{"id":"W3200684360","doi":"10.1093/toxsci/kfab113","title":"A Pragmatic Approach to Adverse Outcome Pathway Development and Evaluation","year":2021,"lang":"en","type":"article","venue":"Toxicological Sciences","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"Miljøstyrelsen; Vetenskapsrådet; Svenska Forskningsrådet Formas; European Commission","keywords":"Adverse Outcome Pathway; Computer science; Risk analysis (engineering); Bottleneck; Framing (construction); Pace; Modular design; Knowledge base; Artificial intelligence; Computational biology; Biology; Business","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":[0.00340518,0.0001025013,0.0001480653,0.00007224291,0.0002760796,0.0001876674,0.0004988775,0.00003981932,0.0000335304],"category_scores_gemma":[0.00100222,0.00007389747,0.00002773879,0.0009410557,0.0001054007,0.0003435423,0.0005726427,0.00007170987,0.0000341794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008455371,"about_ca_system_score_gemma":0.0004475455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001206808,"about_ca_topic_score_gemma":0.00000477933,"domain_scores_codex":[0.997692,0.0004462831,0.0002614658,0.000569728,0.0007843824,0.000246159],"domain_scores_gemma":[0.9990937,0.00043705,0.00005867019,0.0001582291,0.0001046619,0.0001476888],"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":[0.000004637275,0.0005543305,0.005033258,0.00002393204,0.00001349023,0.00002187902,0.002905641,0.08325429,0.001831203,0.4027582,0.0001017385,0.5034974],"study_design_scores_gemma":[0.0004414977,0.0002154335,0.33373,0.00002075413,0.000008137275,0.00007295227,0.0005226149,0.6226764,0.003271229,0.03408723,0.004484006,0.0004697002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6918104,0.00006417795,0.2916053,0.001201301,0.0001398118,0.0002616504,5.289706e-7,0.00005831924,0.01485854],"genre_scores_gemma":[0.532316,4.027834e-7,0.4668902,0.000677936,0.00001123888,0.00004727433,9.697566e-7,9.877708e-7,0.00005504957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5394222,"threshold_uncertainty_score":0.3013451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1469923386721911,"score_gpt":0.3829345250073153,"score_spread":0.2359421863351242,"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."}}