AI4deeperScience's picture
Add files using upload-large-folder tool
6cf9dac verified
Raw
History Blame Contribute Delete
2.85 kB
{
"n_rows": 3776,
"columns": [
"record_index",
"SMILES",
"Lab",
"RT",
"canonical_smiles_isomeric",
"canonical_smiles_nonisomeric",
"inchi_key_full",
"inchi_key_connectivity",
"structure_group",
"scaffold_group",
"scaffold_component_group",
"fragment_count",
"formal_charge",
"has_explicit_stereo"
],
"n_laboratories": 23,
"laboratory_counts": {
"Aarhus": 179,
"Academy of Forensic Science": 186,
"Adelaide": 177,
"Australian Racing Forensic Laboratory": 90,
"CFSRE": 575,
"ChemCentre": 138,
"Copenhagen": 292,
"Estonian Forensic Science Institute": 72,
"Finnish Customs Laboratory": 114,
"Ghent University": 63,
"IUPA, UJI I (E)": 77,
"King's College Hospital": 106,
"LADR": 69,
"Labor Krone": 50,
"Mainz": 487,
"Odense": 43,
"San Francisco OCME": 466,
"The University of Queensland": 41,
"Trondheim": 41,
"University Hospital of Northern Norway": 42,
"University of Athens": 227,
"Victorian Institute of Forensic Medicine": 193,
"Zurich Institute of Forensic Medicine": 48
},
"unique_smiles_as_supplied": 1361,
"unique_canonical_isomeric_smiles": 1361,
"unique_canonical_nonisomeric_smiles": 1361,
"unique_full_inchi_keys": 1357,
"unique_connectivity_blocks": 1357,
"unique_raw_murcko_scaffold_groups": 350,
"unique_identity_safe_scaffold_components": 348,
"graph_conversion_failures_in_provided_csv": 0,
"upstream_curation_removals": "not inferable without the pre-curation export",
"identity_policy": {
"outer_group_key": "InChIKey connectivity block",
"fallback": "canonical non-isomeric SMILES when InChI generation fails",
"salt_handling": "no fragment removal or parent selection; fragment_count is recorded",
"stereochemistry_handling": "full identity is recorded; connectivity grouping conservatively co-groups stereoisomers",
"tautomer_handling": "no explicit tautomer canonicalizer; InChI connectivity grouping supplies the conservative boundary",
"protonation_handling": "no neutralization; supplied formal charge and full structure remain recorded"
},
"fragment_count_distribution": {
"1": 3776
},
"formal_charge_distribution": {
"0": 3776
},
"rows_with_explicit_stereo": 0,
"labs_per_structure_distribution": {
"1": 540,
"2": 283,
"3": 192,
"4": 104,
"5": 67,
"6": 51,
"7": 47,
"8": 22,
"9": 18,
"10": 16,
"11": 10,
"12": 5,
"13": 1,
"14": 1
},
"structures_seen_in_multiple_labs": 817,
"rows_in_multi_lab_structures": 3235,
"exact_duplicate_extra_rows": 3,
"structure_lab_duplicate_extra_rows": 13,
"structure_lab_groups_with_conflicting_rt": 10
}