{
  "abstract": "Searching large databases of predicted protein structures can reveal remote homologs, but reliable discovery requires accurate significance estimates. We show that native E-values reported by protein structure search tools such as Foldseek and Reseek can be unreliable, leading to false discoveries or missed homologs. To address this problem, we introduce Struct-Caliper, which provides reliable query-specific p-values for protein structure search. The method uses representation-aware query randomization to generate background queries and compares observed alignment scores with the highest scores from randomized searches of the same database. In simulations, SG p-values generally kept reported false positive at or below the chosen cutoff under the evaluated randomization procedures. In searches of 15,177 ASTRAL40 structures, SG p-values increased Foldseek homolog recovery by 18.2% with slightly fewer false discoveries compared with native E-values at a cutoff of 0.01. For Reseek, false discoveries even decreased by 99.5%. Across 73 queries searched against more than two million AlphaFoldDB structures, SG p-values increased the mean recovery of DALI-supported matches by 23.5% at the same cutoff. These results show that Struct-Caliper can improve the reliability of structure searches and help prioritize discoveries for further biological analysis.",
  "abstract_shown": true,
  "affiliations": [
    "University of Wisconsin - Madison"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "L. Shi"
    },
    {
      "name": "H. Zhou"
    },
    {
      "name": "Y. Yang"
    },
    {
      "affs": [
        0
      ],
      "name": "Y. Lu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dvx550dh2fgn1.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.03.764110",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764110v1.full",
  "id": "dvx550dh2fgn1",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764110v1",
  "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": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764110v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dvx550dh2fgn1.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T00:22:03Z",
      "native_id": "10.64898/2026.11.03.764110",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.03.764110v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Representation-aware calibration enables statistically reliable protein structure search",
  "title_text": "Representation-aware calibration enables statistically reliable protein structure search",
  "type": "preprint",
  "updated_at": "2026-11-06T00:21:45Z",
  "url": "https://research.draconitic.com/paper/dvx550dh2fgn1",
  "venue": "bioRxiv",
  "versions": []
}