{"id":"W3164743754","doi":"10.1038/s42256-021-00407-x","title":"A deep generative model enables automated structure elucidation of novel psychoactive substances","year":2021,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institutes of Health; Genome Alberta; Genome British Columbia; Compute Canada; National Institute of Environmental Health Sciences; Canadian Institutes of Health Research; Genome Canada; Foundation for the National Institutes of Health","keywords":"Generative grammar; Computer science; Pharmacology; Traditional medicine; Medicine; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002543835,0.0002469763,0.00028921,0.000162584,0.0001034101,0.0001107242,0.0008333031,0.0002148372,0.00002802024],"category_scores_gemma":[0.0003870292,0.0002220711,0.0001027021,0.001253881,0.00007542565,0.0006585431,0.0002171181,0.0005893545,0.000002251134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008437163,"about_ca_system_score_gemma":0.0003106922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001744278,"about_ca_topic_score_gemma":0.0001445206,"domain_scores_codex":[0.9979353,0.0001759793,0.0004074415,0.0006589239,0.0005842614,0.0002381066],"domain_scores_gemma":[0.9979374,0.000415868,0.0002605403,0.0005267143,0.0007863028,0.00007320649],"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":[0.00001907996,0.0001120795,0.00004936714,0.00002111595,0.000049096,0.000006896028,0.001048811,0.8173888,0.01835698,0.1417681,0.00007418361,0.02110553],"study_design_scores_gemma":[0.00009041795,0.00001935018,0.0003715388,0.00002471517,0.000007766713,0.00002464599,0.00004042369,0.7167789,0.2432006,0.03924344,0.00003697452,0.0001612155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01945142,0.002647058,0.9757805,0.0005636018,0.0004851583,0.0001557802,0.00006865808,0.0001927481,0.0006550627],"genre_scores_gemma":[0.5769356,0.00003242894,0.4226513,0.0002620496,0.00003541557,0.000004803762,0.00003828617,0.000008653634,0.00003149573],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5574842,"threshold_uncertainty_score":0.9055794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01884452616783925,"score_gpt":0.3398571225916302,"score_spread":0.3210125964237909,"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."}}