Talal Widatalla

This study introduces a computational framework for designing antibodies that target multiple antigenic variants, including observed and forecasted ones, and demonstrates its effectiveness against cancer and viral antigens.

This paper demonstrates that in-context learning in the genome language model Evo 2 enables efficient biological sequence design without additional training.

This paper aligns a protein generative model with experimental fitness using Direct Preference Optimization, improving stability prediction and enabling new applications.

Germinal is a generative pipeline that designs functional antibodies with nanomolar binding affinities using minimal experimental testing.

This paper introduces FAMPNN, a method for protein sequence design that explicitly models both amino acid identity and sidechain conformation, achieving state-of-the-art results in sidechain packing and practical design applications.