q-bio.QMMay 23, 2025

A Comprehensive Benchmark of Computational Models for Antibody--Antigen Binding Affinity

Authors: Xinyan Zhao, Yi-Ching Tang, Victor J Cantu, Junseok Lee, Adam E Stogsdill, Ibraheem M Hamdi, Ashwin Kumar Ramesh, Zhiqiang An, 

Organizations: McWilliams School of Biomedical Informatics, UTHealth Houston · Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology · Texas Therapeutics Institute, Brown Foundation Institute of Molecular Medicine, UTHealth Houston

Abstract

Computational antibody design requires benchmarks that measure functional binding rather than similarity to natural sequences. Here we present AbBiBench, which treats the antibody--antigen complex as the evaluation unit and harmonizes 216,560 experimental measurements spanning 13 antibodies and 9 antigens. We compare 20 computational approaches without task-specific training or fine-tuning. The analyses show that global structure-conditioned inverse folding yields the strongest and most consistent affinity rankings, whereas antibody-specific fine-tuning does not consistently improve performance. Across models, rankings are more useful for prioritizing likely affinity gains than for excluding weak variants. In a subsequent case study, multi-objective evaluation of model-generated F045-092 CDR-H3 variants for H1N1 binding revealed a trade-off between predicted binding potential and evolutionary sequence plausibility; all 21 selected candidates produced H1-reactive ELISA signals. AbBiBench provides an open framework for developing and evaluating function-aware antibody design methods.

Figures & tables

Explore similar work

CardsList
  1. CHIMERA-Bench: A Benchmark Dataset for Epitope-Specific Antibody Design

    Mar 13, 2026Mansoor Ahmed, Nadeem Taj, Imdad Ullah Khan +2antibody designBenchmark Design

  2. AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking

    Jul 7, 2026Zhiyuan Chen, Jing Hu, Junzhe Wang +4Learning to RankMeta-Learning