{
  "source": "ORD Dataset Wishlist",
  "snapshot_date": "2026-09-25",
  "ord_wishlist_status_at_snapshot": "Available",
  "ord_wishlist_card": "https://github.com/orgs/open-reaction-database/projects/11?pane=issue&itemId=126569952",
  "ord_data_issue": null,
  "title": "A direct-to-biology high-throughput chemistry approach to reactive fragment screening",
  "doi": "10.1039/D1SC03551G",
  "journal": "Chemical Science",
  "publication_date": "2021-08-11",
  "authors": [
    "Ross P. Thomas",
    "Rachel E. Heap",
    "Francesca Zappacosta",
    "Emma K. Grant",
    "Péter Pogány",
    "Stephen Besley",
    "David J. Fallon",
    "Michael M. Hann",
    "David W. House",
    "Nicholas C. O. Tomkinson",
    "Jacob T. Bush"
  ],
  "article_open_access": {
    "status": "diamond",
    "license": "cc-by"
  },
  "dataset_size_estimate": 1000,
  "experiment_type": "HTE, D2B",
  "ord_priority": "Low",
  "ord_difficulty": "Hard",
  "source_data_kind": "author_request_needed",
  "smiles_in_source": "unknown",
  "needs_author_contact": true,
  "data_locations": [
    {
      "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8457371/",
      "what": "PMC full text (Europe PMC XML fetched). The only supplementary file is SC-012-D1SC03551G-s001.pdf (ESI). No data-availability statement or repository link.",
      "license": "CC-BY-3.0 (article)"
    },
    {
      "url": "https://doi.org/10.1039/D1SC03551G",
      "what": "Chem. Sci. 2021 article landing page. The RSC page returned 403 to the automated request.",
      "license": "CC-BY-3.0 (article)"
    },
    {
      "url": "https://github.com/thatchemistryguy/PyParse",
      "what": "PyParse LC-MS analysis code repository. It contains example_dataset/ (Waters and Shimadzu raw LC-MS files plus a small platemap CSV). Its relation to this paper's library is unclear, and the repository has no license.",
      "license": "none declared"
    },
    {
      "url": "https://doi.org/10.1039/D3DD00167A",
      "what": "PyParse paper (Digital Discovery 2023), which reuses data from this study. SI not checked.",
      "license": "unknown"
    }
  ],
  "notes": "Source: Chem. Sci. 2021, 10.1039/D1SC03551G (CC BY 3.0 article; PMC8457371). This is a direct-to-biology high-throughput chemistry study of about 1000 reactions building reactive fragments. The ESI is a single PDF and does not include the per-reaction data table, so the data must be obtained from the authors, coordinated through ORD. The same data was also used in the PyParse paper (Digital Discovery 2023, 10.1039/D3DD00167A). Check for overlap with any ORD dataset or wishlist item from that paper to avoid duplicates. The PyParse GitHub repository contains example LC-MS data only and has no license.",
  "verification_caveats": "Direct-to-biology workflow: crude reaction mixtures go straight to biological assays and products are not isolated or characterized. Outcomes are probably LC-MS-based conversion or product detection (semi-quantitative). The data may be split or duplicated with the PyParse dataset. Library-scale enumeration needs templated SMILES."
}