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

Project Page [ OpenReview]

Abstract

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.

Chat is not available.