AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions

TL;DR

AntibodyFlow is a novel 3D flow-based model that designs antibody CDR loops by predicting amino acids conditioned on geometric structures, improving validity and structural accuracy over existing methods.

Contribution

The paper introduces AntibodyFlow, a new 3D flow model that effectively captures the geometry of antibody CDRs for improved design accuracy.

Findings

Up to 16.0% increase in validity rate.

24.3% reduction in RMSD error.

Consistent outperformance over baseline methods.

Abstract

Therapeutic antibodies have been extensively studied in drug discovery and development in the past decades. Antibodies are specialized protective proteins that bind to antigens in a lock-to-key manner. The binding strength/affinity between an antibody and a specific antigen is heavily determined by the complementarity-determining regions (CDRs) on the antibodies. Existing machine learning methods cast in silico development of CDRs as either sequence or 3D graph (with a single chain) generation tasks and have achieved initial success. However, with CDR loops having specific geometry shapes, learning the 3D geometric structures of CDRs remains a challenge. To address this issue, we propose AntibodyFlow, a 3D flow model to design antibody CDR loops. Specifically, AntibodyFlow first constructs the distance matrix, then predicts amino acids conditioned on the distance matrix. Also, AntibodyFlow conducts constraint learning and constrained generation to ensure valid 3D structures. Experimental results indicate that AntibodyFlow outperforms the best baseline consistently with up to 16.0% relative improvement in validity rate and 24.3% relative reduction in geometric graph level error (root mean square deviation, RMSD).