{
  "abstract": "To address widespread data leakage and inconsistent evaluation in protein-ligand affinity prediction, we introduce PLABench, a leakage-controlled and target-centric benchmarking framework that enables standardized comparison across sequence- and structure-based models. We benchmark nine deep learning methods across blind CASP16 targets, leakage-controlled ChEMBL35 sets, and established Davis and KIBA datasets under rigorous data split settings, standardizing structural input via AlphaFold3 to ensure fair comparison. Although pretrained structure-based models achieve the highest overall accuracy, they show severe target-dependent variability, and increasing structural fidelity from predicted to experimental conformations yields no consistent gains. Meanwhile, sequence-based approaches surpass some structure-based methods on select targets, and protein family-level evaluations reveal uneven performance across families and substantial inter-model complementarity obscured by aggregate metrics. These findings demonstrate that training scale and structural input alone cannot guarantee cross-target generalization, highlighting the need for context-aware interaction modeling. PLABench provides an extensible open-source platform to facilitate these developments.",
  "abstract_shown": true,
  "affiliations": [
    "University of Missouri - Columbia"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "L. Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Cheng"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6me4669rgdxcn.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.17.752433",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752433v1.full",
  "id": "6me4669rgdxcn",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752433v1",
  "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": "W7214103012",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752433v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6me4669rgdxcn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:09Z",
      "native_id": "10.64898/2026.09.17.752433",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752433v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction",
  "title_text": "Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:09Z",
  "url": "https://research.draconitic.com/paper/6me4669rgdxcn",
  "venue": "bioRxiv",
  "versions": []
}