JSON source · original UTF-8 line locators · 4.1 KiB
{
"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=126569965",
"ord_data_issue": null,
"title": "Streamlining the Automated Discovery of Porous Organic Cages",
"doi": "10.26434/chemrxiv-2023-63ckv",
"journal": "ChemRxiv",
"publication_date": "2023-11-16",
"authors": [
"Annabel R. Basford",
"Steven P. Bennett",
"Muye Xiao",
"Lukas Turcani",
"Jasmine Allen",
"Kim E. Jelfs",
"Rebecca L. Greenaway"
],
"article_open_access": {
"status": "green",
"license": "cc-by"
},
"dataset_size_estimate": 366,
"experiment_type": "HTE",
"ord_priority": null,
"ord_difficulty": null,
"source_data_kind": "open_repository_machine_readable",
"smiles_in_source": "partial",
"needs_author_contact": false,
"data_locations": [
{
"url": "https://github.com/GreenawayLab/Streamlining-Automated-Discovery-POCs",
"what": "Code repo: precursor_combination_map_to_exp_data.json (366 combos A1-U34 -> experiment code/plate/formulation + raw-data paths) and HT_Cage_Assembly_Optimisation/precursors.json (precursor codes Di*/Tri* -> SMILES); Opentrons protocols with substance_locations.json",
"license": "none declared (no LICENSE file; GitHub license API 404)"
},
{
"url": "https://zenodo.org/records/10675206",
"what": "Experimental data (version cited by Chem Sci): precursor_combination_map_to_exp_data.json (129 KB), nmr.zip (211 MB), ms.zip (4.0 GB), turbidity.zip (1.4 GB)",
"license": "CC-BY-4.0"
},
{
"url": "https://zenodo.org/records/10138085",
"what": "Earlier data version: precursor_positions.json (8 KB plate layouts by experiment code) plus the same raw NMR/HRMS/turbidity zips",
"license": "CC-BY-4.0"
},
{
"url": "https://europepmc.org/article/PMC/PMC11062116",
"what": "Chem Sci 2024 article (doi 10.1039/D3SC06133G) and its ESI PDF (SC-015-D3SC06133G-s001.pdf); probable source of per-combination outcome labels. Only the filename was listed; contents not inspected",
"license": "CC-BY-3.0 (article, per Crossref)"
},
{
"url": "https://doi.org/10.26434/chemrxiv-2023-63ckv",
"what": "ChemRxiv preprint (the DOI on the wishlist card)",
"license": "CC-BY-4.0 (per Crossref)"
}
],
"notes": "Self-assembled porous organic cage synthesis (imine condensation of di-/tri-topic aldehydes and amines) run by HTE on an Opentrons platform: 366 precursor combinations (codes A1-U34). The preprint (doi 10.26434/chemrxiv-2023-63ckv, CC-BY 4.0) was published as Chem. Sci. 2024, doi 10.1039/D3SC06133G (CC-BY 3.0); the dataset should cite the journal DOI. Inputs: GitHub GreenawayLab/Streamlining-Automated-Discovery-POCs, where HT_Cage_Assembly_Optimisation/precursors.json maps precursor codes to SMILES and precursor_combination_map_to_exp_data.json maps each combination to experiment code, plate and well. The repo has no license file, so bind the copies on Zenodo 10.5281/zenodo.10675206 (CC-BY-4.0) instead, together with precursor_positions.json from Zenodo 10.5281/zenodo.10138085. Raw NMR/HRMS/turbidity archives are large (0.2-4 GB); do not bind them, only reference them. Outcome labels (cage formation and purity by 1H NMR/HRMS, solubility by turbidity) are not in the mapping JSON and must be taken from the paper and ESI PDF. Conditions (solvent, concentration, temperature, time, stoichiometry) come from the ESI experimental section.",
"verification_caveats": "Outcomes are qualitative/categorical (cage formed, clean, soluble), not yields. Product cage structures (topology such as Tri2Di3 / Tri4Di6) may be assigned only by HRMS mass, so product SMILES may be absent or ambiguous. The reactions are plate-based, and the well-to-combination mapping must be joined across the two JSON files. Precursor codes use mixed SMILES styles (some Kekul\u00e9, some stereo) that need canonicalisation.",
"allowed_dois": [
"10.26434/chemrxiv-2023-63ckv",
"10.1039/D3SC06133G"
]
}