{
  "abstract": "Data splitting is a critical determinant of machine-learning performance in small-molecule drug design. Different strategies impose distinct assumptions about structural similarity, temporal order, data provenance and chemical-space coverage, thereby affecting both evaluation realism and the interpretation of model performance. This perspective critically examines major splitting approaches, discusses their advantages, applicability and limitations, and offers evidence-based considerations for designing partitions aligned with intended prediction scenarios.",
  "abstract_shown": true,
  "affiliations": [
    "Université Paris Cité",
    "INSERM ERL",
    "CNRS UMR",
    "University of Strasbourg",
    "Department of Bioengineering",
    "Imperial College London"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Cao-Minh Truong"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Van-Thinh To"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Gia-Bao Truong"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Alexey Orlov"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Pedro J. Ballester"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Olivier Taboureau"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Viet-Khoa Tran-Nguyen",
      "orcid": "0000-0001-7497-333X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8ez3bv9v0m4dp.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009691/v1",
  "fulltext_url": null,
  "id": "8ez3bv9v0m4dp",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009691/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": "W7214927326",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009691/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/8ez3bv9v0m4dp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:21Z",
      "native_id": "10.26434/chemrxiv.15009691",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009691/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Small-Molecule Data Splitting for Machine Learning in Drug Design",
  "title_text": "Small-Molecule Data Splitting for Machine Learning in Drug Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/8ez3bv9v0m4dp",
  "venue": "ChemRxiv",
  "versions": []
}