{
  "abstract": "Motivation: Accurate prediction of antibody-antigen binding affinity is fundamental to therapeutic design and the rapid response to evolving pathogens. However, current computational approaches predominantly formulate this as a point-wise regression task. This paradigm struggles to discriminate subtle affinity differences among highly homologous variants and lacks the global context necessary to effectively prioritize top-tier candidates. Furthermore, the field is severely constrained by label sparsity. Although sequence data is abundant, experimentally verified affinities are scarce, leaving a massive pool of unverified antibody-antigen structural interactions unexploited by standard supervised paradigms.\n\nResults: We propose AbLWR (Antibody-antigen binding affinity Listwise Ranking), a novel framework that reformulates the conventional affinity regression task as a listwise ranking problem to directly optimize candidate prioritization. To mitigate label sparsity, AbLWR incorporates a Positive-Unlabeled (PU) learning mechanism, leveraging a dual-level contrastive objective and meta-optimized label refinement to distill robust structural representations from vast unlabeled data. To accommodate antigenic variation, we employ a homologous antigen sampling strategy coupled with a Multi-Head Self-Attention (MHSA) module, which explicitly models inter-sample dependencies within training lists to capture subtle affinity nuances. Extensive evaluations demonstrate that AbLWR significantly outperforms state-of-the-art sequence-, structure-, and complex-based baselines. It improves the Full Rank Accuracy (FRA) by approximately 8% compared to the strongest baseline in randomized cross-validation, and exhibits strong robustness in out-of-distribution scenarios involving distinct antigen and antibody clusters. Case studies on Influenza Viruses and Human Interleukin-33 further validate its practical utility. Specifically, AbLWR successfully tracks affinity drops caused by antigenic drift and immediately captures optimal binders in simulated wet-lab screening.\n\nAvailability: Source code and datasets are freely available at https://github.com/Josie-xufan/AbLWR.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "name": "Fan Xu",
      "orcid": "0000-0002-3530-2661"
    },
    {
      "name": "Zhi-An Huang",
      "orcid": "0000-0001-9974-148X"
    },
    {
      "name": "Haohuai He",
      "orcid": "0000-0003-3831-3996"
    },
    {
      "name": "Yidong Song",
      "orcid": "0000-0003-2872-3086"
    },
    {
      "name": "Wei Liu"
    },
    {
      "name": "Dongxu Zhang",
      "orcid": "0000-0002-8200-494X"
    },
    {
      "name": "Yao Hu",
      "orcid": "0000-0002-5477-8753"
    },
    {
      "name": "Jibin Wu",
      "orcid": "0000-0003-0135-4188"
    },
    {
      "name": "Kay Chen Tan",
      "orcid": "0000-0002-6802-2463"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cfb7bybtggb8a.bib",
  "cited_by": 1,
  "doi": "10.1093/bioinformatics/btag793",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13728850/",
  "id": "cfb7bybtggb8a",
  "issns": [
    "1367-4803",
    "1367-4811"
  ],
  "landing_url": "https://doi.org/10.1093/bioinformatics/btag793",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "AcademicSubjects/SCI01060"
    ],
    [
      "heading",
      "Data and Text Mining"
    ],
    [
      "heading",
      "Original Paper"
    ],
    [
      "openalex",
      "1312|vaccines and immunoinformatics approaches"
    ]
  ],
  "openalex": "W7154361006",
  "pdf_url": "https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btag793/72475348/btag793.pdf",
  "pmcid": "PMC13728850",
  "pmid": "42925410",
  "published": "2026-10-23",
  "publisher": "Oxford University Press",
  "ris": "https://research.draconitic.com/paper/cfb7bybtggb8a.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T12:21:44Z",
      "native_id": "PMC13728850",
      "source": "pmc",
      "url": "https://doi.org/10.1093/bioinformatics/btag793"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|vaccines and immunoinformatics approaches",
      "subfield": "molecular-biology"
    }
  ],
  "title": "AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning",
  "title_text": "AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T12:21:44Z",
  "url": "https://research.draconitic.com/paper/cfb7bybtggb8a",
  "venue": "Bioinformatics",
  "versions": []
}