, showing improved immunogenicity compared to single-epitope designs.

This study designs stem-epitope mimetics using computational methods to elicit broadly reactive antibodies against influenza viruses.

This paper designs chimeric influenza hemagglutinins that combine antigenic surfaces from different strains to elicit cross-group immunity and neutralize multiple strains.