{"id":"W2272266927","doi":"10.1111/rssc.12432","title":"Cluster Analysis of Microbiome Data by Using Mixtures of Dirichlet–Multinomial Regression Models","year":2020,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Covariate; Microbiome; Multinomial distribution; Regression; Mixture model; Multinomial logistic regression; Regression analysis; Dirichlet distribution; Biology; Biota; Probabilistic logic; Statistics; Ecology; Mathematics; Econometrics; Bioinformatics","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":[0.0003218092,0.0002100366,0.0006376726,0.0000245494,0.0001229942,0.00002327957,0.000666532,0.0001766143,0.00005395066],"category_scores_gemma":[0.0001692153,0.0001456037,0.0002183875,0.000239108,0.0003835083,0.000009983106,0.0004929453,0.0002604471,3.782106e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003220575,"about_ca_system_score_gemma":0.000193114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005284891,"about_ca_topic_score_gemma":0.00001071404,"domain_scores_codex":[0.9981549,0.0001135583,0.0008834852,0.000289147,0.0003019845,0.0002569368],"domain_scores_gemma":[0.9981639,0.0001218365,0.0009270105,0.0003898519,0.0002308324,0.0001665272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009097894,0.000144497,0.0002516961,0.0002315691,0.001437853,0.000001630107,0.0004471162,0.00944096,0.8195701,0.0005667647,0.1663941,0.0006039278],"study_design_scores_gemma":[0.01071253,0.003154153,0.009886472,0.0003423909,0.01628152,0.00005900509,0.002805906,0.6445649,0.2706179,0.00303697,0.03617357,0.002364718],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1272733,0.0005158933,0.852386,0.0005668965,0.0001601546,0.0002264465,0.01881846,0.000003576311,0.00004923444],"genre_scores_gemma":[0.8406973,0.0001445298,0.1575264,0.0006704658,0.0001480561,7.433097e-7,0.0007320272,0.00002797578,0.00005253422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.713424,"threshold_uncertainty_score":0.5937545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02440155035215219,"score_gpt":0.2862104524876901,"score_spread":0.2618089021355379,"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."}}