{
  "abstract": "Polygenic risk scores (PRSs) have improved substantially in predictive performance, yet results remain difficult to compare across studies that differ in cohorts, phenotype definitions, and evaluation procedures. Comparison to machine-learning methods is harder still, since their performance depends strongly on how data are partitioned and whether related individuals leak across splits. Here, we introduce a family-aware benchmark for polygenic prediction built on version 9 of the All of Us Research Program (AoU). The benchmark assigns entire family components to fixed discovery, calibration, and test partitions, reserves first-degree relatives for within-family evaluation, and separates models trained only on AoU discovery data from those using external GWAS summary statistics. This enables direct comparison between conventional PRS pipelines and machine-learning models trained under identical data budgets. We report results for 14 binary disease traits. Our strongest scores explain 5.7-24.9% of liability-scale variance, with particularly strong prediction for Alzheimers disease, type 2 diabetes, prostate cancer, glaucoma, and inflammatory bowel disease, and match or exceed published commercial and academic scores for most traits. Across 12 traits with interpretable within-family estimates of within-sibship-to-population effect ratio, 11 confidence intervals included a ratio of 1. Type 2 diabetes showed an attenuation ratio of 0.86 [0.76, 0.97].",
  "abstract_shown": true,
  "affiliations": [
    "Reticular"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "G. Ren"
    },
    {
      "name": "K. Wu"
    },
    {
      "name": "C. Ren"
    },
    {
      "name": "I. Nyiha"
    },
    {
      "name": "K. Wu"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Yang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/epjw1g074c1en.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.22.26366229",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.22.26366229v1.full",
  "id": "epjw1g074c1en",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.22.26366229v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "genetic and genomic medicine"
    ],
    [
      "openalex",
      "1311|Genetic Associations and Epidemiology"
    ]
  ],
  "openalex": "W7223689280",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.22.26366229v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/epjw1g074c1en.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:51Z",
      "native_id": "10.64898/2026.10.22.26366229",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.22.26366229v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:genetic and genomic medicine",
      "subfield": "human-genetics"
    }
  ],
  "title": "A family-aware All of Us benchmark for polygenic prediction and genomic machine learning",
  "title_text": "A family-aware All of Us benchmark for polygenic prediction and genomic machine learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:51Z",
  "url": "https://research.draconitic.com/paper/epjw1g074c1en",
  "venue": "medRxiv",
  "versions": []
}