{"dataset_distribution":[{"entry_count":99257,"name":"pKaHub_combined","unique_smiles":33377},{"entry_count":22589,"name":"IUPAC_high_confidence_v2.3","unique_smiles":9930},{"entry_count":9721,"name":"Leito_2025_non_aqueous","unique_smiles":100},{"entry_count":8233,"name":"D2A-pKa","unique_smiles":6475},{"entry_count":6835,"name":"EX_CSV_enriched","unique_smiles":6722},{"entry_count":1620,"name":"PKAD-2","unique_smiles":0},{"entry_count":690,"name":"DrugBank","unique_smiles":0},{"entry_count":83,"name":"zenodo_prediction_ref_values","unique_smiles":40},{"entry_count":83,"name":"zenodo_prediction_calc_values","unique_smiles":40},{"entry_count":78,"name":"PKAD-R","unique_smiles":0}],"np_distribution":[{"cnt":267,"np_superclass":"Small peptides"},{"cnt":184,"np_superclass":"Fatty Acids and Conjugates"},{"cnt":107,"np_superclass":"Fatty acyls"},{"cnt":100,"np_superclass":"Lysine alkaloids"},{"cnt":58,"np_superclass":"Ornithine alkaloids"},{"cnt":50,"np_superclass":"Saccharides"},{"cnt":32,"np_superclass":"Fatty esters"},{"cnt":24,"np_superclass":"Monoterpenoids"},{"cnt":19,"np_superclass":"Peptide alkaloids"},{"cnt":15,"np_superclass":"Aminosugars and aminoglycosides"},{"cnt":14,"np_superclass":"Pseudoalkaloids"},{"cnt":14,"np_superclass":"Oligopeptides"},{"cnt":12,"np_superclass":"Steroids"},{"cnt":12,"np_superclass":"Macrolides"},{"cnt":7,"np_superclass":"\u03b2-lactams"},{"cnt":6,"np_superclass":"Triterpenoids"},{"cnt":6,"np_superclass":"Naphthalenes"},{"cnt":5,"np_superclass":"Histidine alkaloids"},{"cnt":5,"np_superclass":"Fatty amides"},{"cnt":4,"np_superclass":"Polyols"},{"cnt":4,"np_superclass":"Diterpenoids"},{"cnt":4,"np_superclass":"Cyclic polyketides"},{"cnt":3,"np_superclass":"Meroterpenoids"},{"cnt":3,"np_superclass":"Glycerophospholipids"},{"cnt":3,"np_superclass":"Eicosanoids"},{"cnt":3,"np_superclass":"Apocarotenoids"},{"cnt":2,"np_superclass":"Sesquiterpenoids"},{"cnt":2,"np_superclass":"Serine alkaloids"},{"cnt":2,"np_superclass":"Phenolic acids (C6-C1)"},{"cnt":2,"np_superclass":"Aromatic polyketides"}],"release":{"checks":{"legacy_numeric_ids_preserved":42782,"membership_group_sizes_agree":true,"membership_rows":150994,"original_fields_preserved":174082,"unique_source_ids":174082},"downloads":[{"bytes":6658111,"file":"all_source_rows_with_decisions.csv.gz","sha256":"cabfde1be396eff6ff3ad320fc75b0af2f9caf4024f6aa246375b0aef8320c40","url":"/static/data/v3-2026-10-13/all_source_rows_with_decisions.csv.gz"},{"bytes":5768447,"file":"eligible_source_rows.csv.gz","sha256":"890d9ed7384a76c615040f1f2a34afe8c9875ece66067f5b5f3bfa14525225e2","url":"/static/data/v3-2026-10-13/eligible_source_rows.csv.gz"},{"bytes":8799290,"file":"pkaatlas_v3_candidate_records.csv.gz","sha256":"3f933fe3edbe29bb3114f143eb363a0250999b191c2046ed034afd445b7bb366","url":"/static/data/v3-2026-10-13/pkaatlas_v3_candidate_records.csv.gz"},{"bytes":816397,"file":"quarantined_rows.csv.gz","sha256":"81ff22966c13882bb28c438c9bd7e817fed01a6790d132d24815db8fa1b38322","url":"/static/data/v3-2026-10-13/quarantined_rows.csv.gz"},{"bytes":4547239,"file":"source_row_membership.csv.gz","sha256":"703b44f8fe057f234af361f10d91b0605b574f20595a0bedbfb86d8f568a0507","url":"/static/data/v3-2026-10-13/source_row_membership.csv.gz"},{"bytes":302810,"file":"identity_resolution_queue.csv.gz","sha256":"4e2c262b14541dc523d178b6aefbfbbf77934d88ed80fae90e952da8da8bd6bc","url":"/static/data/v3-2026-10-13/identity_resolution_queue.csv.gz"},{"bytes":15650,"file":"source_qc_ambiguous_keys.csv.gz","sha256":"4f143b0e467713f0c38e37b98812b2c51f5dd52125469dd2bd6ed05650856132","url":"/static/data/v3-2026-10-13/source_qc_ambiguous_keys.csv.gz"}],"entity_counts":{"protein_site_context":1612,"structure_defined":39974,"unresolved_record":10380},"field_population":{"coconut_id":13831,"doi":149189,"np_superclass":10570,"reference":149186,"structure_smiles":137111,"temperature_numeric_c":73801},"inherited_grade_counts":{"A":7289,"B":128786,"C":13031,"D":83},"inherited_type_counts":{"experimental":149106,"predicted":83},"input_hashes":{"enriched_pka_database_with_pubyear.csv":"49ada355a6a24a3f3379168f2bb02f8ba8d0656da0c27876a65be0b12b4d67a4","pkahub_combined_unified_dataset.tsv":"32388da61546dc0a2cd56147d7d12c0aff72f107694a92e1d36529cc65e992ad"},"license":"Upstream source-specific terms apply; no blanket data license is granted.","manuscript_versions":["10.18","10.19"],"original_publication_year_range":[1889,1973],"original_publication_year_records":22305,"pka_range":[-19.3,70.0],"published":"2026-10-29","record_identity_counts":{"protein_site_context":1698,"structure_defined":137111,"unresolved_record":10380},"representative_solvent_counts":{"1,2-dichloroethane":22,"DMF":2257,"DMSO":7364,"N-methylpyrrolidone":28,"THF":552,"acetone":696,"acetonitrile":2255,"ethanol":205,"ethylene glycol":22,"methanol":455,"nitromethane":42,"propylene carbonate":83,"pyridine":344,"water":134864},"representative_source_counts":{"10.1021/acs.jcim.5b00120":5628,"10.1021/acs.jcim.6c00107":99257,"10.1021/ci800162h":181,"10.1021/jacs.5c02578":8233,"10.1093/nar/gkae255":1620,"10.1093/nar/gkx1037":690,"10.1093/nar/gky1075":708,"10.1142/s2737416525500164":78,"10.5281/zenodo.11225612":166,"10.5281/zenodo.12608876":9721,"10.5281/zenodo.7236452":22907},"representatives_requiring_review":10936,"review_status":"Processing integrity verified; inherited source, identity, grade and permission review annotations retained.","scopes":{"all":174082,"eligible":150994,"quarantine":23088,"representatives":149189},"sequential_qc":[{"input_rows":174082,"newly_quarantined":888,"output_rows":173194,"rule_hits_including_overlaps":888,"step":"pka_non_numeric_or_empty"},{"input_rows":173194,"newly_quarantined":4,"output_rows":173190,"rule_hits_including_overlaps":4,"step":"pka_impossible"},{"input_rows":173190,"newly_quarantined":1,"output_rows":173189,"rule_hits_including_overlaps":5,"step":"pka_water_impossible"},{"input_rows":173189,"newly_quarantined":1536,"output_rows":171653,"rule_hits_including_overlaps":1561,"step":"temp_invalid"},{"input_rows":171653,"newly_quarantined":11010,"output_rows":160643,"rule_hits_including_overlaps":11010,"step":"pkahub_solvent_unlabeled_nonwater"},{"input_rows":160643,"newly_quarantined":2639,"output_rows":158004,"rule_hits_including_overlaps":2639,"step":"pkahub_cosolvent_mixed"},{"input_rows":158004,"newly_quarantined":5073,"output_rows":152931,"rule_hits_including_overlaps":5073,"step":"pkahub_assignment_outlier"},{"input_rows":152931,"newly_quarantined":1305,"output_rows":151626,"rule_hits_including_overlaps":1305,"step":"pkahub_suspicious_remark"},{"input_rows":151626,"newly_quarantined":632,"output_rows":150994,"rule_hits_including_overlaps":637,"step":"pkahub_assignment_error_large"},{"input_rows":150994,"newly_quarantined":0,"output_rows":150994,"rule_hits_including_overlaps":690,"step":"pkahub_value_unparseable"},{"input_rows":150994,"newly_quarantined":0,"output_rows":150994,"rule_hits_including_overlaps":0,"step":"pkahub_inequality_value"}],"source_sha256":{"all_source_rows_with_decisions.csv":"b9e3c9c03694d09801251ea7e76c930268bb11c1d8fe87b6ecdcb360e0920fd2","identity_resolution_queue.csv":"238552bcbdca685186988474eaf63379f2848c00ec09a0df06a1c86eeefcbf2d","pkaatlas_v3_candidate_records.csv":"2836efd9facd950a29c9c2dff5e0765cb62f15da833d634c4e2574ed523720f5","quarantined_rows.csv":"c2b925e3b5e137313e23d098e0dbafca8adf45c42c868d9689119cc8e1c9442c","source_qc_ambiguous_keys.csv":"8132a4ff744ddcc7ee295918cb847a960a424105f5572a09f061fa312ecc9311","source_row_membership.csv":"d4dba31815a7def65cabd5d019c40af93f29dd9c8414a5fdb2e1e0371a4db311"},"version":"v3-2026-10-13","within_source_rows_collapsed":1805},"solvent_distribution":[{"cnt":134864,"solvent":"water"},{"cnt":7364,"solvent":"DMSO"},{"cnt":2257,"solvent":"DMF"},{"cnt":2255,"solvent":"acetonitrile"},{"cnt":696,"solvent":"acetone"},{"cnt":552,"solvent":"THF"},{"cnt":455,"solvent":"methanol"},{"cnt":344,"solvent":"pyridine"},{"cnt":205,"solvent":"ethanol"},{"cnt":83,"solvent":"propylene carbonate"},{"cnt":42,"solvent":"nitromethane"},{"cnt":28,"solvent":"N-methylpyrrolidone"},{"cnt":22,"solvent":"ethylene glycol"},{"cnt":22,"solvent":"1,2-dichloroethane"}],"stats":{"acquisition_label_groups":11,"count_grade_a":7289,"count_grade_b":128786,"count_grade_c":13031,"count_grade_d":83,"dataset_version":"v3-2026-10-13","entries_with_pub_year":22305,"experimental_label_records":149106,"pka_range_max":70.0,"pka_range_min":-19.3,"predicted_label_records":83,"protein_context_keys":1612,"pub_year_max":1973,"pub_year_min":1889,"total_compounds":39974,"total_eligible_source_rows":150994,"total_measurements":149189,"total_np_compounds":1362,"total_quarantined_rows":23088,"total_source_rows":174082,"unique_datasets":10,"unique_solvents":14,"unresolved_records":10380}}
