Antibodies constitute the core of our immune system, and help neutralize pathogens. Designing new antibodies subsumes some key challenges pertaining to multiple tasks, including protein folding (sequence to structure), inverse folding (structure to sequence), and docking (binding). This work surmounts these challenges by bringing together, and building on, some prominent recent advances in deep learning (graph neural networks, neural ODEs/PDEs, equivariant/invariant models etc.) establishing a new state of the art.
In one of our ICML 2023 papers, we show how generative AI can help design new antibodies from scratch given information about the specific antigens (such as virus, bacteria).
