{
  "abstract": "Discovering broadly neutralizing antibodies (bnAbs) from human natural immune repertoires remains a fundamental challenge in immunology, hindered by: the extreme rarity of bnAb, incomplete understanding of their cellular origins across pathogens, and the inability of existing computational tools to generalize across emerging viral threats. Here we present ImmuneAgent, a closed-loop AI system that integrates multimodal reasoning with continual meta-learning and wet-lab feedback to overcome these barriers. Applied to screen the natural BCR repertoires from vaccinated or infected cohorts, the system achieves a ~55% neutralization antibody discovery rate (60 of 110 cloned candidates) and a ~11% bnAb yield (12 of 110), substantially outperforming a state-of-the-art sequence-based neutralization predictor or cofolding models evaluated at the same cloning budget. Five ImmuneAgent-discovered antibodies conferred 100% in vivo protection against lethal influenza challenge, comparable to the clinical-stage therapeutic MEDI8852. The system recovered the cellular and structural determinants of bnAb activity and identified FCRL5+CD27+ atypical memory B cells as a conserved bnAb reservoir and hydrophobic interface enrichment as a cross-viral structural signature, which generalized to unseen antigens, discovering human metapneumovirus (hMPV) cross-neutralizing and human papillomavirus (HPV)-neutralizing antibodies without antigen-specific sorting. These results validate that ImmuneAgent is a generalizable framework for rapid therapeutic antibody discovery against emerging viral threats.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.03160",
  "author_total": 24,
  "authors": [
    {
      "name": "Hantao Lou"
    },
    {
      "name": "Jianqing Zheng"
    },
    {
      "name": "Can Yue"
    },
    {
      "name": "Meihan Zhang"
    },
    {
      "name": "Yuanchao Bao"
    },
    {
      "name": "Yu Chen"
    },
    {
      "name": "Mengting Huang"
    },
    {
      "name": "Yupeng Yang"
    },
    {
      "name": "Qianyu Pan"
    },
    {
      "name": "Nana Fu"
    },
    {
      "name": "Yansong Shi"
    },
    {
      "name": "Hongli Li"
    },
    {
      "name": "Yangyang Chai"
    },
    {
      "name": "Ruyi Chen"
    },
    {
      "name": "Wansheng Li"
    },
    {
      "name": "Zhu Liang"
    },
    {
      "name": "Rongmei Yao"
    },
    {
      "name": "Yuanhan Mo"
    },
    {
      "name": "Lei Wang"
    },
    {
      "name": "Chunmei Wang"
    },
    {
      "name": "Yun Quan"
    },
    {
      "name": "Qiong Zhang"
    },
    {
      "name": "Xiangxi Wang"
    },
    {
      "name": "Xuetao Cao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2tr0tw2e43qg1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.03160",
  "fulltext_url": null,
  "id": "2tr0tw2e43qg1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.03160",
  "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",
      "q-bio.CB"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.03160",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2tr0tw2e43qg1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:50Z",
      "native_id": "2610.03160",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.03160"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    },
    {
      "field": "biology",
      "origin": "arxiv:q-bio.CB",
      "subfield": "cell-biology"
    }
  ],
  "title": "Multimodal reasoning for broadly neutralizing antibody discovery from label-free human B cell repertoires across virus families",
  "title_text": "Multimodal reasoning for broadly neutralizing antibody discovery from label-free human B cell repertoires across virus families",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:50Z",
  "url": "https://research.draconitic.com/paper/2tr0tw2e43qg1",
  "venue": "arXiv",
  "versions": []
}