{"id":"W4399231422","doi":"10.1007/s12561-024-09435-8","title":"A Comprehensive Performance Comparison Study of Various Statistical Models that Accommodate Challenges of the Gut Microbiome Data","year":2024,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Microbiome; Human microbiome; Count data; Computational biology; Biology; Amplicon sequencing; Gut microbiome; Statistical model; Statistics; Computer science; Bioinformatics; Genetics; Poisson distribution; Artificial intelligence; Mathematics; 16S ribosomal RNA","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":[0.000320123,0.0001329488,0.0002424483,0.0000788402,0.00007560107,0.00002649703,0.0008606925,0.00006295768,0.000005478761],"category_scores_gemma":[0.00002944551,0.00009330525,0.00001598152,0.0002085139,0.0004672567,0.00001282585,0.0005747591,0.0001322722,0.000001277889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001185247,"about_ca_system_score_gemma":0.0001988046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002778012,"about_ca_topic_score_gemma":0.001166249,"domain_scores_codex":[0.9986321,0.000121075,0.0003687158,0.0004435416,0.0002084305,0.0002261058],"domain_scores_gemma":[0.9990771,0.00009203482,0.000118215,0.0006093333,0.00006784189,0.00003549224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002889877,0.003129481,0.04157319,0.003442934,0.0002590069,0.00002303625,0.01327179,0.002446498,0.8510612,0.03546152,0.008172381,0.04086993],"study_design_scores_gemma":[0.003281976,0.006620104,0.6542313,0.001031932,0.0002671978,0.00008380783,0.02655545,0.2476873,0.03934912,0.006873687,0.01249812,0.001519938],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896026,0.002825364,0.004098274,0.0001237858,0.0004251656,0.000365187,0.002424933,0.000005829168,0.000128818],"genre_scores_gemma":[0.994288,0.001100985,0.00443893,0.000025441,0.00001741276,0.000004151354,0.00009878675,0.000008749033,0.00001759106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8117121,"threshold_uncertainty_score":0.3804878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1246672887512797,"score_gpt":0.3704999728769519,"score_spread":0.2458326841256722,"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."}}