Sequence-Only Prediction of Binding Affinity Changes: A Robust and Interpretable Model for Antibody Engineering

2025/05/14 by Chen Liu, Mingchen Li, Liu, Chen +9 · 1 voice · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Medicine · #FOS: Biological sciences #FOS: Computer and information sciences #Glycosylation and Glycoproteins Research #Machine Learning (cs.LG) #Monoclonal and Polyclonal Antibodies Research #Protein purification and stability #Quantitative Methods (q-bio.QM) #cs.LG #q-bio.QM

paper · pdf · doi:10.48550/arxiv.2505.20301

openalex publication_date 2025/05/14 · arxiv published 2025/05/14 · arxiv updated 2025/05/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A pivotal area of research in antibody engineering is to find effective modifications that enhance antibody-antigen binding affinity. Traditional wet-lab experiments assess mutants in a costly and time-consuming manner. Emerging deep learning solutions offer an alternative by modeling antibody structures to predict binding affinity changes. However, they heavily depend on high-quality complex structures, which are frequently unavailable in practice. Therefore, we propose ProtAttBA, a deep learning model that predicts binding affinity changes based solely on the sequence information of antibody-antigen complexes. ProtAttBA employs a pre-training phase to learn protein sequence patterns, following a supervised training phase using labeled antibody-antigen complex data to train a cross-attention-based regressor for predicting binding affinity changes. We evaluated ProtAttBA on three open benchmarks under different conditions. Compared to both sequence- and structure-based prediction methods, our approach achieves competitive performance, demonstrating notable robustness, especially with uncertain complex structures. Notably, our method possesses interpretability from the attention mechanism. We show that the learned attention scores can identify critical residues with impacts on binding affinity. This work introduces a rapid and cost-effective computational tool for antibody engineering, with the potential to accelerate the development of novel therapeutic antibodies.

Citations

• Protein engineering in the deep learning era
• Retrieval-Enhanced Mutation Mastery: Augmenting Zero-Shot Prediction of Protein Language Model
• Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection
• ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
• Enhancing predictions of protein stability changes induced by single mutations using MSA-based language models
• Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language Models
• Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling
• Evolutionary-scale prediction of atomic-level protein structure with a language model
• Learning inverse folding from millions of predicted structures
• Are Transformers More Robust Than CNNs?
• Highly accurate protein structure prediction with AlphaFold
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
• ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning
• End-to-End Learning on 3D Protein Structure for Interface Prediction

Cited by

• DuaDeep-SeqAffinity: Dual-Stream Deep Learning Framework for Sequence-Only Antigen-Antibody Affinity Prediction
• Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding

Discussions

• Sequence-Only Prediction of Binding Affinity Changes: A Robust and Interpretable Model for Antibody Engineering arxiv.org/abs/2505.2... --- #proteomics #prot-preprint [bsky, 0 points, 0 comments]

Related

• AffinityFlow: Guided Flows for Antibody Affinity Maturation
• Sequence-based deep learning antibody design for in silico antibody affinity maturation
• Active learning for affinity prediction of antibodies
• ANTIPASTI: interpretable prediction of antibody binding affinity exploiting Normal Modes and Deep Learning
• DuaDeep-SeqAffinity: Dual-Stream Deep Learning Framework for Sequence-Only Antigen-Antibody Affinity Prediction