{"id":"W3093686667","doi":"10.3390/microorganisms8101612","title":"Clustering on Human Microbiome Sequencing Data: A Distance-Based Unsupervised Learning Model","year":2020,"lang":"en","type":"article","venue":"Microorganisms","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Crohn's and Colitis Canada","keywords":"Cluster analysis; Microbiome; Human microbiome; Computer science; Beta diversity; Sample (material); Alpha diversity; Data mining; Artificial intelligence; Pattern recognition (psychology); Statistics; Biology; Mathematics; Bioinformatics; Species diversity; Ecology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001481849,0.0002584677,0.0002243134,0.00003922522,0.0003038955,0.00006890982,0.0005574537,0.00016827,0.00003831857],"category_scores_gemma":[0.0000307304,0.0002706583,0.00006533253,0.0001300205,0.00006288211,0.000007542417,0.000318623,0.0002634458,0.00006254055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006932233,"about_ca_system_score_gemma":0.0002224629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002161093,"about_ca_topic_score_gemma":0.00004776733,"domain_scores_codex":[0.9983863,0.00006329634,0.000279151,0.0007617321,0.00009001405,0.0004195121],"domain_scores_gemma":[0.9990937,0.00000622363,0.0000920231,0.0005880325,0.00004513795,0.0001748634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006155903,0.00002875093,0.0001731032,0.00008907933,0.00001920052,0.000007314863,0.0002224746,0.004902162,0.992575,0.00001316456,0.001778994,0.0001291722],"study_design_scores_gemma":[0.001363064,0.0004341723,0.0001125298,0.00005720118,0.00002492115,0.000009956663,0.0001517474,0.01830243,0.9632129,0.000007318702,0.01585425,0.0004694698],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9012914,0.00025546,0.09637087,0.001119891,0.00007714142,0.0002824475,0.0001884232,0.00009491903,0.000319482],"genre_scores_gemma":[0.9866178,0.00001787904,0.006365719,0.004838037,0.0002190984,0.000004047973,0.001574986,0.000077403,0.0002850169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09000515,"threshold_uncertainty_score":0.9999745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08633262681074326,"score_gpt":0.3009231417100958,"score_spread":0.2145905148993525,"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."}}