{"id":"W4313816625","doi":"10.1002/minf.202200186","title":"A comparison between 2D and 3D descriptors in QSAR modeling based on bio‐active conformations","year":2023,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Quantitative structure–activity relationship; Cheminformatics; Random forest; Protein Data Bank (RCSB PDB); Molecular descriptor; Lasso (programming language); Computer science; Set (abstract data type); Artificial intelligence; Test set; Data mining; Pattern recognition (psychology); Machine learning; Chemistry; Computational chemistry; Stereochemistry","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":[0.0005813729,0.0001549235,0.0002220751,0.0006010355,0.0001005798,0.000194942,0.0003701615,0.00006449034,0.000001340889],"category_scores_gemma":[0.0001412478,0.0001599244,0.00004575588,0.0009246145,0.00003217741,0.0007481369,0.0002066132,0.0002068386,0.00005082448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008399111,"about_ca_system_score_gemma":0.000115081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001523063,"about_ca_topic_score_gemma":0.00000211924,"domain_scores_codex":[0.9985234,0.0001019062,0.0005572874,0.0001254292,0.0004259127,0.0002661353],"domain_scores_gemma":[0.9991214,0.0002904858,0.0001259847,0.0003075422,0.00006596492,0.00008862424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003312613,0.00001554887,0.0006604315,0.00003555571,0.000009164802,0.000003067679,0.003355332,0.9774364,0.00001055339,0.006188762,0.00003926079,0.01224266],"study_design_scores_gemma":[0.00036027,0.00004647159,0.002595428,0.00005656252,0.000006040687,0.000001069131,0.0003993179,0.9936429,0.0005473159,0.001984952,0.0001857926,0.0001739246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3587815,0.000005770657,0.639679,0.0001588539,0.0000587237,0.0001618406,0.000008611248,0.00009646696,0.001049197],"genre_scores_gemma":[0.8969265,0.000001944604,0.1025368,0.0004439336,0.000007416606,0.00001723523,0.00005531823,0.00000803681,0.000002795027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.538145,"threshold_uncertainty_score":0.6521526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05288652475164202,"score_gpt":0.337118736541096,"score_spread":0.284232211789454,"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."}}