{"id":"W2042110087","doi":"10.1021/ci600426e","title":"Evaluating Virtual Screening Methods:  Good and Bad Metrics for the “Early Recognition” Problem","year":2007,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":858,"is_retracted":false,"has_abstract":true,"ca_institutions":"TransCanada (Canada)","funders":"","keywords":"Computer science; Virtual screening; Artificial intelligence; Machine learning; Pattern recognition (psychology); Bioinformatics; Drug discovery; Biology","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":[0.005973659,0.00007390491,0.0001282805,0.0001668127,0.0001514304,0.000207847,0.0001860974,0.00006341675,0.000001021182],"category_scores_gemma":[0.001408765,0.00005166788,0.00004602224,0.000198914,0.0000156665,0.001325055,0.00008394853,0.0003450084,2.990284e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002303005,"about_ca_system_score_gemma":0.0000438354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009953438,"about_ca_topic_score_gemma":1.769078e-7,"domain_scores_codex":[0.9987608,0.00004944248,0.0006861327,0.00006566565,0.000283188,0.000154782],"domain_scores_gemma":[0.9976835,0.001138333,0.0004226271,0.000075476,0.0005762135,0.0001038861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002721524,0.00000320359,0.00004550912,0.00003160427,0.00001221318,1.460724e-7,0.001629864,0.006199898,0.0004160537,0.001209519,0.000007590009,0.9904172],"study_design_scores_gemma":[0.00044595,0.0001239328,0.00002469275,0.00006554381,0.00001503904,0.00008249603,0.0002463827,0.9953511,0.0009629278,0.00228564,0.0003292157,0.0000670558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07865742,0.0002524659,0.91996,0.0008293819,0.00007646724,0.0001298052,7.012772e-7,0.00001506602,0.00007875109],"genre_scores_gemma":[0.2646908,0.00002919867,0.734779,0.0004179204,0.00007526359,0.00000213695,0.000001058765,0.000002791914,0.000001815852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9903501,"threshold_uncertainty_score":0.2106955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1342111082886273,"score_gpt":0.4229986251823157,"score_spread":0.2887875168936884,"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."}}