{
  "abstract": "Finite sampling complicates interpretation and comparison of T cell receptor (TCR) repertoires. We introduce BEAM, a probability model for TCR{beta} complementarity-determining region 3 amino-acid sequences that combines local sequence dependence with exact normalisation. Its tractable local structure permits deterministic evaluation of sequence-pattern probabilities and sampling expectations without enumerating or Monte Carlo sampling the sequence domain. A reference built from 38,538 human repertoires links sampling depth to expected sequence recovery, recurrence, overlap and publicness, the number of cohort repertoires containing a sequence. Models built from individual repertoires define distances attributable to sequence lengths and local patterns. BEAM improves held-out sequence prediction over controls matched for length and individual-position frequencies, ranks sequence publicness in an external cohort and matches CD4 and CD8 repertoires across independent studies. BEAM therefore provides a tractable observational probability landscape for depth-aware sampling calculations and interpretable repertoire comparison.",
  "abstract_shown": true,
  "affiliations": [
    "Yale University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "T. Konstantinovsky"
    },
    {
      "affs": [
        0
      ],
      "name": "G. Yaari"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2nb76q95f2z3f.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.15.759459",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759459v1.full",
  "id": "2nb76q95f2z3f",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759459v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "2403|T-cell and B-cell Immunology"
    ]
  ],
  "openalex": "W7223130375",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759459v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2nb76q95f2z3f.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:57Z",
      "native_id": "10.64898/2026.10.15.759459",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759459v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "A computable probability landscape for T cell receptor repertoire sampling and comparison",
  "title_text": "A computable probability landscape for T cell receptor repertoire sampling and comparison",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:57Z",
  "url": "https://research.draconitic.com/paper/2nb76q95f2z3f",
  "venue": "bioRxiv",
  "versions": []
}