AbODE: Ab Initio Antibody Design using Conjoined ODEs

TL;DR

AbODE is a novel generative model for antibody design that jointly models amino acid sequences and 3D structures using continuous differential attention, improving upon existing methods in antibody generation.

Contribution

The paper introduces AbODE, a new graph PDE-based generative model that captures interactions within antibodies and with antigens using a single decoding step and continuous differential attention.

Findings

Outperforms existing methods on standard benchmarks

Effectively models antibody-antigen interactions

Utilizes a novel continuous differential attention mechanism

Abstract

Antibodies are Y-shaped proteins that neutralize pathogens and constitute the core of our adaptive immune system. De novo generation of new antibodies that target specific antigens holds the key to accelerating vaccine discovery. However, this co-design of the amino acid sequence and the 3D structure subsumes and accentuates some central challenges from multiple tasks, including protein folding (sequence to structure), inverse folding (structure to sequence), and docking (binding). We strive to surmount these challenges with a new generative model AbODE that extends graph PDEs to accommodate both contextual information and external interactions. Unlike existing approaches, AbODE uses a single round of full-shot decoding and elicits continuous differential attention that encapsulates and evolves with latent interactions within the antibody as well as those involving the antigen. We unravel fundamental connections between AbODE and temporal networks as well as graph-matching networks. The proposed model significantly outperforms existing methods on standard metrics across benchmarks.