{"id":"W4414563706","doi":"10.1021/acs.est.5c04614","title":"Multiscale-Information-Embedded Universal Toxicity Prediction Framework","year":2025,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Interpretability; Generalizability theory; Identification (biology); Representation (politics); Quantitative structure–activity relationship; Toxicity; Human health; Hazard","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":[0.000435032,0.0001319947,0.0001189773,0.0009019126,0.0004402114,0.0001135748,0.001618281,0.0001396194,0.00003357689],"category_scores_gemma":[0.0001664696,0.000136242,0.00004033919,0.002424781,0.001105263,0.002195591,0.001138953,0.000267535,0.0001159272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005551782,"about_ca_system_score_gemma":0.0001412563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004612436,"about_ca_topic_score_gemma":6.804088e-7,"domain_scores_codex":[0.9985089,0.00003789505,0.0002380934,0.0004284658,0.0004373952,0.0003492551],"domain_scores_gemma":[0.9991545,0.0001033022,0.00008642659,0.0005744307,0.00001498084,0.00006635717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009612209,0.0001915253,0.01124396,0.000006478511,0.0000162119,0.000006324882,0.0007483694,0.02494803,0.01796118,0.7390382,0.0002461371,0.2055839],"study_design_scores_gemma":[0.0005893324,0.0001621889,0.1171096,0.00005061822,0.0000102969,0.00003571644,0.0008498654,0.5988796,0.0779541,0.1911231,0.01282932,0.0004062567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2307065,0.00002398223,0.7644038,0.001662017,0.0005119493,0.0001666956,0.000009385661,0.0003081192,0.00220751],"genre_scores_gemma":[0.8723481,0.000008830474,0.1272194,0.0003115194,0.000009695188,0.00001465484,0.000003116777,0.000002129596,0.00008258785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6416416,"threshold_uncertainty_score":0.5555787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003956235133311244,"score_gpt":0.2496457882119664,"score_spread":0.2456895530786551,"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."}}