Poster
in
Workshop: Accessible and Efficient Foundation Models for Biological Discovery
A generative foundation model for antibody sequence understanding
Justin Barton · Aretas Gaspariunas · David Yadin · Jorge Dias · Francesca Nice · Danielle Minns · Olivia Snudden · Chelsea Povall · Sara Tomas · Harry Dobson · James Farmery · Jinwoo Leem · Jacob Galson
Keywords: [ Generative Models ] [ foundation models ] [ antigen binding prediction ] [ de novo design ] [ antibodies ]
Here we introduce FAbCon, a generative antibody-specific language model comprising 2.4 billion parameters. A commonly accepted wisdom in developing large language models is that increasing model scale will translate to higher performance on downstream tasks. Starting from a 144-million parameter setup, we show that progressively larger models achieve greater accuracy in predicting antigen binding and can also be used to design new antibodies with good predicted developability potential.