{
  "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=126570035",
  "ord_data_issue": null,
  "title": "Exploring Optimal Reaction Conditions Guided by Graph Neural Networks and Bayesian Optimization",
  "doi": "10.1021/acsomega.2c05165",
  "journal": "ACS Omega",
  "publication_date": "2022-12-02",
  "authors": [
    "Youngchun Kwon",
    "Dongseon Lee",
    "Jin Woo Kim",
    "Youn-Suk Choi",
    "Sun Kim"
  ],
  "article_open_access": {
    "status": "gold",
    "license": "cc-by-nc-nd"
  },
  "dataset_size_estimate": null,
  "experiment_type": null,
  "ord_priority": null,
  "ord_difficulty": null,
  "source_data_kind": "author_request_needed",
  "smiles_in_source": "partial",
  "needs_author_contact": true,
  "data_locations": [
    {
      "url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9753507/",
      "what": "Full text (PMC): data availability says data are available from the corresponding author on reasonable request; Table 1 defines search spaces",
      "license": "Article CC-BY-NC-ND 4.0"
    },
    {
      "url": "https://pubs.acs.org/doi/suppl/10.1021/acsomega.2c05165/suppl_file/ao2c05165_si_001.pdf",
      "what": "SI PDF (about 1.6 MB): reaction details (Tables S1-S7), Task 2 optimization details as figures (S6, S8)",
      "license": "not verified"
    },
    {
      "url": "https://github.com/b-shields/edbo",
      "what": "Task 1 source data (Shields et al. EDBO: Suzuki-Miyaura, Buchwald-Hartwig, direct arylation), including experiments/data CSVs; originates from other papers",
      "license": "MIT"
    }
  ],
  "notes": "Source: Kwon et al., ACS Omega 2022, doi:10.1021/acsomega.2c05165 (open access, CC-BY-NC-ND 4.0). Task 1 benchmarks a GNN plus Bayesian optimization method on published HTE datasets, taken from the EDBO repository (github.com/b-shields/edbo, MIT). Those datasets come from earlier Doyle/Shields papers and should be checked against ORD before any curation to avoid duplicates. Task 2 is the paper's own experimental data: 22 reaction optimizations (Suzuki-Miyaura 4a-4j, Buchwald-Hartwig 5a-5h, Ullmann 6a-6b, Chan-Lam 7a-7b) run on the authors' HTE platform. It is shown only as SI figures, and the paper says data are available from the corresponding author on request. The Reaxys training data used for the GNN is not redistributable and is out of scope.",
  "verification_caveats": "Sequential optimization campaigns (algorithm-selected conditions), so each experiment must be recorded individually. Task 1 data likely duplicates existing ORD datasets. Task 2 values exist only in figures unless the authors supply them."
}