{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003269687,0.0001654289,0.0002818938,0.0003702726,0.0002633823,0.0003693081,0.001356695,0.00008526044,0.000007197636],"category_scores_gemma":[0.0001291378,0.0001494946,0.00008025681,0.001202405,0.0002251902,0.0009312243,0.002053054,0.0001133219,0.000007805055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002698984,"about_ca_system_score_gemma":0.0002126299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001099455,"about_ca_topic_score_gemma":0.0000223651,"domain_scores_codex":[0.9972364,0.00009627415,0.0006312159,0.001158427,0.0004180133,0.0004597037],"domain_scores_gemma":[0.996401,0.00006323932,0.0003621229,0.002919457,0.000137986,0.0001161706],"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":[0.00001270453,0.0001252784,0.0002457551,0.0002267689,0.00005582725,0.001487071,0.002159357,0.04159287,0.8876827,0.002535678,0.00904076,0.05483528],"study_design_scores_gemma":[0.0000924053,0.000008709245,0.000049764,0.00004498484,0.00001242498,0.0002372589,0.000008932519,0.955217,0.01781152,0.02576037,0.0005659545,0.0001906594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04061291,0.00009005103,0.9514257,0.00004210808,0.007122416,0.000179627,0.00001387168,0.0001604296,0.000352925],"genre_scores_gemma":[0.5519578,0.000001933521,0.447495,0.00001310923,0.00006556806,0.000002059636,0.00004522627,0.00001094151,0.000408322],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9136242,"threshold_uncertainty_score":0.6096212,"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."}}