{
  "abstract": "Benchmarks for rare-disease gene prioritisation are assembled from published clinical cases. Those cases often come from the same publications used to build knowledge-base (\"curated\") tools, so a curated tool can be scored on its own source literature. This resource makes that circularity measurable. We release a stratified benchmark of 1,047 rare-disease cases from the GA4GH Phenopacket Store v0.1.26. Each case pairs a Human Phenotype Ontology profile with a 50-gene candidate list (one causal gene, 49 distractors) and the causal-gene label, sampled across four operational MONDO-derived disease strata and issued in two case-paired variants: random distractors, and phenotype-similar distractors selected by HPO Resnik similarity. Two case-level metadata layers support fairer evaluation: a per-case flag recording whether a case's source publication is cited in the HPO disease-annotation file, defining an overlap-absent subset (n = 282), and publication-recency strata. We also specify a deterministic, version-pinned recipe for a hybrid dense-plus-sparse retrieval index over approximately 2.25 million PMC Open Access articles (52,777,395 chunks). The resource reports no tool comparisons.",
  "abstract_shown": true,
  "affiliations": [
    "Universidad Europea de Valencia"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "J. Angulo"
    },
    {
      "name": "V. Yeste"
    },
    {
      "affs": [
        0
      ],
      "name": "H. Espinos-Morato"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/10pqv38p25y5y.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.30.748028",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748028v1.full",
  "id": "10pqv38p25y5y",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748028v1",
  "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",
      "1312|Biomedical Text Mining and Ontologies"
    ]
  ],
  "openalex": "W7207752507",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748028v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/10pqv38p25y5y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:10Z",
      "native_id": "10.64898/2026.08.30.748028",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.08.30.748028v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "An annotation-overlap-flagged rare-disease gene-prioritisation benchmark and PMC index recipe",
  "title_text": "An annotation-overlap-flagged rare-disease gene-prioritisation benchmark and PMC index recipe",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:10Z",
  "url": "https://research.draconitic.com/paper/10pqv38p25y5y",
  "venue": "bioRxiv",
  "versions": []
}