{"id":"W6944971056","doi":"10.23645/epacomptox.28507007","title":"Categorical Machine Learning for Predicting Caco-2 Permeability in High Throughput Toxicokinetics","year":2025,"lang":"en","type":"other","venue":"U.S. Environmental Protection Agency","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Categorical variable; Throughput; Predictive modelling; Permeability (electromagnetism); Toxicokinetics; Training set","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002721685,0.001035718,0.001398312,0.001877401,0.0005515434,0.001901837,0.001138969,0.001195649,0.01357071],"category_scores_gemma":[0.008329088,0.0003800119,0.001568115,0.001801359,0.0003769278,0.00111566,0.0009792476,0.002057177,0.009081184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001698206,"about_ca_system_score_gemma":0.001569956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01124441,"about_ca_topic_score_gemma":0.01530122,"domain_scores_codex":[0.9988561,0.0004809873,0.00006507878,0.0002222418,0.000285134,0.0000903564],"domain_scores_gemma":[0.9975054,0.001494825,0.0001418853,0.0002071826,0.0005342309,0.000116537],"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":[0.002932712,0.001051842,0.04792595,0.001749364,0.0006725306,0.0001810059,0.0001089188,0.1965671,0.02300121,0.006146756,0.1181995,0.6014632],"study_design_scores_gemma":[0.00009841616,0.0006771414,0.01484234,0.0001594369,0.0001505095,0.0000776114,0.00008953154,0.9452811,0.01056075,0.01065077,0.01730068,0.000111674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.2335389,0.0263394,0.5646646,0.009397505,0.00238691,0.001263746,0.09786358,0.02603795,0.03850738],"genre_scores_gemma":[0.638715,0.007892129,0.2423928,0.002009591,0.0008933505,0.001330835,0.07897307,0.0009684635,0.02682474],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01357071,"threshold_uncertainty_score":0.04539847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01400413175308943,"score_gpt":0.2358063256844366,"score_spread":0.2218021939313472,"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."}}