{"id":"W2963613699","doi":"10.1039/c9sc01992h","title":"A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification","year":2019,"lang":"en","type":"article","venue":"Chemical Science","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Bayesian network; Computer science; Bayesian probability; Uncertainty quantification; Graph; Artificial intelligence; Machine learning; Theoretical 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":[0.0007718582,0.00008916229,0.0001242627,0.0000627729,0.00009199719,0.00006583562,0.0006907682,0.00003300378,0.00000352578],"category_scores_gemma":[0.0001150868,0.00006905269,0.0000438907,0.001073373,0.0003794115,0.0005177999,0.0001124752,0.00006269121,0.000003122438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007985532,"about_ca_system_score_gemma":0.0003804984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001543516,"about_ca_topic_score_gemma":4.095442e-7,"domain_scores_codex":[0.9985059,0.00002342622,0.0002054997,0.0004651989,0.000538595,0.0002613153],"domain_scores_gemma":[0.9989853,0.0001156779,0.000113241,0.0003415287,0.0003702507,0.00007398369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004267897,0.00004374959,0.001108511,0.00003754111,0.000006233351,1.564009e-7,0.00007324595,0.3444552,0.5336482,0.1197231,0.00009931764,0.0007621563],"study_design_scores_gemma":[0.0002282839,0.00007965158,0.001297634,0.00005816066,0.000004138675,0.000004480212,0.000009380125,0.7715305,0.204592,0.0219761,0.0001259689,0.0000936638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3380388,0.00004095575,0.6610538,0.000209762,0.0001301385,0.000283496,0.00000459107,0.00003664916,0.000201833],"genre_scores_gemma":[0.8437927,8.770784e-7,0.1560646,0.00005368817,0.00002151553,0.00003532328,0.00000698882,0.000003667366,0.00002056066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.505754,"threshold_uncertainty_score":0.2815887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01906070602826038,"score_gpt":0.250107882471045,"score_spread":0.2310471764427847,"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."}}