{
  "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=126570092",
  "ord_data_issue": null,
  "title": "Nanoscale synthesis and affinity ranking",
  "doi": "10.1038/s41586-018-0056-8",
  "journal": "Nature",
  "publication_date": "2018-04-19",
  "authors": [
    "Nathan J. Gesmundo",
    "Bérengère Sauvagnat",
    "Patrick J. Curran",
    "Matthew P. Richards",
    "Christine L. Andrews",
    "Peter J. Dandliker",
    "Tim Cernak"
  ],
  "article_open_access": {
    "status": "closed",
    "license": null
  },
  "dataset_size_estimate": null,
  "experiment_type": null,
  "ord_priority": null,
  "ord_difficulty": null,
  "source_data_kind": "si_spreadsheet_or_csv",
  "smiles_in_source": "yes",
  "needs_author_contact": false,
  "data_locations": [
    {
      "url": "https://www.nature.com/articles/s41586-018-0056-8",
      "what": "Article landing page; lists the Supplementary Information PDF (MOESM1) and 11 Source Data files (Fig. 2, 3, 4; ED Fig. 2-6, 8-10) as XLS/XLSX",
      "license": "Springer Nature, closed-access article (Crossref: springer.com/tdm only)"
    },
    {
      "url": "https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41586-018-0056-8/MediaObjects/41586_2018_56_MOESM9_ESM.xlsx",
      "what": "Source Data for ED Fig. 6 (catalyst/base survey, 0.78 MB). Sheets: Suzuki Coupling Screen 1 (687 rows), Suzuki 2 Optimization (162), C-N Coupling Screen 1 (384), C-N Coupling Screen 2 (364), Diverse Coupling Screen (1,536), Compiled Yield Data (2,110), plus plate maps. Columns include Core SMILES, Building Block SMILES/MFCD, Product SMILES, catalyst, base, solvent, UV areas, Pdt-to-IS ratio, % conversion, calculated % yield",
      "license": "Springer Nature source data; no CC license stated"
    },
    {
      "url": "https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41586-018-0056-8/MediaObjects/41586_2018_56_MOESM2_ESM.xls",
      "what": "Source Data for Fig. 2 (library synthesis; 1.3 MB per HEAD); MOESM3-8 and MOESM10-12 are the other figure source data files (HEAD checked only on MOESM2/3/9/12)",
      "license": "Springer Nature source data; no CC license stated"
    },
    {
      "url": "https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41586-018-0056-8/MediaObjects/41586_2018_56_MOESM1_ESM.pdf",
      "what": "Supplementary Information PDF (procedures, concentrations and amounts, compound data)",
      "license": "Springer Nature; closed"
    }
  ],
  "notes": "Nanomole-scale (1536-well) Pd-catalysed coupling screens (Suzuki, C-N amination, amide/diverse nucleophile couplings) and library syntheses from Gesmundo et al., Nature 2018 (doi:10.1038/s41586-018-0056-8). Reaction data is in the article's Source Data Excel files (Fig. 2-4 and Extended Data Figs. 2-6, 8-10) on nature.com. Rows give reactant and product SMILES, plate position, catalyst (trade names such as XPhos Pd G3), base (e.g. P2-Et, BTMG, BTTP), solvent, LC-UV areas and a calculated percent yield from a product-to-internal-standard ratio. Reagent volumes are in the plate-map sheets. Concentrations, stoichiometry, temperature and time must be taken from the Supplementary Information PDF. Pitfalls: (1) some sheets identify building blocks only by MFCD number, so resolve SMILES from other sheets; (2) the 'Compiled Yield Data' sheet repeats rows from the individual screen sheets, so do not double-count; (3) some sheets have two yield columns (e.g. 'Calc. Percent Yield' and 'Calc'd % Yield Updated'), so state which one is used; (4) affinity-selection mass spectrometry (ASMS) binding data is not reaction data and is out of scope; (5) catalyst and base names need structures. The ORD Dataset must cite the paper DOI.",
  "verification_caveats": "Yields are LC-UV estimates against an internal standard, not isolated yields; conversion and yield columns coexist. Screens are spread across many sheets and files with overlap (compiled vs per-screen), so reviewers must check for deduplication. Many reactions give 0% yield (valid negative data). Precatalysts are named by trade name. Reaction conditions such as temperature, time and concentrations live in the SI PDF, not in the spreadsheets. It may need 2 datasets if library synthesis and condition screens are kept separate."
}