{
  "abstract": "Rank correlation and discriminative resolution are distinct properties of a stability predictor, yet current benchmarks measure only the first. Here we introduce resolving power: the {Delta}{Delta}G separation at which a predictor orders two variants correctly three times in four. Applied to BioEmu across twelve wild-type domains and three supervised regressors on an independent twenty-seven, resolving powers cluster near 1 kcal mol -1 --- comparable to the median variant-pair separation the benchmarks ask these models to rank, so most pairs cannot be ordered. A closed form ties this resolution to the calibration slope ; Spearman correlations account for only 31% of its variance. BioEmu extracts {Delta}G from the ratio of folded and unfolded populations, so what it samples of each becomes a question. Its folded populations reproduce experimental radii of gyration within half an [a]ngstrom, whereas those it labels unfolded are collapsed chains roughly 20 to 40% below a sequence-specific random-coil reference. The ensemble still carries variant differences on panels where the sampled unfolded fraction approaches zero, but the log-odds counting readout runs out of range. Scored by a learned energy, those same conformations recover resolution on ten of twelve panels, with the gain separated from noise on four, without retraining.",
  "abstract_shown": true,
  "affiliations": [
    "Joint Research Centre, European Commission"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "M. Ronco"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fgc4edyyw3nyx.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.18.752669",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.18.752669v1.full",
  "id": "fgc4edyyw3nyx",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.18.752669v1",
  "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|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7214318432",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.18.752669v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fgc4edyyw3nyx.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:27Z",
      "native_id": "10.64898/2026.09.18.752669",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.18.752669v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Resolving power as a measure of protein stability prediction",
  "title_text": "Resolving power as a measure of protein stability prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:27Z",
  "url": "https://research.draconitic.com/paper/fgc4edyyw3nyx",
  "venue": "bioRxiv",
  "versions": []
}