{
  "abstract": "As benchmarks saturate, traditional validation methods fail to capture the probabilistic representations of genomic foundation models. This study probes self-supervised generalists (NTv3 650M, Evo2 40B, Genos 10B) alongside task-specific specialists (SpliceAI, AlphaGenome, Borzoi) using a mechanistically focused paradigm centered on expert-curated single-nucleotide substitutions within the splicing regions of the exon-rich OPA1 gene. Extending this analysis across the broader corpus of OPA1 mutations, variants of uncertain significance (VUS), and an independent 65-gene dataset of spliceogenic mutations demonstrates that generalists can match task-specific networks. Training data scale, genetic diversity, and evolutionary context are key for capturing RNA splicing syntax, whereas sparse routing may constrain performance. Mechanistically, foundation models exhibit a compute-asymmetry: the Evo2 40B model frontloads compute into massive parameter scale to resolve single-nucleotide variants within a narrow 425-bp context window, whereas the bidirectional NTv3 650M model and the Genos 10B mixture-of-experts (MoE) architecture backload compute to inference, requiring spatial logit aggregation and expansive context windows of up to 94 kb. Furthermore, classification accuracy across these foundation models benefitted from locus-specific thresholding rather than mutation-class calibration, exposing representation boundaries of the models.",
  "abstract_shown": true,
  "affiliations": [
    "712 North Inc."
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "M. V. Alavi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4zynp5naqrr1j.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.02.756289",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.02.756289v1.full",
  "id": "4zynp5naqrr1j",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.02.756289v1",
  "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",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|RNA Research and Splicing"
    ]
  ],
  "openalex": "W7221158542",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.02.756289v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4zynp5naqrr1j.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:50Z",
      "native_id": "10.64898/2026.10.02.756289",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.02.756289v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Probing Genomic Foundation Models with Splice-Variant Perturbations",
  "title_text": "Probing Genomic Foundation Models with Splice-Variant Perturbations",
  "type": "preprint",
  "updated_at": "2026-11-02T00:21:19Z",
  "url": "https://research.draconitic.com/paper/4zynp5naqrr1j",
  "venue": "bioRxiv",
  "versions": []
}