{
  "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=126570017",
  "ord_data_issue": null,
  "title": "Predicting Three-Component Reaction Outcomes from 40k Miniaturized Reactant Combinations",
  "doi": "10.26434/chemrxiv-2024-5328b",
  "journal": "Science Advances",
  "publication_date": "2025-05-28",
  "authors": [
    "Julian Götz",
    "E. Glen Richards",
    "Iain A. Stepek",
    "Yu Takahashi",
    "Yi‐Lin Huang",
    "Louis Bertschi",
    "Bertran Rubi",
    "Jeffrey W. Bode"
  ],
  "article_open_access": {
    "status": "green",
    "license": "cc-by-nc"
  },
  "dataset_size_estimate": 40000,
  "experiment_type": "HTE",
  "ord_priority": "High",
  "ord_difficulty": "Normal",
  "source_data_kind": "si_spreadsheet_or_csv",
  "smiles_in_source": "yes",
  "needs_author_contact": false,
  "data_locations": [
    {
      "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12118581/",
      "what": "Science Advances article in PMC. SI files: sciadv.adw6047_data_s1_to_s4.zip (Data S1–S4, per ORD note a CSV with SMILES), sciadv.adw6047_sm.pdf, movies zip. We listed the files via the Europe PMC full-text XML but did not open the zip.",
      "license": "CC BY-NC (Europe PMC)"
    },
    {
      "url": "https://github.com/jugoetz/library-generation",
      "what": "Library enumeration and plate/data processing code (dirs: buildingblocks, db, plates, inputs, library_static)",
      "license": "MIT"
    },
    {
      "url": "https://github.com/jugoetz/synferm-predictions",
      "what": "ML code; data/ holds only example CSVs, not the full dataset",
      "license": "MIT"
    },
    {
      "url": "https://zenodo.org/doi/10.5281/zenodo.13769229",
      "what": "Virtual-library property predictions (SDF chunks). Not reaction outcome data.",
      "license": "unknown"
    },
    {
      "url": "https://doi.org/10.1126/sciadv.adw6047",
      "what": "Publisher landing page (science.org returned HTTP 403 to automated access)",
      "license": "CC BY-NC (per Europe PMC)"
    }
  ],
  "notes": "Source: Science Advances 2025, DOI 10.1126/sciadv.adw6047 (preprint 10.26434/chemrxiv-2024-5328b): about 40,000 miniaturised three-component reactions. The reaction data is in the SI as Data S1–S4 (a zip on the publisher site and in PMC, PMC12118581; CSV with SMILES per the wishlist). The processing code is at github.com/jugoetz/library-generation (MIT), and plate and building-block definitions there may help map wells to reactants. Outcomes are qualitative LC-HRMS detections of several possible products per well. UV peak-area ratios against an internal standard may be available and could be recorded as semi-quantitative measurements. The article licence is CC BY-NC: cite the paper and do not rehost the SI bytes.",
  "verification_caveats": "Qualitative multi-product outcomes: each well can form several products, which need SMILES and presence or absence per product. Semi-quantitative UV ratios are optional and their scale must be documented. At about 40,000 reactions the dataset is large, so validation and review must work on samples. Plate or well provenance must be kept. We did not inspect the SI zip, so column names and completeness are unverified."
}