{"id":"W4413343015","doi":"10.1021/acs.jcim.5c00719","title":"A Benchmark Set of Bioactive Molecules for Diversity Analysis of Compound Libraries and Combinatorial Chemical Spaces","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Chemical space; chEMBL; Benchmark (surveying); Cheminformatics; Pharmacophore; Set (abstract data type); Computer science; Chemical database; Data mining; Combinatorial chemistry; Drug discovery; Information retrieval; Chemistry; Bioinformatics; Computational chemistry; Biology; Stereochemistry; Organic chemistry; Geography","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":[0.0003195512,0.00006198203,0.0002733813,0.0002950813,0.00003833609,0.00006700451,0.0001743432,0.00004612654,5.411763e-7],"category_scores_gemma":[0.0001710904,0.00005512463,0.00009888886,0.0003223876,0.00006548962,0.001155103,0.0002848571,0.00007357525,9.877806e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001801748,"about_ca_system_score_gemma":0.00007973204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008131158,"about_ca_topic_score_gemma":8.514537e-8,"domain_scores_codex":[0.9992406,0.0000216445,0.0004346176,0.00005617839,0.0001872834,0.00005962868],"domain_scores_gemma":[0.9988634,0.0003644244,0.0003301895,0.00005676371,0.0003436469,0.00004155353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001565633,0.0002277423,0.002212235,0.0008168982,0.003282499,0.000001159826,0.0180364,0.3061928,0.03466688,0.6061066,0.000367932,0.02652317],"study_design_scores_gemma":[0.0005666352,0.00002427976,0.0000647436,0.00003606884,0.0001471502,0.000001846246,0.0002129979,0.9398463,0.02678466,0.03224301,0.00002473128,0.00004754706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.512161,0.00005693581,0.487485,0.0001631701,0.00004327926,0.00003005608,0.000008273643,0.000002041023,0.00005026831],"genre_scores_gemma":[0.9385323,0.00001518847,0.06138255,0.0000504229,0.00001032197,4.363326e-7,0.000007778272,6.835744e-7,2.950682e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6336535,"threshold_uncertainty_score":0.2247917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02544409565004288,"score_gpt":0.2962427450767079,"score_spread":0.270798649426665,"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."}}