MitoInteract / recovery /reports /bindingdb-source-aware-audit.json
Ethan Troy
feat: add source-aware BindingDB recovery track
9ae8d85
Raw
History Blame Contribute Delete
3.51 kB
{
"coverage": {
"records_missing_assay_join": 695,
"records_with_assay_join": 86620,
"records_with_citation_doi_or_pmid": 86764,
"records_with_publication_date": 87315
},
"duplicates": {
"duplicate_pairs_across_assays": 4531,
"duplicate_reactant_set_ids": 122,
"extra_assay_instances": 6624,
"extra_reactant_set_rows": 190,
"pairs_with_multiple_measurement_types": 4531
},
"emitted_records": {
"by_relation": {
"<": 451,
"=": 75971,
">": 10893
},
"by_type": {
"EC50": 4144,
"IC50": 55805,
"Kd": 2615,
"Ki": 24751
},
"by_type_relation": {
"EC50|<": 7,
"EC50|=": 3753,
"EC50|>": 384,
"IC50|<": 306,
"IC50|=": 48288,
"IC50|>": 7211,
"Kd|<": 7,
"Kd|=": 2455,
"Kd|>": 153,
"Ki|<": 131,
"Ki|=": 21475,
"Ki|>": 3145
},
"total": 87315
},
"exact_gold_kd_records": 2432,
"gold_exact_kd": {
"pkd_above_12_review_flag": 3,
"pkd_below_3_review_flag": 47,
"pkd_max": 13.327902142064282,
"pkd_min": 1.1146161610532512,
"records": 2432,
"review_flags_are_not_filters": true,
"unique_assays": 245,
"unique_pairs": 2198,
"unique_proteins": 442
},
"ordering": "stable source order: main-TSV row order, then Reactant_set_id assay mapping order, then fixed measurement-type order Ki, IC50, Kd, EC50",
"outputs": {
"gold_exact_kd.jsonl": {
"bytes": 7768913,
"records": 2432,
"sha256": "432507f29163acf37c7c74e62c3bba47b1dff02a38e34945c1b06cac14c7282e"
},
"source_records.jsonl": {
"bytes": 387594449,
"records": 87315,
"sha256": "1e9963217b9ed65528ca477adcba66beea1fa341a1c1c6d41cd789332ab85bbb"
}
},
"rejections": {
"cell_level": {},
"gold_excluded": {
"missing_assay_join": 23,
"non_exact_relation": 160,
"non_kd_type": 84700
},
"gold_exclusion_reasons_are_nonexclusive": true,
"row_level": {
"invalid_smiles": 740,
"missing_smiles": 56,
"multichain_target": 8157,
"no_supported_measurement": 1105
},
"rows_flagged_invalid_smiles": 796,
"rows_flagged_missing_sequence": 0,
"rows_flagged_multichain": 8157
},
"rows_with_emitted_measurements": 83654,
"schema_version": "bindingdb-source-envelope/v1",
"source_database": "BindingDB",
"source_release": "202607",
"source_release_files": {
"assays_zip": {
"member": "BindingDB_Assays.tsv",
"sha256": "27cc219d3fc9517eba5cbcaf7cdac1c3065371e06e62d3e5bd147dd3e0cd3e12",
"url": "https://www.bindingdb.org/rwd/bind/downloads/BindingDB_Assays_202607_tsv.zip",
"zip_name": "BindingDB_Assays_202607_tsv.zip"
},
"main_zip": {
"member": "BindingDB_BindingDB_Articles.tsv",
"sha256": "d2584d1519318d00ab5f46289da5ab3549affe732d598a5072f8777b6b3b5262",
"url": "https://www.bindingdb.org/rwd/bind/downloads/BindingDB_BindingDB_Articles_202607_tsv.zip",
"zip_name": "BindingDB_BindingDB_Articles_202607_tsv.zip"
},
"mapping_zip": {
"member": "BindingDB_rsid_eaids.tsv",
"sha256": "9bc94ffd13de2fdcfc40e6c73c8b81c9e745ca0103632545b7120a1f2247f84b",
"url": "https://www.bindingdb.org/rwd/bind/downloads/BindingDB_rsid_eaids_202607_tsv.zip",
"zip_name": "BindingDB_rsid_eaids_202607_tsv.zip"
}
},
"source_rows": 93712,
"uniques": {
"assays": 3125,
"ligands": 43413,
"pairs": 74994,
"proteins": 2210
}
}