AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learning

2026-04-13

AI Summary

This study addresses the challenge of predicting antibody–antigen binding affinity, which is hindered by extremely sparse labels and high antigenic variability. The authors reformulate the problem as a listwise ranking task and propose a novel framework integrating positive–unlabeled learning, context-aware homologous antigen sampling, multi-head self-attention, and meta-optimized label refinement. To capture fine-grained inter-sample relationships, they introduce a dual-level contrastive objective. This approach substantially mitigates label sparsity and enhances generalization to diverse antigens, achieving over a 10% improvement in Precision@1 under random cross-validation. The method demonstrates superior ranking consistency and antibody screening efficiency in case studies on influenza and IL-33.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Metareasoning and Metaheuristics
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Accurate prediction of antibody-antigen binding affinity is fundamental to therapeutic design, yet remains constrained by severe label sparsity and the complexity of antigenic variations. In this paper, we propose AbLWR (Antibody-antigen binding affinity List-Wise Ranking), a novel framework that reformulates the conventional affinity regression task as a listwise ranking problem. To mitigate label sparsity, AbLWR incorporates a PU (Positive-Unlabeled) learning mechanism leveraging a dual-level contrastive objective and meta-optimized label refinement to learn robust representations. Furthermore, we address antigenic variation by employing a homologous antigen sampling strategy where Multi-Head Self-Attention (MHSA) explicitly models inter-sample relationships within training lists to capture subtle affinity nuances. Extensive experiments demonstrate that AbLWR significantly outperforms state-of-the-art baselines, improving the Precision@1 (P@1) by over 10$\%$ in randomized cross-validation experiments. Notably, case studies on Influenza and IL-33 validate its practical utility, demonstrating robust ranking consistency in distinguishing subtle viral mutations and efficiently prioritizing top-tier candidates for wet-lab screening.

Problem

• antibody-antigen binding affinity
• label sparsity
• antigenic variation
• affinity prediction

Innovation

• Listwise Ranking
• Positive-Unlabeled Learning
• Multi-Head Self-Attention
• Antibody-Antigen Binding Affinity
• Homologous Antigen Sampling