Improving Antibody Design with Force-Guided Sampling in Diffusion Models

TL;DR

This paper introduces DiffForce, a novel diffusion model that incorporates force-field energy feedback to improve antibody CDR design, resulting in more accurate and energetically favorable antibody structures.

Contribution

The paper presents a new method integrating force-guided sampling into diffusion models for antibody design, addressing dataset limitations and improving structure quality.

Findings

Guides diffusion models to generate lower-energy antibody structures.

Enhances both structural accuracy and sequence quality of designed antibodies.

Demonstrates improved generalization to out-of-distribution interfaces.

Abstract

Antibodies, crucial for immune defense, primarily rely on complementarity-determining regions (CDRs) to bind and neutralize antigens, such as viruses. The design of these CDRs determines the antibody's affinity and specificity towards its target. Generative models, particularly denoising diffusion probabilistic models (DDPMs), have shown potential to advance the structure-based design of CDR regions. However, only a limited dataset of bound antibody-antigen structures is available, and generalization to out-of-distribution interfaces remains a challenge. Physics based force-fields, which approximate atomic interactions, offer a coarse but universal source of information to better mold designs to target interfaces. Integrating this foundational information into diffusion models is, therefore, highly desirable. Here, we propose a novel approach to enhance the sampling process of diffusion models by integrating force field energy-based feedback. Our model, DiffForce, employs forces to guide the diffusion sampling process, effectively blending the two distributions. Through extensive experiments, we demonstrate that our method guides the model to sample CDRs with lower energy, enhancing both the structure and sequence of the generated antibodies.