AI Insight
Researchers developed AbAffinity, a machine learning model that predicts how strongly antibodies bind to antigens using only amino acid sequences, without requiring 3D structural information. The model maintains separate computational pathways for heavy chains, light chains, and antigens, achieving superior performance compared to existing sequence-based methods across multiple benchmark datasets. The approach successfully identifies key binding regions and provides an efficient tool for screening antibody candidates when structural data is unavailable.
Why it matters
This tool could accelerate early-stage antibody drug discovery by enabling rapid screening of large antibody libraries before expensive structural determination or experimental binding assays. The model's ability to work with sequences alone and identify critical binding residues makes it particularly valuable for therapeutic development and understanding immune responses.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Motivation: Antibody-antigen affinity determines which antibodies advance in therapeutic discovery, repertoire analysis and affinity maturation, but experimental measurements are sparse relative to the scale of sequence libraries. Structure-based predictors can exploit interface geometry when reliable complexes are available, yet early discovery often requires ranking many heavy-light chain pairs against antigens for which no complex structure exists. Existing sequence-based models are scalable, but frequently compress heavy and light chains into a single antibody representation or concatenate antibody and antigen features obscuring the chain-specific and epitope-specific signals that drive binding. Results: We present AbAffinity, a sequence-only chain-aware three-stream architecture that maintains heavy chain, light chain and antigen as distinct streams. It integrates frozen ESM-2 embeddings with heavy-chain CDR-focused pooling, heavy-light self-attention, adaptive fusion gating and gated cross-attention, training only a compact interaction module. On the SAAINT-DB benchmark, AbAffinity achieves strong predictive performance under ten-fold cross-validation and maintains robust accuracy on novel antigens. It consistently outperforms recent sequence-based models across external benchmarks including SAbDab, AB-Bind and SKEMPI 2.0. Ablation studies highlight the contributions of chain-specific representations, CDR-focused pooling and the gated interaction pathway. Integrated Gradients attributions recover known paratope and epitope residues at structurally validated interfaces. AbAffinity provides a lightweight, explainable sequence-first framework for antibody triage and prioritisation when structural information is limited or unavailable.
Source: Antibody-Antigen Affinity Prediction with Chain-Aware Protein Language Modeling