{
  "abstract": "The gap between reported machine learning (ML) model performance in drug discovery and the experience of using these models in live discovery projects remains a major hurdle for the field, because the retrospective nature of most benchmarks makes it difficult to objectively assess progress. To address this gap, OpenADMET has hosted a series of blind challenges to benchmark and advance predictive modeling in absorption, distribution, metabolism, excretion, and toxicity (ADMET). In this Perspective, we distill the operational, strategic, and community-level lessons from our first four blind challenges, providing a practical blueprint for designing and running collaborative machine learning competitions in the life sciences. In addition, we open-source our blind challenge infrastructure and data-validation tools to lower the barrier to entry for hosting rigorous, community-driven competitions and to foster a sustainable framework for collective learning in computer-aided drug discovery.",
  "abstract_shown": true,
  "affiliations": [
    "Open Molecular Software Foundation",
    "Hugging Face",
    "Octant, Inc.",
    "Department of Bioengineering and Therapeutic Sciences",
    "University of California San Francisco",
    "Computational and Systems Biology Program",
    "Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 14,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hugo MacDermott-Opeskin",
      "orcid": "0000-0002-7393-7457"
    },
    {
      "affs": [
        0
      ],
      "name": "Maria Castellanos"
    },
    {
      "affs": [
        0
      ],
      "name": "Jonathan A. Swain"
    },
    {
      "affs": [
        0
      ],
      "name": "Jenke Scheen"
    },
    {
      "affs": [
        0
      ],
      "name": "Sean Colby"
    },
    {
      "affs": [
        1
      ],
      "name": "Georgia Channing"
    },
    {
      "affs": [
        2
      ],
      "name": "Scott Simpkins"
    },
    {
      "affs": [
        2
      ],
      "name": "Robert Warneford-Thompson"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Galen J. Correy"
    },
    {
      "affs": [
        2
      ],
      "name": "L. Naomi Handly"
    },
    {
      "affs": [
        2
      ],
      "name": "Sri Kosuri"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "John Chodera"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "James S. Fraser"
    },
    {
      "affs": [
        0
      ],
      "name": "W. Patrick Walters"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9d6gwyps45nmw.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009105/v1",
  "fulltext_url": null,
  "id": "9d6gwyps45nmw",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009105/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": "W7213943203",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009105/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-20",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/9d6gwyps45nmw.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15009105",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009105/v2"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Operational insights from the front lines of OpenADMET: lessons from our blind challenges",
  "title_text": "Operational insights from the front lines of OpenADMET: lessons from our blind challenges",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/9d6gwyps45nmw",
  "venue": "ChemRxiv",
  "versions": []
}