{"id":"W4307493350","doi":"10.1007/s10822-022-00483-0","title":"Physicochemical QSAR analysis of hERG inhibition revisited: towards a quantitative potency prediction","year":2022,"lang":"en","type":"article","venue":"Journal of Computer-Aided Molecular Design","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Diabetes Canada","funders":"","keywords":"hERG; Interpretability; Quantitative structure–activity relationship; ADME; Cross-validation; Computer science; Potency; Drug discovery; Applicability domain; Data mining; Artificial intelligence; Chemistry; Machine learning; Drug; Pharmacology; Medicine","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":[0.002269735,0.0002237667,0.0007051241,0.001197188,0.0001278103,0.00009619249,0.0008089613,0.00005199919,0.00001969602],"category_scores_gemma":[0.0001400625,0.0002306915,0.0007049819,0.003257325,0.00005539261,0.000598107,0.0004339106,0.0004236445,0.000001212288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002421867,"about_ca_system_score_gemma":0.0003964259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009711292,"about_ca_topic_score_gemma":9.290583e-8,"domain_scores_codex":[0.995056,0.001822389,0.001079013,0.0003834713,0.001425114,0.0002340361],"domain_scores_gemma":[0.9970406,0.0004926501,0.001191424,0.0004251447,0.00072168,0.000128537],"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":[0.0001144525,0.0003676879,0.00001822461,0.00002138471,0.001103668,0.0002833621,0.0006217049,0.9126477,0.05453341,0.01492643,0.0005311687,0.01483079],"study_design_scores_gemma":[0.0006887739,0.00134211,0.001137677,0.00006328169,0.0005325614,0.0002309743,0.00004035043,0.9515122,0.02827447,0.01583955,0.0001227251,0.000215357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1125719,0.0003963342,0.8861077,0.0003380305,0.000299661,0.0001800491,0.00001895495,0.00003173059,0.00005565593],"genre_scores_gemma":[0.5257577,0.00001247672,0.4739131,0.0002189449,0.0000606517,0.000006573007,0.00001404351,0.00001256588,0.000003970837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4131858,"threshold_uncertainty_score":0.9407325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02866884183169466,"score_gpt":0.299158298156579,"score_spread":0.2704894563248844,"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."}}