Breadth over Depth: Predictor-Agnostic Consensus for Improved Antibody--Antigen Structure Prediction
Antibody–antigen structure prediction commonly relies on sampling a single co-folding predictor deeply and selecting its highest-confidence output using model-specific confidence scores. We introduce AbPoolRank, a predictor-agnostic structural selector that ranks mixed pools using cross-pose agreement, within-source reproducibility and interface geometry, without native confidence, predictor identities or predictor-specific parameters. On 103 cluster-disjoint, post-2021 antibody–antigen complexes from SAbDab2, three structures each from Boltz-2, Promera, Protenix-v2, ESMFold2-Fast and OpenDDE form a 15-structure pool that reaches 58.0% medium-or-better Success@1 (DockQ ≥ 0.49), exceeding confidence-based selection from every individual predictor sampled 100 times (26–52%). Existing ranking methods did not rescue deep single-predictor sampling or surpass our selector on mixed pools, with no method exceeding 51.5% on 100 structures from one co-folder and AbPoolRank matching the strongest single-structure methods while significantly outperforming consensus methods. AbPoolRank trained without one predictor lost at most 3.0 percentage points, and the frozen model accepted full MSA-conditioned ESMFold2, a sixth predictor absent from method development, without retraining or loss of accuracy. Diversification also improved the accuracy–compute frontier, with the 15-structure pool using 1.8-fold less aggregate GPU time than the most accurate single-predictor setting in our compute benchmark and 3.3-fold less than sampling that predictor 100 times. Together, these results show that shallow sampling across complementary co-folders, coupled with a confidence-free selector, provides an accurate and computationally efficient inference strategy for antibody–antigen structure prediction.
Authors
- Abhinav Gupta (ORCID: https://orcid.org/0000-0002-9197-0736)
- Pep Amengual-Rigo (ORCID: https://orcid.org/0000-0002-3115-0349)
- Norbert Furtmann (ORCID: https://orcid.org/0009-0006-8226-7586)
- Bonnie Berger (ORCID: https://orcid.org/0000-0002-2724-7228)
- Varun Ullanat (ORCID: https://orcid.org/0000-0002-1238-7041)
- Bryan D. Bryson (ORCID: https://orcid.org/0000-0003-1716-6712)
- Ruijiang Li (ORCID: https://orcid.org/0000-0003-3521-8926)
Institutions
- Sanofi (France) (FR)
- Massachusetts Institute of Technology (US)
Publication Details
- Journal
- bioRxiv (Cold Spring Harbor Laboratory)
- Published
- 2026-11-19
- DOI
- https://doi.org/10.64898/2026.11.17.767212
- Primary Topic
- Protein Structure and Dynamics
- Type
- preprint