{
  "abstract": "This study evaluates how multi-view gene representations should be compared under a matched contract. Each of 18,460 genes is described by five aligned views: DNA sequence-derived features (D), RNA sequence-derived features (R), protein language-model embeddings (P), curated text knowledge (K), and single-cell expression (X). The contract fixes the gene universe, the 256-D output, label-free outer-training-only fitting, one random-forest probe, and task-equal Macro-F1 over nine registered binary tasks, and varies only the fusion operator across four protocol-defined input states: Core (DNA+RNA+protein), Core+K, Core+X, and Core+K+X. Under these states, the top-scoring operator changes with the available view combination and all task-bootstrap intervals overlap, establishing a condition-dependent rather than universal ranking pattern. An independently configured external RF track provides a separate check of the numerical range, while a gene-to-cell boundary diagnostic shows that gene-level differences attenuate toward a dimension-matched random control under expression-weighted aggregation, as predicted by a dilution identity. Historical log-derived multiplicative-interaction screening is retained only as magnitude-only supplementary evidence because fold-level records are unavailable. The contribution is therefore the matched contract and its audit trail: an evidence-graded protocol for turning fusion claims into comparable, condition-bounded measurements.",
  "abstract_shown": true,
  "affiliations": [
    "BGI Research, Beijing"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "H. Hou"
    },
    {
      "name": "T. Xia"
    },
    {
      "name": "L. Hu"
    },
    {
      "name": "Y. Zhang"
    },
    {
      "name": "Y. Li"
    },
    {
      "name": "S. Fang"
    },
    {
      "affs": [
        0
      ],
      "name": "L. Cao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f3pyt9g1hh509.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.06.11.731512",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.06.11.731512v2.full",
  "id": "f3pyt9g1hh509",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.06.11.731512v2",
  "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|Bioinformatics and Genomic Networks"
    ]
  ],
  "openalex": "W7164821621",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.06.11.731512v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-11",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f3pyt9g1hh509.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:02Z",
      "native_id": "10.64898/2026.06.11.731512",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.06.11.731512v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "RepGene: Auditing Condition-Specific Fusion Biases for Multi-View Gene Representations",
  "title_text": "RepGene: Auditing Condition-Specific Fusion Biases for Multi-View Gene Representations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:02Z",
  "url": "https://research.draconitic.com/paper/f3pyt9g1hh509",
  "venue": "bioRxiv",
  "versions": []
}