{
  "abstract": "Binding prediction models accelerate therapeutic antibody and TCR discovery, but their performance on new datasets is unpredictable, often leading to low discovery rates. Density-ratio methods (PAPE, M-CBPE) provide label-free performance estimation for binary classification, but their assumptions and aggregate-only outputs limit binding prediction on neoepitopes, antigen variants and chemical scaffolds. Here we present CaliPPer (Calibration and Prediction of Performance), a post-hoc framework pairing a multi-chain Sample-to-Domain Distance (S2DD) with distance-aware Bayesian recalibration, operating at three resolutions: generalisability score, aggregate performance prediction, and per-sample confidence. Across ten models, eight architectures and two immune-receptor domains, CaliPPer attains distance--performance correlations $|r|=0.80\\text{--}0.92$, predicts AUROC/AP/F1 with mean absolute errors $0.008\\text{--}0.070$, and improves AUROC by up to $+0.20$ on unseen epitopes/variants. Applied retrospectively to five published TCR, BCR, MHC--peptide and small-molecule studies, CaliPPer raises true discovery rates in all five (e.g.\\ $0/5 \\to 3/5$ confirmed neoantigens), providing a triage layer between computational prediction and experimental validation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.07258",
  "author_total": 9,
  "authors": [
    {
      "name": "Jian-Qing Zheng"
    },
    {
      "name": "Hantao Lou"
    },
    {
      "name": "Zinan Yin"
    },
    {
      "name": "Sam Farrar"
    },
    {
      "name": "Yuze Zhou"
    },
    {
      "name": "Elie Antoun"
    },
    {
      "name": "Xiangxi Wang"
    },
    {
      "name": "Xuetao Cao"
    },
    {
      "name": "Tao Dong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f9a6h7bhjy9gv.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.07258",
  "fulltext_url": null,
  "id": "f9a6h7bhjy9gv",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.07258",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CE"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1312|vaccines and immunoinformatics approaches"
    ]
  ],
  "openalex": "W7163907271",
  "pdf_url": "https://arxiv.org/pdf/2606.07258",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f9a6h7bhjy9gv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:16Z",
      "native_id": "2606.07258",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.07258"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "CaliPPer: quantifying, predicting and improving AI model performance for binding prediction",
  "title_text": "CaliPPer: quantifying, predicting and improving AI model performance for binding prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:16Z",
  "url": "https://research.draconitic.com/paper/f9a6h7bhjy9gv",
  "venue": "arXiv",
  "versions": []
}