{"id":"W4381996969","doi":"10.1016/j.chroma.2023.464176","title":"Accurate prediction of isothermal gas chromatographic Kováts retention indices","year":2023,"lang":"en","type":"article","venue":"Journal of Chromatography A","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada Foundation for Innovation; University of Alberta; Genome Canada","keywords":"NIST; Kovats retention index; Chemistry; Chromatography; Gas chromatography; Mean absolute percentage error; Polar; Trimethylsilyl; Analytical Chemistry (journal); Derivatization; Mean squared error; Biological system; High-performance liquid chromatography; Statistics; Mathematics; Computer science; Organic chemistry","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":[0.001646011,0.000175323,0.0003732198,0.002003677,0.0001004816,0.0001147268,0.0008469381,0.00009192514,0.00001537073],"category_scores_gemma":[0.00008602333,0.0001558387,0.000538677,0.003890697,0.0001182227,0.001512576,0.0001348363,0.0002226561,0.00000807532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001949518,"about_ca_system_score_gemma":0.0001530903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000670822,"about_ca_topic_score_gemma":0.000001270921,"domain_scores_codex":[0.9973172,0.000320326,0.0009472257,0.0002286602,0.000918157,0.0002684194],"domain_scores_gemma":[0.9976799,0.0002963449,0.001234048,0.0003202581,0.0003443452,0.0001250835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007797893,0.002669315,0.2789551,0.002415737,0.0053351,0.001208436,0.01615851,0.1347574,0.2578922,0.1236011,0.03275423,0.1434731],"study_design_scores_gemma":[0.001647159,0.0008077935,0.832061,0.0005864332,0.000094151,0.000629574,0.0001938681,0.1123278,0.009393413,0.04085603,0.001095748,0.000307037],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.878774,0.0003456598,0.119168,0.0003114157,0.0008357957,0.0001212745,0.00001469018,0.000123904,0.0003052199],"genre_scores_gemma":[0.9857232,0.0002600042,0.01380774,0.00003913868,0.0001389885,0.000004704298,0.000005126119,0.00001558384,0.000005541056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5531058,"threshold_uncertainty_score":0.6354918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02875423380470241,"score_gpt":0.2796389338414931,"score_spread":0.2508847000367906,"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."}}