{
  "abstract": "A polygenic score (PGS) is a unitless weighted sum of allele dosages, interpretable only as a percentile within a reference distribution. Evaluating risk across models requires scoring each individual against a whole reference panel, but current CPU pipelines process targets or models sequentially, making full cross-product calculations prohibitively expensive. We reformulated PGS calculation as a cohort-wide sparse matrix product on a GPU and optimized it via an autonomous coding agent under read-only inputs, cold starts, and strict numerical validation against pgsc_calc. The scorer was \"trained\" by the agent accessing synthetic data and real 1000 Genomes data. On a synthetic benchmark, the scorer achieved a 10.6-fold speedup during the training course (184.9 s to 17.4 s) and ran 71-fold faster than pgsc_calc. However, on held-out real genomes, the synthetic-trained scorer was 15.3-fold slower than the real-data-trained version and diverged significantly from pgsc_calc (maximum absolute difference of 3.7x10-1 vs. 3.1x10-4). Three replications of the synthetic loop from an identical prompt showed that agent optimization trajectory variance explains 91 to 96% of total wall-clock variance, against 0 to 2.6% for the data sampled and 0.2 to 3.3% for repeated execution. A memory-bounded rebuild then scored all the 3,202 1000 Genome genotypes against all 5,385 models in 6.5 h within a 72 GB memory cap, released here as a frozen scoring manifest with ancestry-stratified reference distributions for the whole PGS Catalog",
  "abstract_shown": true,
  "affiliations": [
    "Boston Children's Hospital, Department of Pediatrics, Division of Genetics and Genomics, Boston, MA"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "A. Afyouni"
    },
    {
      "name": "B. Yang"
    },
    {
      "affs": [
        0
      ],
      "name": "C. Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2ac63zr1s6j39.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.28.755102",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.28.755102v1.full",
  "id": "2ac63zr1s6j39",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.28.755102v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1311|Genetic Associations and Epidemiology"
    ]
  ],
  "openalex": "W7218641840",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.28.755102v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2ac63zr1s6j39.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:56Z",
      "native_id": "10.64898/2026.09.28.755102",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.28.755102v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Agent-optimized GPU polygenic scoring at cohort scale",
  "title_text": "Agent-optimized GPU polygenic scoring at cohort scale",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:56Z",
  "url": "https://research.draconitic.com/paper/2ac63zr1s6j39",
  "venue": "bioRxiv",
  "versions": []
}