{"id":"W1899644141","doi":"10.1002/minf.201400118","title":"Towards Better BBB Passage Prediction Using an Extensive and Curated Data Set","year":2015,"lang":"en","type":"article","venue":"Molecular Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Linear discriminant analysis; Set (abstract data type); Test set; Computer science; Data set; Artificial intelligence; Machine learning; Regression; Linear regression; Data mining; Variance (accounting); Drug discovery; Linear model; Regression analysis; Statistics; Mathematics; Bioinformatics; 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":[0.0007028318,0.0001334717,0.000135312,0.0001061778,0.00006500066,0.0003382708,0.0006871906,0.00005744737,0.000001082505],"category_scores_gemma":[0.0001848313,0.0001287786,0.0000170887,0.000290899,0.00004421029,0.002897689,0.000930203,0.0001224088,0.000007447783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004992128,"about_ca_system_score_gemma":0.0002003565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002203811,"about_ca_topic_score_gemma":9.540042e-7,"domain_scores_codex":[0.9986936,0.000143795,0.0003400674,0.0001813454,0.0004569434,0.0001842855],"domain_scores_gemma":[0.9985667,0.00003512827,0.0001317385,0.0008578171,0.0002440302,0.0001645223],"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":[0.00004540771,0.0002429418,0.001032352,0.0002532612,0.0002848537,0.0002779331,0.03806779,0.6790442,0.002904475,0.02348295,0.00860625,0.2457575],"study_design_scores_gemma":[0.0002877592,0.00005293104,0.0005562938,0.000015556,0.00001523075,0.00009468554,0.0002421912,0.9908257,0.0006582327,0.005897702,0.001209735,0.000143986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.291077,0.00002870701,0.7080379,0.0001598682,0.0001647748,0.000108862,0.00004740776,0.00006760285,0.0003079246],"genre_scores_gemma":[0.2664935,0.000003007314,0.7314016,0.001738319,0.00004402527,0.00000305376,0.0003006923,0.00001206337,0.000003733977],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3117814,"threshold_uncertainty_score":0.5251441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1242311728463903,"score_gpt":0.3528909864422495,"score_spread":0.2286598135958592,"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."}}