{"id":"W1973328576","doi":"10.1016/j.febslet.2006.02.003","title":"A complete small molecule dataset from the protein data bank","year":2006,"lang":"en","type":"article","venue":"FEBS Letters","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"","keywords":"Protein Data Bank; PubChem; Molecule; Ligand (biochemistry); Chemistry; Set (abstract data type); Small molecule; Data set; Monomer; Computer science; Aromaticity; Data mining; Crystallography; Protein structure; Artificial intelligence; Biochemistry; Receptor; Organic chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009685034,0.0001520629,0.00009934654,0.00001042357,0.00009938666,0.00005595763,0.0009166097,0.00007339096,0.00001944329],"category_scores_gemma":[0.00002852068,0.0001133207,0.00003567736,0.00005013209,0.00009690101,0.000004555428,0.0004978818,0.0001125221,0.00002383163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006764435,"about_ca_system_score_gemma":0.00002356285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001269614,"about_ca_topic_score_gemma":0.0007970297,"domain_scores_codex":[0.9990103,0.00006597971,0.0001503619,0.0004328879,0.0001107284,0.0002297716],"domain_scores_gemma":[0.9984038,0.00001215562,0.00006698632,0.001471866,0.00001289755,0.00003226091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002825281,0.00001034058,0.0003024319,0.000003295756,0.0000282255,0.00001096579,0.000003602176,0.00002877018,0.8429965,0.00008144544,0.1562624,0.000243795],"study_design_scores_gemma":[0.0006870026,0.00005067375,0.003737214,0.00001588631,0.00004205102,0.00001376343,0.0000100695,0.0005531709,0.06634742,0.0003246201,0.9278337,0.0003844018],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9436893,0.0006200802,0.02325097,0.00819004,0.0001306911,0.0005676001,0.02316962,0.0000251494,0.0003565505],"genre_scores_gemma":[0.7782081,0.000008960502,0.008568805,0.02183358,0.001349551,0.00004948341,0.1898142,0.00004602638,0.00012134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7766491,"threshold_uncertainty_score":0.4621084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01653860743476964,"score_gpt":0.2243197527190075,"score_spread":0.2077811452842378,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}