{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003812701,0.0007262438,0.001315159,0.001413413,0.0009785636,0.001294565,0.00269435,0.001812901,0.001389664],"category_scores_gemma":[0.008190179,0.0004837746,0.001372908,0.001343845,0.001411677,0.001528436,0.001657934,0.001865145,0.0006306803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002093672,"about_ca_system_score_gemma":0.001365421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01426468,"about_ca_topic_score_gemma":0.008862567,"domain_scores_codex":[0.9983425,0.0006487162,0.00008843996,0.0005314201,0.0002613681,0.0001275344],"domain_scores_gemma":[0.9955195,0.002869939,0.000433524,0.000308337,0.0007201625,0.0001485593],"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":[0.000151318,0.00009554065,0.00495445,0.00009349029,0.0001253347,0.000090836,0.0002195578,0.9246873,0.0009202625,0.01926518,0.001649428,0.04774733],"study_design_scores_gemma":[0.000005843096,0.00001445691,0.0003586403,0.000004723488,0.000005979197,0.00001611396,0.000009373,0.993399,0.0001191072,0.005812887,0.0002450928,0.000008804723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06528316,0.0004335967,0.9309708,0.0007323014,0.00005955836,0.000174937,0.0004109535,0.0003994125,0.001535287],"genre_scores_gemma":[0.7078781,0.0006673815,0.2790755,0.0004092207,0.0001285162,0.0006537661,0.001533835,0.0001622514,0.009491431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01426468,"threshold_uncertainty_score":0.02836329,"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."}}