{"id":"W2805002767","doi":"10.1021/acs.jcim.7b00690","title":"Reinforced Adversarial Neural Computer for <i>de Novo</i> Molecular Design","year":2018,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Tata Steel; Ministry of Education and Science of the Russian Federation","keywords":"Chemical space; Computer science; Artificial neural network; Artificial intelligence; Reinforcement learning; Deep learning; Generator (circuit theory); Set (abstract data type); Representation (politics); Adversarial system; Differentiable function; Machine learning; Generative grammar; Theoretical computer science; Drug discovery; Programming language; Chemistry","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":[0.0006901466,0.00007756464,0.000128976,0.00009503308,0.00004563214,0.0001637876,0.0002484531,0.00004868151,0.0000011577],"category_scores_gemma":[0.0001313854,0.00006854877,0.00007604339,0.00008954227,0.00002543999,0.001714181,0.00007946416,0.0001034994,0.0000011192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003722384,"about_ca_system_score_gemma":0.0001185874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.923124e-7,"about_ca_topic_score_gemma":8.835605e-9,"domain_scores_codex":[0.9990987,0.00003061943,0.0004672236,0.00005864865,0.0002077239,0.0001371272],"domain_scores_gemma":[0.9990243,0.0001442524,0.0002103227,0.00007794094,0.0004454872,0.00009771484],"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":[0.000127088,0.000005431183,4.413328e-7,0.00001449795,0.00001542465,9.629701e-7,0.0009058584,0.9557139,0.009880625,0.008314987,0.0001987639,0.02482205],"study_design_scores_gemma":[0.0007976025,0.0001083908,4.753975e-7,0.00001788848,0.000007393972,0.0001159717,0.000009577232,0.9730382,0.02196175,0.003570337,0.0002949479,0.00007743629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1037937,0.00001113033,0.8953728,0.0004295202,0.0002479393,0.00007880718,6.860747e-7,0.00001418727,0.00005126178],"genre_scores_gemma":[0.4734826,0.000001860314,0.5252,0.001121881,0.0001883787,0.000001094165,0.000001246534,0.000002166505,7.748657e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3701728,"threshold_uncertainty_score":0.2795338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03560623312534594,"score_gpt":0.3017826192751583,"score_spread":0.2661763861498123,"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."}}