{"id":"W4327989184","doi":"10.1016/j.ecoenv.2023.114806","title":"Application of a developed triple-classification machine learning model for carcinogenic prediction of hazardous organic chemicals to the US, EU, and WHO based on Chinese database","year":2023,"lang":"en","type":"article","venue":"Ecotoxicology and Environmental Safety","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Support vector machine; Naive Bayes classifier; Artificial intelligence; Random forest; Machine learning; Computer science","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":[0.0006196456,0.00009964035,0.0001543203,0.0000775471,0.0001331792,0.000006400639,0.0001756615,0.00005609195,0.000004583091],"category_scores_gemma":[0.0001010628,0.00008105562,0.00003337751,0.0002139004,0.00006800037,0.00008833919,0.000174227,0.00008613904,0.000002491259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006315706,"about_ca_system_score_gemma":0.00003061625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004165295,"about_ca_topic_score_gemma":0.00001209796,"domain_scores_codex":[0.9990867,0.0001147529,0.000251272,0.0003087783,0.0001231746,0.000115292],"domain_scores_gemma":[0.9992186,0.000393015,0.0001205495,0.0002133115,0.000008005914,0.00004646804],"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":[0.0004416149,0.000203849,0.04504693,0.00007885139,0.00004657854,4.016287e-7,0.001119676,0.5504222,0.3760437,0.001017182,0.00008477497,0.02549426],"study_design_scores_gemma":[0.0004171429,0.00009103741,0.2272563,0.000004612953,0.00000939117,0.000001930525,0.00001070503,0.7681066,0.003706567,0.0001633318,0.0001820469,0.00005029251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5019202,0.00002266599,0.4969142,0.0005678911,0.00002222096,0.000384756,0.0001461614,0.00001552778,0.000006445225],"genre_scores_gemma":[0.9881057,0.00005311501,0.01120879,0.0001669326,0.00001283606,0.0001140568,0.0002924258,0.000008343462,0.00003778352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4861856,"threshold_uncertainty_score":0.3305352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02102943426583914,"score_gpt":0.2651145485049677,"score_spread":0.2440851142391286,"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."}}