{
  "abstract": "Learning from large-scale bioactivity archives is complicated by heterogeneous assay readouts and differences in data reliability. Here we show that a model that predicts probability distributions over binding affinities from sequence data opens model training to vast and diverse troves of heterogeneous bioactivity data. We develop PSICHIC+, a bioactivity foundation model trained on approximately 82 million protein-ligand records using a distributional objective that preserves quantitative resolution while incorporating variation in data reliability. Given a protein sequence and ligand SMILES, PSICHIC+ predicts binding affinity in milliseconds. In zero-shot virtual-screening benchmarks without target-specific training data, it improves enrichment over regression- and classification-based approaches and performs competitively with leading structure-based methods. In lab-in-the-loop campaigns, distribution-guided acquisition improves recovery of high-activity compounds under fixed screening budgets. Combining PSICHIC+ with Boltz-2 improves hit-to-lead affinity prediction over Boltz-2 alone, with mean correlation approaching that of FEP+ on the evaluated benchmarks, without requiring high-resolution protein structures. These results support distributional learning as a scalable approach to using heterogeneous bioactivity data for hit identification and hit-to-lead optimization.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Data Science and Artificial Intelligence, Monash University, VIC, Australia; Drug Discovery Biology, Monash Institute of Pharmaceutical Sciences,"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "H. Y. Koh"
    },
    {
      "affs": [
        0
      ],
      "name": "H. J. W. Koh"
    },
    {
      "name": "Y. Zheng"
    },
    {
      "name": "V. Naranbhai"
    },
    {
      "name": "D. F. Schmidt"
    },
    {
      "name": "J. Barthelemy"
    },
    {
      "name": "Y.-J. Chen"
    },
    {
      "name": "A. T. N. Nguyen"
    },
    {
      "name": "S. Pan"
    },
    {
      "name": "L. T. May"
    },
    {
      "name": "G. I. Webb"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4hsx60szyjwdx.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.26.762100",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.762100v1.full",
  "id": "4hsx60szyjwdx",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.762100v1",
  "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": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.26.762100v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4hsx60szyjwdx.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T12:20:58Z",
      "native_id": "10.64898/2026.10.26.762100",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.26.762100v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Bioactivity foundation model for hit identification and hit-to-lead optimization from sequence data",
  "title_text": "Bioactivity foundation model for hit identification and hit-to-lead optimization from sequence data",
  "type": "preprint",
  "updated_at": "2026-11-02T00:21:21Z",
  "url": "https://research.draconitic.com/paper/4hsx60szyjwdx",
  "venue": "bioRxiv",
  "versions": []
}