{
  "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=126570043",
  "ord_data_issue": null,
  "title": "Predicting relative efficiency of amide bond formation using multivariate linear regression",
  "doi": "10.1073/pnas.2118451119",
  "journal": "PNAS",
  "publication_date": "2022-04-11",
  "authors": [
    "Brittany C. Haas",
    "Adam E. Goetz",
    "Ana Bahamonde",
    "James Christopher McWilliams",
    "Matthew S. Sigman"
  ],
  "article_open_access": {
    "status": "hybrid",
    "license": "cc-by-nc-nd"
  },
  "dataset_size_estimate": 88,
  "experiment_type": "kinetic dataset",
  "ord_priority": null,
  "ord_difficulty": null,
  "source_data_kind": "si_pdf_tables",
  "smiles_in_source": "unknown",
  "needs_author_contact": false,
  "data_locations": [
    {
      "url": "https://www.ebi.ac.uk/europepmc/webservices/rest/PMC9169781/fullTextXML",
      "what": "Full text (PMC9169781). Lists supplementary files pnas.2118451119.sd01.xlsx and sd02.xlsx. Data availability says all data are in the article/SI.",
      "license": "CC BY-NC-ND 4.0 (article licence per Crossref/OpenAlex; the SI licence is not separately stated)"
    },
    {
      "url": "https://www.ebi.ac.uk/europepmc/webservices/rest/PMC9169781/supplementaryFiles",
      "what": "Europe PMC supplementary bundle (zip, partial download). Dataset S1 (sd01.xlsx, ~2.6 MB) has sheets 'Acid PCA & Clustering' and 'Amine PCA & Clustering' with DFT descriptor PCA loadings/clusters. It has no reaction outcomes and no SMILES column.",
      "license": "CC BY-NC-ND 4.0 (assumed from article)"
    },
    {
      "url": "https://www.pnas.org/doi/suppl/10.1073/pnas.2118451119/suppl_file/pnas.2118451119.sd02.xlsx",
      "what": "Dataset S2. Per the paper, DFT descriptors used for model generation. It may also carry the measured ln(k); not inspected.",
      "license": "CC BY-NC-ND 4.0 (assumed)"
    },
    {
      "url": "https://www.pnas.org/doi/suppl/10.1073/pnas.2118451119/suppl_file/pnas.2118451119.sapp.pdf",
      "what": "SI Appendix PDF. Kinetic procedure, likely rate-constant tables, and characterisation of isolated products (pnas.org returned 403).",
      "license": "CC BY-NC-ND 4.0 (assumed)"
    }
  ],
  "notes": "Open-access article (PMC9169781, CC BY-NC-ND 4.0 article licence). It has two XLSX supplementary datasets and an SI Appendix PDF. Dataset S1 contains only DFT-descriptor PCA/clustering tables for the acids and amines. The reaction data are second-order rate constants k (M^-1 min^-1) for carboxylic acid + primary alkyl amine couplings with CDI in THF, ~88 combinations. They are expected in the SI Appendix and possibly in Dataset S2. Kinetics were followed by quenching unreacted amine with 2,4-dinitrofluorobenzene and quantifying by UPLC-PDA against 2,6-dinitrotoluene as internal standard. Each product was also isolated and characterised. Substrate structures may be available only as drawings or names, so SMILES may need to be generated.",
  "verification_caveats": "Outcomes are rate constants, not yields. ORD has no native rate-constant field, so a convention is needed: a CUSTOM product measurement, or time-course amine consumption if timepoints are tabulated. Training and validation sets may be reported separately. The descriptor spreadsheets are not reaction data and should not be imported as reactions."
}