LGFeb 14, 2025

AffinityFlow: Guided Flows for Antibody Affinity Maturation

arXiv:2502.10365v23 citationsh-index: 9Has CodeICML
Originality Highly original
AI Analysis

This work addresses a significant problem for researchers and developers in the field of antibody therapeutics, providing an incremental solution for affinity maturation.

The authors tackled the problem of antibody affinity maturation, achieving state-of-the-art performance using their proposed AffinityFlow method. This method enables the generation of diverse protein structures with high binding affinity, but no specific numbers are provided.

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. A key challenge is the lack of labeled data for training both predictors. 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes