{"database": "scout", "private": false, "path": "/scout", "size": 116158464, "tables": [{"name": "aptamer_costructures", "columns": ["pdb_id", "title", "keywords", "resolution_A", "pmid", "doi", "experimental_method"], "primary_keys": [], "count": 114, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "db_meta", "columns": ["key", "value"], "primary_keys": [], "count": 7, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "db_stats", "columns": ["ord", "metric", "value", "grade", "definition", "source"], "primary_keys": [], "count": 23, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "ev_map_conserved", "columns": ["gene_name", "feature", "category", "misev_marker", "entrezgene_id", "pevs_median", "in_apt_scout", "apt_scout_uniprot"], "primary_keys": [], "count": 224, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "kd_measurements", "columns": ["id", "source_pmid", "aptamer_name", "target_name_canonical", "target_uniprot", "kd_value", "kd_unit", "kd_log10_molar", "binding_constant_type", "aptamer_chemistry", "aptamer_modifications", "assay_method", "assay_buffer", "assay_ph", "assay_temperature_k", "assay_cations", "verification_status", "source_db", "source_record_id", "aptamer_seq", "aptamer_seq_raw", "measurement_class", "verbatim_quote", "seq_source", "tier", "sequence_status", "pi_provenance_flag", "include_in_gold", "doi"], "primary_keys": ["id"], "count": 743, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "kd_structure_crossmatch", "columns": ["target", "n_kd_records", "n_structures", "pdb_ids"], "primary_keys": [], "count": 33, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "membrane_surface_class", "columns": ["target_id", "surface_class", "is_surface_accessible", "surface_evidence"], "primary_keys": ["target_id"], "count": 7197, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "sqlite_sequence", "columns": ["name", "seq"], "primary_keys": [], "count": 1, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_aptamer_pmids", "columns": ["target_id", "aptamer_pmids", "aptamer_pubmed_query"], "primary_keys": ["target_id"], "count": 7197, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_layer1_structure", "columns": ["target_id", "pdb_count_total", "pdb_count_detailed", "pdb_best_resolution_A", "alphafold_mean_pLDDT", "alphafold_model_count", "emdb_count", "has_cryoEM", "has_xray", "has_NMR", "raw_json", "recorded_utc"], "primary_keys": ["target_id"], "count": 7197, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_layer2_modification", "columns": ["target_id", "ptm_count", "ptm_phospho_count", "ptm_glyco_count", "ptm_ubiq_count", "has_activation_state_pdb_pair", "activation_state_pdb_active", "activation_state_pdb_inactive", "conformational_states_count", "raw_json", "recorded_utc"], "primary_keys": ["target_id"], "count": 7197, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_layer3_interaction", "columns": ["target_id", "ppi_count", "drug_count_approved", "drug_count_clinical", "aptamer_count_pubmed", "aptamer_count_aptagen", "antibody_count_hpa", "has_known_aptamer", "raw_json", "recorded_utc"], "primary_keys": ["target_id"], "count": 7197, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_layer4_expression", "columns": ["target_id", "hpa_tissue_count", "hpa_tissue_jsons", "gtex_protein_id", "ev_proteome_pride_id", "in_vesiclepedia", "in_exocarta", "in_cev_map", "raw_json", "recorded_utc", "cev_map_in", "cev_map_is_ev_hallmark", "cev_map_is_nonev_hallmark", "cev_map_conservation_pct", "cev_map_isolation", "cev_map_detection", "cev_map_n_samples", "cev_map_source_doi"], "primary_keys": ["target_id"], "count": 7198, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_layer5_disease", "columns": ["target_id", "opentargets_top_disease_name", "opentargets_top_disease_score", "opentargets_disease_count", "omim_count", "clinvar_pathogenic_count", "ev_biomarker_disease", "ev_biomarker_pubmed_count", "raw_json", "recorded_utc", "clinvar_likely_pathogenic_count", "clinvar_benign_count", "clinvar_vus_count"], "primary_keys": ["target_id"], "count": 7197, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "target_names", "columns": ["target_id", "gene_symbol", "protein_name"], "primary_keys": [], "count": 7198, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "targets", "columns": ["id", "target_type", "seed_source", "status", "priority_score", "added_utc", "started_utc", "completed_utc", "error", "tier", "worker_host"], "primary_keys": ["id"], "count": 7198, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "verification_human", "columns": ["row_id", "verdict", "checker", "checked_utc", "note"], "primary_keys": [], "count": 0, "hidden": false, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "citations", "columns": ["target_id", "citation_type", "citation_value", "source_layer", "extracted_utc"], "primary_keys": ["target_id", "citation_type", "citation_value", "source_layer"], "count": 19231, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "llm_curation_kappa", "columns": ["batch_id", "table_name", "field_name", "kappa_ab", "kappa_ac", "kappa_bc", "fleiss_kappa", "n_records", "n_agreement_AAA", "n_agreement_2of3", "n_agreement_ABC", "computed_utc"], "primary_keys": ["batch_id", "table_name", "field_name"], "count": 0, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "llm_curation_log", "columns": ["id", "target_id", "table_name", "field_name", "llm_a_id", "llm_a_value", "llm_a_raw_response", "llm_b_id", "llm_b_value", "llm_b_raw_response", "llm_c_id", "llm_c_value", "llm_c_raw_response", "consensus_value", "agreement_pattern", "decision_method", "timestamp_utc", "batch_id"], "primary_keys": ["id"], "count": 0, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "llm_curation_quarantine", "columns": ["target_id", "triggered_field", "triggered_batch", "triggered_utc", "reviewed_by_human", "reviewed_utc", "resolution"], "primary_keys": ["target_id"], "count": 0, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}], "hidden_count": 4, "views": [{"name": "v_target_full", "private": false}, {"name": "v_targets_by_tier", "private": false}, {"name": "v_citations", "private": false}, {"name": "v_kd", "private": false}, {"name": "v_surface_targets", "private": false}, {"name": "v_targets", "private": false}], "queries": [{"title": "Kd \u2014 intrinsic, tightest binders", "description": "Verbatim-verified intrinsic equilibrium Kd, tightest first. NOTE: the same aptamer\u00d7target can appear in several rows at DIFFERENT temperatures/assays \u2014 see assay_temperature_k (K) and assay_method. Compare on kd_log10_molar only.", "sql": "SELECT target_name_canonical, target_type, aptamer_name, kd_reported, kd_log10_molar, assay_method, assay_temperature_k, source_pmid, verbatim_quote FROM v_kd WHERE measurement_class='intrinsic' AND kd_log10_molar IS NOT NULL ORDER BY kd_log10_molar ASC", "name": "kd_intrinsic_strong", "private": false}, {"title": "Kd \u2014 all source-verified measurements", "description": "All Gold-tier aptamer\u2013target Kd records with verbatim quote + measurement class. Use facets to filter to intrinsic vs apparent/avidity.", "sql": "SELECT target_name_canonical, target_type, aptamer_name, kd_reported, kd_log10_molar, measurement_class, assay_method, assay_temperature_k, source_pmid, verbatim_quote FROM v_kd ORDER BY kd_log10_molar ASC", "name": "kd_all", "private": false}, {"title": "Activation-state-selective targets", "description": "Targets with a curated ACTIVE vs INACTIVE PDB pair. Click the PDB IDs to verify at RCSB.", "sql": "SELECT id, gene_symbol, protein_name, activation_state_pdb_active, activation_state_pdb_inactive, opentargets_top_disease_name, evidence_priority FROM v_targets WHERE has_activation_state_pdb_pair=1 ORDER BY evidence_priority DESC", "name": "activation_selective", "private": false}, {"title": "EV-associated targets with known aptamers", "description": "EV-Map circulating-EV proteins that also have known aptamer evidence.", "sql": "SELECT id, gene_symbol, protein_name, in_cev_map, aptamer_count_pubmed, opentargets_top_disease_name, evidence_priority FROM v_targets WHERE has_known_aptamer=1 AND in_cev_map=1 ORDER BY evidence_priority DESC", "name": "ev_with_aptamer", "private": false}, {"title": "Top-priority targets", "description": "Top 100 targets by apt-scout composite priority score.", "sql": "SELECT id, gene_symbol, protein_name, tier, evidence_priority, has_structure, pdb_count_total, has_activation_state_pdb_pair, has_known_aptamer, opentargets_top_disease_name FROM v_targets ORDER BY evidence_priority DESC LIMIT 100", "name": "top_priority", "private": false}, {"title": "Kd \u2014 ready-to-use subset (intrinsic, protein, 1 per aptamer\u00d7target)", "description": "Benchmark / reference subset (NOT a training set): intrinsic-equilibrium only, protein targets only, one row per (target, aptamer) taking the tightest reported kd_log10_molar, with the number of underlying measurements. A clean, comparable, provenance-verified set that ENABLES/benchmarks modelling; sort on kd_log10_molar (do not use mixed-unit reported values).", "sql": "SELECT target_name_canonical, aptamer_name, MIN(kd_log10_molar) AS kd_log10_molar, COUNT(*) AS n_measurements, MIN(source_pmid) AS example_pmid FROM v_kd WHERE measurement_class='intrinsic' AND target_type='protein' AND kd_log10_molar IS NOT NULL GROUP BY target_name_canonical, aptamer_name ORDER BY kd_log10_molar ASC", "name": "kd_ready_to_use", "private": false}, {"title": "EV-Map conserved EV-hallmark proteins in apt-scout (104 of 182)", "description": "The EV-Map conserved EV-hallmark proteins that are apt-scout targets (104 of the source's 182). See ev_map_conserved for the full 182+42 with coverage.", "sql": "SELECT gene_name, apt_scout_uniprot, category FROM ev_map_conserved WHERE feature='EV-hallmark' AND in_apt_scout=1 ORDER BY gene_name", "name": "ev_hallmark_targets", "private": false}, {"title": "EV-surface aptamer candidates (surface ecto \u00d7 EV-Map hallmark), ranked", "description": "Cell-surface ecto proteins that are ALSO EV-Map conserved EV-hallmark proteins \u2014 the top set of targets reachable by an aptamer on an intact circulating EV. Ranked by targetability_score.", "sql": "SELECT gene_symbol, protein_name, surface_class, targetability_score, pdb_count, top_disease, disease_score, surface_evidence FROM v_surface_targets WHERE surface_class='A_surface' AND ev_map_hallmark=1 ORDER BY targetability_score DESC", "name": "ev_surface_candidates", "private": false}, {"title": "Surface vs cargo \u2014 class counts (why the split matters)", "description": "How the human target universe splits by EV accessibility. Only A_surface (ecto) is reachable by an aptamer on an intact EV; A2 sits at the PM but faces the cytoplasm; B is luminal cargo.", "sql": "SELECT surface_class, COUNT(*) AS n, CASE surface_class WHEN 'A_surface' THEN 'integral/ecto cell-surface \u2014 EV-surface accessible' WHEN 'A2_pm_peripheral' THEN 'plasma-membrane but cytoplasmic leaflet \u2014 NOT accessible' WHEN 'A_assoc' THEN 'secreted / surface corona' WHEN 'B_cargo' THEN 'luminal cargo (inside EV)' ELSE 'no HPA localization' END AS meaning FROM membrane_surface_class GROUP BY surface_class ORDER BY n DESC", "name": "surface_vs_cargo_split", "private": false}], "allow_execute_sql": true, "query_ms": 136.84565527364612, "source": "apt-scout automated curation pipeline (E. Dohi, NCNP) \u2014 values harvested from public databases; raw source stored per target", "source_url": "https://apt-scout.org", "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}