Maria Francesca Abbate

PEPE efficiently extracts multimodal protein embeddings from language models, enabling scalable and memory-efficient generation of large embedding datasets for downstream biological tasks.

The paper develops MS-BCR-DB, a unified BCR repertoire database for MS, identifying disease-associated features and shared clonotypes across patients.

The paper quantitatively maps antigen specificity in immune repertoire embedding spaces, showing distinct regions for different antigen-specific sequences.

This study presents a computational method to identify antigen-specific BCRs from immune repertoires using sequence similarity and validates it with human data post-vaccination and infection.