{
  "abstract": "The increasing use of AI in chemical research requires reliable reaction data to support efficient synthetic route design and reaction discovery. We present OPRD-100, an expert-curated and cross-validated dataset of 3,878 reactions extracted from 100 Organic Process Research & Development articles published between 1999 and 2024. Each entry captures detailed reactivity information, including yield, stereochemistry, temperature, time, solvents, and reagents. Analysis of the dataset reveals the relative importance of reaction data reported in tables versus text—particularly for reactions with low or no yields—and highlights the challenges of consistently capturing information from complex studies. Comparison with Reaxys showed systematic omissions and a strong bias toward high-yield reactions, underscoring the risks of relying on uncurated data. OPRD-100 thus provides a robust benchmark for training and evaluating AI tools in industrially relevant organic synthesis. Reaction data, data mining, benchmarking dataset",
  "abstract_shown": true,
  "affiliations": [
    "School of Chemistry, University of Leeds, Woodhouse Lane, Leeds, United Kingdom, LS2 9JT",
    "Molecular Sciences Research Hub, Imperial College London, 82 Wood Lane, London, United Kingdom, W12 0BZ",
    "School of Chemistry, University of Southampton, University Road, Highfield, Southampton, SO17 1BJ"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "George A. Hodgin"
    },
    {
      "affs": [
        1
      ],
      "name": "Alexander P. Atkins"
    },
    {
      "affs": [
        0
      ],
      "name": "Jago F. Deane"
    },
    {
      "affs": [
        0
      ],
      "name": "Ching Wai (Andy) Fong"
    },
    {
      "affs": [
        0
      ],
      "name": "Alister S. Goodfellow"
    },
    {
      "affs": [
        2
      ],
      "name": "Samuel A. Munday"
    },
    {
      "affs": [
        0
      ],
      "name": "Rachel Napier"
    },
    {
      "affs": [
        0
      ],
      "name": "Abigail E. Tranter"
    },
    {
      "affs": [
        2
      ],
      "name": "Jeremy G. Frey"
    },
    {
      "affs": [
        1
      ],
      "name": "King Kuok (Mimi) Hii"
    },
    {
      "affs": [
        0
      ],
      "name": "Bao N. Nguyen",
      "orcid": "0000-0002-0254-025X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dav382260ywjv.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15011178/v1",
  "fulltext_url": null,
  "id": "dav382260ywjv",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011178/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",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7224097890",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-28",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/dav382260ywjv.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.26434/chemrxiv.15011178",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011178/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "OPRD-100: An Expert-Curated Dataset of Organic Reactions for Benchmarking Reaction Data Mining Tools",
  "title_text": "OPRD-100: An Expert-Curated Dataset of Organic Reactions for Benchmarking Reaction Data Mining Tools",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/dav382260ywjv",
  "venue": "ChemRxiv",
  "versions": []
}