{"id":"W2612334248","doi":"10.1016/j.comtox.2017.05.001","title":"Performance of machine learning algorithms for qualitative and quantitative prediction drug blockade of hERG1 channel","year":2017,"lang":"en","type":"article","venue":"Computational Toxicology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of Alberta","funders":"National Heart, Lung, and Blood Institute; Alberta Innovates; Heart and Stroke Foundation of Canada; National Institutes of Health; University of Alberta; Li Ka Shing Foundation","keywords":"Computer science; Machine learning; Artificial intelligence; Algorithm; Qualitative analysis; Qualitative research","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":[0.001127128,0.000139333,0.0003260044,0.0001724561,0.0003373209,0.00003743205,0.0004734174,0.00005919141,0.000003029681],"category_scores_gemma":[0.0006486099,0.0001436226,0.00006963949,0.000110302,0.0003502525,0.0004898053,0.0002808194,0.0001287696,0.000001124541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003202332,"about_ca_system_score_gemma":0.0001404088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002088237,"about_ca_topic_score_gemma":0.000005376814,"domain_scores_codex":[0.9984555,0.000337726,0.0004331329,0.0003483904,0.0002530903,0.0001722218],"domain_scores_gemma":[0.9960545,0.00261202,0.0006481129,0.0001956133,0.0004357412,0.00005396964],"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":[0.0002000117,0.0002118648,0.001922337,0.0002226955,0.0001605176,0.000001506529,0.01703487,0.8261065,0.0009199999,0.1350021,0.00005608624,0.01816152],"study_design_scores_gemma":[0.0008007897,0.0006601351,0.02914608,0.00003445645,0.00001213324,0.000009852596,0.0002542168,0.9238116,0.001518276,0.04359746,0.00004547045,0.0001095386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.462011,0.0001149982,0.5366927,0.0005508519,0.0002375419,0.0002100621,0.00005862006,0.00002075963,0.0001034632],"genre_scores_gemma":[0.7343379,0.00001301289,0.2654718,0.00002259572,0.00003205687,0.00002875618,0.00002619024,0.000007463128,0.000060233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2723269,"threshold_uncertainty_score":0.5856758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07615681208883787,"score_gpt":0.3929067938441664,"score_spread":0.3167499817553285,"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."}}