{
  "abstract": "The completion of telomere-to-telomere (T2T) human genomes has expanded the accessible landscape of human genetic variation, yet benchmark resources remain limited to conventional high-confidence regions defined by existing reference frameworks. Here, we generated a near-perfect diploid T2T genome (T2T-LIN) from a Chinese individual and established assembly-based truth sets by comparison with T2T-YAO, an ancestry-matched near-perfect T2T reference genome. The benchmark showed a heterozygous/homozygous SNV ratio of ~2, consistent with expectations under Hardy-Weinberg equilibrium, and enabled genome-wide evaluation of reference-dependent biases. We found that reference choice substantially influences genome interpretation: ancestry-matched linear T2T references provided the most faithful representation of individual genomic variation and enabled more accurate genome reconstruction than unmatched linear, diploid and graph-based references. Benchmarking previously inaccessible repetitive and structurally complex regions revealed substantial limitations of current variant callers that were masked by conventional metrics. The T2T-LIN and YAO-LIN benchmarks establish a T2T-era framework for evaluating reference-dependent genome interpretation and variant discovery across nearly the complete human genome.",
  "abstract_shown": true,
  "affiliations": [
    "Beijing Institute of Genomics, Chinese Academy of Sciences, and China National Center for Bioinformation"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 15,
  "authors": [
    {
      "name": "Z. Huang"
    },
    {
      "name": "Y. Chu"
    },
    {
      "name": "Y. Tian"
    },
    {
      "name": "C. Shao"
    },
    {
      "name": "J. Wang"
    },
    {
      "name": "X. Zhang"
    },
    {
      "name": "J. Chen"
    },
    {
      "name": "Z. Jia"
    },
    {
      "name": "L. Li"
    },
    {
      "name": "J. Li"
    },
    {
      "name": "G. Lin"
    },
    {
      "name": "K. Zhang"
    },
    {
      "name": "S. E. Antonarakis"
    },
    {
      "affs": [
        0
      ],
      "name": "Y. Kang"
    },
    {
      "name": "J. Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/62h5f89kjjwy5.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.07.749735",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.07.749735v1.full",
  "id": "62h5f89kjjwy5",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.07.749735v1",
  "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",
      "genomics"
    ],
    [
      "openalex",
      "1312|Genomics and Phylogenetic Studies"
    ]
  ],
  "openalex": "W7212229659",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.07.749735v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/62h5f89kjjwy5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:19Z",
      "native_id": "10.64898/2026.09.07.749735",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.07.749735v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:genomics",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "A T2T Benchmark Reveals How Reference Choice Shapes Human Genome Interpretation",
  "title_text": "A T2T Benchmark Reveals How Reference Choice Shapes Human Genome Interpretation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:19Z",
  "url": "https://research.draconitic.com/paper/62h5f89kjjwy5",
  "venue": "bioRxiv",
  "versions": []
}