{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001318593,0.0009906981,0.0009079795,0.003079647,0.0006650428,0.000994385,0.001159296,0.000647576,0.002931454],"category_scores_gemma":[0.003824182,0.0001799149,0.0008604103,0.003567697,0.0004878346,0.0008848032,0.000776872,0.0005669781,0.0007412875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007126762,"about_ca_system_score_gemma":0.001446294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002060206,"about_ca_topic_score_gemma":0.002604349,"domain_scores_codex":[0.9990946,0.0001918566,0.00008449216,0.0001558164,0.0003849819,0.00008834316],"domain_scores_gemma":[0.9984748,0.0005943999,0.0001325633,0.0002526277,0.0004176435,0.0001278882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003597897,0.004782736,0.03472908,0.005936504,0.000850855,0.001696585,0.0002623619,0.291878,0.2036182,0.01470265,0.04288836,0.3950568],"study_design_scores_gemma":[0.001087563,0.007830234,0.04587392,0.0002760954,0.0004632175,0.002929819,0.0006167478,0.5461575,0.2772122,0.01143218,0.1059201,0.0002004452],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8748398,0.005682951,0.04599996,0.0004657829,0.000103995,0.001212364,0.05157544,0.002217034,0.0179027],"genre_scores_gemma":[0.7006287,0.002800855,0.1147545,0.0002807329,0.00005263675,0.00142152,0.175509,0.00025813,0.004293965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003079647,"threshold_uncertainty_score":0.009806693,"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."}}