{
  "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=126888100",
  "ord_data_issue": null,
  "title": "Continuous collective analysis of chemical reactions",
  "doi": "10.1038/s41586-024-08211-4",
  "journal": "Nature",
  "publication_date": "2024-12-11",
  "authors": [
    "Maowei Hu",
    "Lei Yang",
    "Nathaniel R. Twarog",
    "Jason Ochoada",
    "Yong Li",
    "Eirinaios I. Vrettos",
    "Arnaldo X. Torres Hernandez",
    "James B. Martinez",
    "Jiya Bhatia",
    "Brandon Michael Young",
    "Jeanine E. Price",
    "Kevin M. McGowan"
  ],
  "article_open_access": {
    "status": "green",
    "license": null
  },
  "dataset_size_estimate": 2688,
  "experiment_type": "HTE",
  "ord_priority": "High",
  "ord_difficulty": "Hard",
  "source_data_kind": "si_spreadsheet_or_csv",
  "smiles_in_source": "partial",
  "needs_author_contact": false,
  "data_locations": [
    {
      "url": "https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41586-024-08211-4/MediaObjects/41586_2024_8211_MOESM2_ESM.xlsx",
      "what": "Supplementary Data XLSX (4.57 MB, 60 sheets). Sheets 12-34 and 42-50 are 384-well plate grids (processed LC-MS / NL-ADE-MS / NL-LC-MS). Sheet 60 lists 96 amines and target products with SMILES; sheets 5 and 35 have more SMILES; sheet 59 has compound QC/HRMS",
      "license": "Nature SI; no open license stated"
    },
    {
      "url": "https://www.nature.com/articles/s41586-024-08211-4",
      "what": "Article landing page listing SI: Supplementary Information PDF (19.8 MB), Supplementary Data XLSX, Source Data XLSX for Figs 2 and 4 and Extended Data Figs 1-10",
      "license": "Nature publisher license; green OA author manuscript in PMC (PMC11823688)"
    },
    {
      "url": "https://github.com/nathanieltwarog/HuEtAl2024_Nature",
      "what": "Code repo: R example for extracting NL-ADE-MS intensities from .wiff files (example raw MS files, output and formatting XLSX). Not the reaction dataset",
      "license": "No license file"
    }
  ],
  "notes": "Source: Nature 10.1038/s41586-024-08211-4 (St. Jude Children's Research Hospital): continuous collective analysis of reactions by neutral-loss acoustic droplet ejection MS (NL-ADE-MS). Reaction data are in the Supplementary Data XLSX (60 sheets). Each screen is a 384-well plate grid of processed outcomes (LC-MS, NL-ADE-MS or NL-LC-MS) for one substrate and transformation. Transformations include C-N, C-C and C-O couplings, amidation, reductive amination and N-alkylation of TIDA boronates and complex substrates. One sheet lists the 96 amines and the target products with SMILES. Other substrates (e.g. drug-like and natural-product derivatives) and the catalyst/base conditions per row must be taken from the SI PDF. Per-figure Source Data XLSX files are also provided. The linked GitHub repository has analysis code and example raw MS files only. The Nature article is not open access (an author manuscript is in PMC), and the SI has no open license stated. Agree the scope (which plates and which analytical readout is primary) before starting, because the same reactions appear under several analysis methods.",
  "verification_caveats": "Outcomes are MS-derived relative quantities (LC-MS concentration or conversion estimates and NL-ADE-MS signal), not isolated yields. Several analytical readouts exist for the same wells and should become multiple analyses of one reaction, not duplicate reactions. Some experiments are multiplexed (6- or 8-plex pools with several products per well). Mapping plate rows and columns to conditions requires the SI PDF. The reaction count may differ from ORD's estimate of 2688. SMILES for non-amine substrates are incomplete."
}