{"id":"W2913363455","doi":"10.1016/j.bpj.2018.11.3021","title":"Toward Reducing HERG Affinities for Dat Inhibitors with a Combined Machine Learning and Molecular Modeling Approach","year":2019,"lang":"en","type":"article","venue":"Biophysical Journal","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"hERG; Affinities; chEMBL; Quantitative structure–activity relationship; Binding affinities; Chemistry; Artificial intelligence; Machine learning; Computational biology; Drug discovery; Stereochemistry; Pharmacology; Potassium channel; Computer science; Biology; Biophysics; Biochemistry; Receptor","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005142218,0.0009673334,0.0007957785,0.0003928225,0.0002629541,0.0007006885,0.000780421,0.0006195614,0.0008547275],"category_scores_gemma":[0.001111718,0.0003618005,0.000643096,0.0002902322,0.0001815496,0.000873589,0.00045195,0.0009808008,0.0002507365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004179874,"about_ca_system_score_gemma":0.0006978611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002076086,"about_ca_topic_score_gemma":0.003300274,"domain_scores_codex":[0.9997949,0.00007178124,0.00001191457,0.00003055775,0.0000680769,0.00002281389],"domain_scores_gemma":[0.9996933,0.0001617124,0.00005263297,0.0000230677,0.00005492858,0.00001441546],"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":[0.0002149858,0.0003928025,0.001894482,0.0002772788,0.0001927374,0.0001448954,0.00004349752,0.8369381,0.06779622,0.006730782,0.001172634,0.08420159],"study_design_scores_gemma":[0.00001139448,0.00007479862,0.0001520471,0.000007613925,0.00003202918,0.00003307237,0.000007798246,0.9882426,0.009418074,0.001322317,0.0006906743,0.000007558103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1986815,0.003197735,0.7860651,0.001356556,0.00007813184,0.0001807181,0.0003728972,0.001366771,0.00870054],"genre_scores_gemma":[0.8386984,0.002113438,0.1559552,0.0004654108,0.0000425746,0.0001935371,0.0003280575,0.0001175565,0.002085761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002076086,"threshold_uncertainty_score":0.004128039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141127883899287,"score_gpt":0.2390516693230271,"score_spread":0.2249388809330984,"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."}}