{"id":"W1999798000","doi":"10.1021/ci500747n","title":"Deep Neural Nets as a Method for Quantitative Structure–Activity Relationships","year":2015,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1186,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Machine learning; Artificial neural network; Set (abstract data type); Random forest; Deep neural networks; Support vector machine; Data set; Training set; Data mining","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":[0.001089224,0.00007946582,0.0001529242,0.0001303848,0.0000526044,0.000154435,0.0001773628,0.00005358304,6.89224e-7],"category_scores_gemma":[0.001286198,0.00006707803,0.00006159898,0.000134215,0.00001275132,0.003232347,0.00006339692,0.0002255071,7.995916e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005370467,"about_ca_system_score_gemma":0.0001333062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000050056,"about_ca_topic_score_gemma":4.001645e-7,"domain_scores_codex":[0.999037,0.0001026796,0.000414418,0.0000657772,0.0002799148,0.000100189],"domain_scores_gemma":[0.998347,0.0005022955,0.0003209574,0.00007219847,0.0006103168,0.00014717],"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":[0.0001089279,0.00001014457,0.000007028161,0.00001238442,0.00001610514,3.537447e-7,0.002843714,0.9131353,0.0009167215,0.03684094,0.00006073098,0.04604767],"study_design_scores_gemma":[0.0005048635,0.00005847625,0.00001068869,0.000008840814,0.000008085349,0.00009468956,0.0001579847,0.9078919,0.001650648,0.0894134,0.000130376,0.00007003998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2033224,0.00004987009,0.7953919,0.0009381095,0.0001360447,0.00006760535,0.00000139291,0.00001016403,0.00008246824],"genre_scores_gemma":[0.5142378,0.000001039209,0.4855394,0.0001945177,0.00002235278,9.317458e-7,0.00000176774,0.000001600281,5.624622e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3109154,"threshold_uncertainty_score":0.2735363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1295232065273913,"score_gpt":0.3918566737895487,"score_spread":0.2623334672621574,"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."}}