{"id":"W4386496250","doi":"10.1038/s41598-023-41318-8","title":"Clustering microbiome data using mixtures of logistic normal multinomial models","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Simons Foundation","keywords":"Mixture model; Cluster analysis; Multinomial distribution; Computer science; Microbiome; Count data; Simplex; Bayesian probability; Latent variable; Multinomial logistic regression; Data mining; Variable (mathematics); Statistics; Artificial intelligence; Mathematics; Biology; Bioinformatics; Machine learning; Poisson distribution","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006911984,0.001153682,0.001813022,0.002166093,0.001100524,0.002287433,0.004010128,0.002200151,0.002148705],"category_scores_gemma":[0.01965619,0.001208146,0.00302583,0.002402995,0.001572905,0.002641228,0.002570319,0.003170417,0.001273929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00180497,"about_ca_system_score_gemma":0.001404208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01690291,"about_ca_topic_score_gemma":0.01646062,"domain_scores_codex":[0.996034,0.002237481,0.0001853861,0.0008114887,0.0005179747,0.0002137626],"domain_scores_gemma":[0.9937106,0.004427875,0.000504463,0.0005450358,0.0006490292,0.0001628988],"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":[0.0002225327,0.00008724608,0.005574879,0.0001813813,0.0001904472,0.000197697,0.0005341375,0.8345542,0.001763634,0.08038027,0.003138181,0.07317536],"study_design_scores_gemma":[0.00000896641,0.000008786035,0.0002439677,0.00001134266,0.000006576025,0.00002948463,0.00002541126,0.9797948,0.0001466219,0.01914311,0.0005657593,0.00001522102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009744229,0.0002793313,0.988841,0.0002353608,0.00002891931,0.00006950043,0.0001780542,0.0002496565,0.0003740472],"genre_scores_gemma":[0.3282526,0.0009042561,0.6611949,0.0003636826,0.0001924133,0.0006848507,0.002753001,0.0003090359,0.005345195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01690291,"threshold_uncertainty_score":0.03655446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1431925949667628,"score_gpt":0.3395313977061513,"score_spread":0.1963388027393885,"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."}}