{
  "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=132979986",
  "ord_data_issue": null,
  "title": "Swarm intelligence for chemical reaction optimization",
  "doi": "10.1016/j.chempr.2026.103035",
  "journal": "Chem",
  "publication_date": "2026-09",
  "authors": [
    "Rémi Schlama",
    "Joshua W. Sin",
    "Ryan P. Burwood",
    "Kurt Püntener",
    "Raphael Bigler",
    "Philippe Schwaller"
  ],
  "article_open_access": {
    "status": "open",
    "license": "CC BY 4.0",
    "source": "Crossref version-of-record license metadata, checked 2026-10-14"
  },
  "dataset_size_estimate": 989,
  "experiment_type": null,
  "ord_priority": "High",
  "ord_difficulty": "Easy",
  "source_data_kind": "open_repository_machine_readable",
  "smiles_in_source": "partial",
  "needs_author_contact": false,
  "data_locations": [
    {
      "url": "https://github.com/schwallergroup/alphaswarm/tree/master/data/HTE_datasets",
      "what": "Two SURF-format CSVs. pd_sulfonamide_SURF.csv has 585 rows and pd_suzuki_SURF.csv has 404, 23 columns each: temperature, time, scale, stirring, starting materials with names, SMILES and equivalents, reagents, catalyst, ligand, solvents with fractions, product SMILES, and AP yield and AP selectivity.",
      "license": "MIT (repository license)"
    },
    {
      "url": "https://github.com/bdeadman/surf",
      "what": "Fork of alexarnimueller/surf that the ORD curator notes name for SURF-to-ORD conversion",
      "license": "MIT"
    },
    {
      "url": "https://doi.org/10.1016/j.chempr.2026.103035",
      "what": "Journal version (Chem, 2026), 'Swarm intelligence for chemical reaction optimization'. Crossref lists CC BY 4.0 among its licenses.",
      "license": "CC BY 4.0 (per Crossref)"
    },
    {
      "url": "https://arxiv.org/abs/2509.11798",
      "what": "arXiv preprint (DOI on the wishlist card)",
      "license": "unknown"
    }
  ],
  "notes": "Data: https://github.com/schwallergroup/alphaswarm/tree/master/data/HTE_datasets (MIT). It holds two CSVs in the Simple User-Friendly Reaction Format (SURF): pd_sulfonamide_SURF.csv (585 Pd-catalysed sulfonamide N-arylations) and pd_suzuki_SURF.csv (404 Pd-catalysed Suzuki couplings), 989 reactions in total. Starting materials and products carry SMILES. Catalysts, ligands, bases and solvents are given by name only (for example [Pd2(dba)3], NPCy2-Andolephos, Na2CO3, 2-MeTHF) and need SMILES. Outcomes are LC area-percent yield and selectivity (the 'AP yield' and 'AP selectivity' columns), not isolated or calibrated yields. Encode them accordingly. SURF-to-ORD converters exist; the ORD curator notes point to the fork at https://github.com/bdeadman/surf. Import only data/HTE_datasets. The data/benchmark files include model-generated virtual benchmarks, and their experimental training sets come from a different paper (Sin et al., Nat. Commun. 2025, 10.1038/s41467-025-61803-0). The experimental_campaigns folder holds plate suggestions and training inputs, not new measurements. The work is now published in Chem (https://doi.org/10.1016/j.chempr.2026.103035, CC BY 4.0), and the card lists arXiv 2509.11798. For dataset provenance this revision explicitly accepts either the published journal DOI 10.1016/j.chempr.2026.103035 or the preprint DOI 10.48550/arXiv.2509.11798 for this same work. Both are bound in allowed_dois.",
  "verification_caveats": "Yields are area-percent values from LC. Two reaction templates (sulfonamide coupling and Suzuki) must be included together in one submitted dataset. Reagent and catalyst SMILES must be added from names. Many rows have 0.000 yield, which is valid negative data. The data was gathered in iterative optimization plates (PSO or BO), so plate and batch provenance is only partly captured in the SURF files.",
  "wishlist_bibliography_at_snapshot": {
    "doi": "10.48550/arXiv.2509.11798",
    "journal": "arXiv",
    "publication_date": "2025-09-15",
    "article_open_access": {
      "status": "green",
      "license": null
    }
  },
  "allowed_dois": [
    "10.1016/j.chempr.2026.103035",
    "10.48550/arXiv.2509.11798"
  ]
}