{
  "abstract": "Structure-aware foundation models that jointly represent proteins and ligands promise to extend affinity prediction beyond the chemical applicability domains of conventional ligand-based models, but whether they provide sufficient resolution to guide fine-grained medicinal-chemistry decisions remains unclear. We evaluatedBoltz-2across12kinasetargetsusinghistoricalbioactivityreconstruction,binding-pocket randomization, cross-target selectivity analysis, and chemical-series evaluation. Across chemically diverse compounds in temporally reconstructed evaluation sets, Boltz-2 and target-specific ligand-based machine learningshowedcomparablemeanglobalrankingacrosstargets,withsubstantialtarget-dependent differences (mean Kendall’s τ = 0.40 vs 0.31). Randomizing the binding pocket reduced mean τ from 0.33 to 0.14, while predictions were centered near −7.64 kcal/mol and retained correlated compound profiles acrossproteins.Together,theseresultssuggestastrongligand-conditionedsignal,withadditional predictive information contributed by the protein pocket. Despite this protein sensitivity, compound-level selectivitypredictionremainedweak(meanτ=0.17),andtheexperimentallystrongesttargetwas recovered for only 18.9% of compounds. Ranking also weakened within 72 temporally classified chemical series and varied substantially among series (protein-balanced mean τ = 0.18 for Boltz-2 and 0.09 for ligand-based models). These results show that structure-aware models can recover affinity information beyond relationshipscaptured by conventionalligand-based approaches whilerevealingaresolution boundary between broad prioritization and the local energetic discrimination required for selectivity and analogue ranking. At their current demonstrated resolution, such models appear best suited to broad compound or series prioritization and complementary hypothesis generation. Extending their use to fine analogueranking,selectivityoptimization,andinterpretationofsmallaffinitydifferenceswillrequire prospective evidence of reliable local resolution.",
  "abstract_shown": true,
  "affiliations": [
    "Avicenna Biosciences Inc., 101 W Chapel Hill St, Durham, North Carolina, 27701",
    "College of Pharmacy",
    "Medical University of South Carolina",
    "Department of Computer Science and Department of Mathematics and Statistics",
    "Department of Biochemistry, Genetics and Microbiology",
    "University of Pretoria"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Pieter B. Burger"
    },
    {
      "affs": [
        0
      ],
      "name": "Thomas M. Kaiser"
    },
    {
      "affs": [
        0
      ],
      "name": "Parker Dryja"
    },
    {
      "affs": [
        0
      ],
      "name": "Morné Muller"
    },
    {
      "affs": [
        1,
        2,
        3
      ],
      "name": "MacLean Levin"
    },
    {
      "affs": [
        0
      ],
      "name": "Sandro Belvedere"
    },
    {
      "affs": [
        0
      ],
      "name": "Ilya Balabin"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Yuri K. Peterson"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Rian E. Pierneef"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Fourie Joubert"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bk2yztgq4b616.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010040/v1",
  "fulltext_url": null,
  "id": "bk2yztgq4b616",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010040/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7220863842",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010040/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/bk2yztgq4b616.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010040",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010040/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Beyond the Ligand Applicability Domain: Generalization and Local Resolution in Structure-Aware Foundation Models for Affinity Prediction",
  "title_text": "Beyond the Ligand Applicability Domain: Generalization and Local Resolution in Structure-Aware Foundation Models for Affinity Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/bk2yztgq4b616",
  "venue": "ChemRxiv",
  "versions": []
}