{"id":"W2024391534","doi":"10.1021/ci900080f","title":"A Model-Based Ensembling Approach for Developing QSARs","year":2009,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; North Carolina State University","keywords":"Cheminformatics; Computer science; Ensemble learning; Measure (data warehouse); Extension (predicate logic); Class (philosophy); Data mining; Machine learning; Artificial intelligence; Ensemble forecasting; Pattern recognition (psychology); Bioinformatics","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":[0.000647624,0.00007631697,0.0001403964,0.0001595884,0.00004698129,0.0001570927,0.0002098995,0.00004412994,8.529148e-8],"category_scores_gemma":[0.0001498706,0.00006697502,0.00007307468,0.0001190501,0.000007111819,0.001696372,0.00002525676,0.0001102941,1.347552e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004801204,"about_ca_system_score_gemma":0.0002041915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.821307e-7,"about_ca_topic_score_gemma":4.489279e-9,"domain_scores_codex":[0.9990852,0.00001278961,0.0005039191,0.00006221888,0.000220514,0.0001153846],"domain_scores_gemma":[0.9992239,0.00008208294,0.0002188631,0.00006545061,0.0003457278,0.00006393738],"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":[0.00002158835,0.000009253852,3.808238e-7,0.00001870707,0.000003630119,8.473955e-8,0.000304145,0.9481487,0.001272961,0.01251516,0.00002200537,0.03768344],"study_design_scores_gemma":[0.0004653632,0.00002088857,7.601955e-7,0.00003062914,0.000004502544,0.00001975416,0.00002026424,0.9737896,0.004509398,0.02101695,0.00003794557,0.00008397913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06120937,0.00003949708,0.937704,0.0007945115,0.00003531461,0.00006597366,5.405384e-7,0.00001564598,0.0001351962],"genre_scores_gemma":[0.4769135,0.000002876587,0.5221601,0.0008992123,0.00002004328,8.055452e-7,0.000002105372,0.000001071413,2.985544e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4157041,"threshold_uncertainty_score":0.2731162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07299094951429778,"score_gpt":0.3295777607380292,"score_spread":0.2565868112237314,"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."}}