{"id":"W2526026918","doi":"10.1016/j.tox.2016.09.015","title":"Integrating in silico models to enhance predictivity for developmental toxicity","year":2016,"lang":"en","type":"article","venue":"Toxicology","topic":"Pharmaceutical studies and practices","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"Health Canada","funders":"Vedecká Grantová Agentúra MŠVVaŠ SR a SAV","keywords":"Quantitative structure–activity relationship; Applicability domain; In silico; Computer science; Domain (mathematical analysis); Nexus (standard); Machine learning; Computational model; Predictive modelling; Data mining; Artificial intelligence; 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":[0.0003480681,0.00009751823,0.0002410922,0.00004518936,0.00005744223,0.000004023652,0.00006487353,0.00007757967,0.0001357911],"category_scores_gemma":[0.0006796344,0.00006271252,0.00003355749,0.00009877985,0.00004921777,0.000116299,0.00008698377,0.0001077016,0.0000275176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002082082,"about_ca_system_score_gemma":0.00006920144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002470127,"about_ca_topic_score_gemma":0.0005260464,"domain_scores_codex":[0.9991215,0.00004638115,0.0001961529,0.0002459258,0.00007919766,0.000310771],"domain_scores_gemma":[0.9990141,0.0007146617,0.00003896601,0.00007103975,0.0000390258,0.0001222481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001636933,0.0004646502,0.009989235,0.00005021825,0.00006793563,0.0000166359,0.0009324729,0.000009055271,0.5890897,0.001736311,0.002327101,0.3936798],"study_design_scores_gemma":[0.005118909,0.003485597,0.03053697,0.0003330323,0.00009730022,0.00009049509,0.0007996666,0.003708422,0.7415562,0.006632205,0.2070548,0.0005863722],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499296,0.00007118449,0.02943717,0.01246789,0.0001312892,0.0006451178,0.0000156339,0.0000370381,0.007265101],"genre_scores_gemma":[0.9882863,0.00003979549,0.007825446,0.003065454,0.00008856779,0.0001986064,9.670767e-7,0.000008392802,0.0004864327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3930934,"threshold_uncertainty_score":0.2557342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.095586551159448,"score_gpt":0.4103339569688536,"score_spread":0.3147474058094056,"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."}}