{"id":"W1973654982","doi":"10.1016/j.chroma.2012.07.064","title":"Comparison of multiple linear regression, partial least squares and artificial neural networks for prediction of gas chromatographic relative retention times of trimethylsilylated anabolic androgenic steroids","year":2012,"lang":"en","type":"article","venue":"Journal of Chromatography A","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Chemistry; Chromatography; Partial least squares regression; Artificial neural network; Linear regression; Anabolism; Kovats retention index; Retention time; Regression; Gas chromatography; Statistics; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005285479,0.0003247233,0.001128281,0.0004434292,0.0001159451,0.00001443126,0.0002196591,0.000394405,0.0000813875],"category_scores_gemma":[0.0001613695,0.0002721319,0.001022518,0.0008600485,0.0006041694,0.0004273645,0.00004519795,0.0003963009,1.001389e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001247255,"about_ca_system_score_gemma":0.00004155177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009282091,"about_ca_topic_score_gemma":0.000001175621,"domain_scores_codex":[0.9967766,0.0001087639,0.001985508,0.0002299162,0.0005064134,0.0003928409],"domain_scores_gemma":[0.9961016,0.0003385575,0.002492068,0.0002771544,0.0005261006,0.0002645011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001556521,0.001077909,0.5822943,0.0009715384,0.001121051,0.000001942728,0.0005868544,0.0003142465,0.4106552,0.0002462302,0.0002229026,0.0009513634],"study_design_scores_gemma":[0.003527172,0.000941893,0.03435074,0.001057251,0.001390146,0.00009805296,0.001260915,0.04825443,0.9081028,0.000610308,0.00008404689,0.0003222807],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900046,0.006679152,0.002751627,0.0000212086,0.0001333417,0.0001594323,0.0001507136,0.00002592173,0.0000739994],"genre_scores_gemma":[0.998664,0.0001694778,0.0007606379,0.000002877982,0.0002986148,0.000007552578,0.00006051081,0.00003221276,0.000004092255],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5479435,"threshold_uncertainty_score":0.9999731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02974611996964435,"score_gpt":0.2889976466101041,"score_spread":0.2592515266404598,"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."}}