{
  "abstract": "Biomolecular structures provide a common physical basis for understanding molecular function and interactions. However, computational models typically specialize in individual molecular classes or tasks, hindering a unified representation of structural information across biological systems. Here we introduce OmniScore, a universal geometric encoder that learns shared representations of proteins, nucleic acids, small molecules and their complexes. Pretraining integrates geometric graph encoding, sequential modeling and tokenization with structural and physicochemical supervision. The frozen pretrained encoder supports complex-level model quality assessment and interaction prediction, as well as residue-level prediction, through task-specific heads. OmniScore outperforms the evaluated antibody--antigen quality-assessment baselines and also improves RNA structure ranking over baselines. For peptide-major histocompatibility complex interaction prediction, the OmniScore embeddings complement structure-prediction confidence metrics to improve predictive performance. Together, these findings support OmniScore as a shared geometric foundation for biomolecular representation and scoring across molecular classes and prediction scales, which may facilitate multi-component therapeutics development.",
  "abstract_shown": true,
  "affiliations": [
    "Seoul National University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "T.-C. Bui"
    },
    {
      "name": "Y. Hong"
    },
    {
      "name": "J. Song"
    },
    {
      "name": "Y. Tao"
    },
    {
      "name": "I. Chung"
    },
    {
      "name": "J. G. Park"
    },
    {
      "name": "J. Ko"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ec823n0mnfdvw.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.28.747942",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.08.28.747942v2.full",
  "id": "ec823n0mnfdvw",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.08.28.747942v2",
  "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",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204718485",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.08.28.747942v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ec823n0mnfdvw.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:53Z",
      "native_id": "10.64898/2026.08.28.747942",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.08.28.747942v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "OmniScore: Universal Scoring of Diverse Biomolecular Complexes via Equivariant Geometry-Aware Discrete Representation Learning",
  "title_text": "OmniScore: Universal Scoring of Diverse Biomolecular Complexes via Equivariant Geometry-Aware Discrete Representation Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:53Z",
  "url": "https://research.draconitic.com/paper/ec823n0mnfdvw",
  "venue": "bioRxiv",
  "versions": []
}