AffinityFlow: Guided Flows for Antibody Affinity Maturation

2025-02-14

AI Summary

This work addresses the challenge of antibody–antigen affinity maturation using only sequence information. We propose the first sequence–structure dual-path collaborative optimization framework. Methodologically: (1) We design an alternating optimization pipeline—first fixing the sequence to guide AlphaFold in generating high-affinity structural conformations, then performing inverse folding to generate mutant sequences, which are subsequently filtered by a bimodal (sequence- and structure-based) affinity predictor; (2) We introduce a co-teaching module that incorporates noisy physical energy terms to enable bidirectional knowledge distillation between sequence and structure predictors; (3) We integrate a flow-matching generative model to enhance conformational sampling diversity. Our framework achieves state-of-the-art performance across multiple benchmark datasets, yielding substantial improvements in predicted binding affinity for generated mutants. The source code will be made publicly available.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Structured Learning
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Antibodies are widely used as therapeutics, but their development requires costly affinity maturation, involving iterative mutations to enhance binding affinity.This paper explores a sequence-only scenario for affinity maturation, using solely antibody and antigen sequences. Recently AlphaFlow wraps AlphaFold within flow matching to generate diverse protein structures, enabling a sequence-conditioned generative model of structure. Building on this, we propose an alternating optimization framework that (1) fixes the sequence to guide structure generation toward high binding affinity using a structure-based affinity predictor, then (2) applies inverse folding to create sequence mutations, refined by a sequence-based affinity predictor for post selection. To address this, we develop a co-teaching module that incorporates valuable information from noisy biophysical energies into predictor refinement. The sequence-based predictor selects consensus samples to teach the structure-based predictor, and vice versa. Our method, AffinityFlow, achieves state-of-the-art performance in affinity maturation experiments. We plan to open-source our code after acceptance.

Problem

• Optimizes antibody affinity maturation via sequence mutations
• Uses co-teaching to refine structure and sequence predictors
• Achieves state-of-the-art in antibody binding enhancement

Innovation

• Alternating optimization framework
• Co-teaching module refinement
• Sequence-based affinity predictor