{"id":"W4323295296","doi":"10.1128/spectrum.02065-22","title":"Decision Tree Ensembles Utilizing Multivariate Splits Are Effective at Investigating Beta Diversity in Medically Relevant 16S Amplicon Sequencing Data","year":2023,"lang":"en","type":"article","venue":"Microbiology Spectrum","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canada First Research Excellence Fund; Ontario Genomics; Genome Canada","keywords":"Multivariate statistics; Amplicon; Decision tree; Beta diversity; Computational biology; Multivariate analysis; Diversity (politics); Computer science; BETA (programming language); Statistics; Data mining; Biology; Machine learning; Mathematics; Genetics; Polymerase chain reaction; Ecology; Gene; Sociology; Biodiversity","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":[0.01166251,0.001568851,0.002002959,0.002929386,0.001166652,0.00189213,0.0008162922,0.001436295,0.0009293017],"category_scores_gemma":[0.02126609,0.0005000324,0.001500904,0.001766364,0.0006431858,0.00197821,0.001428689,0.002644099,0.000449175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004419694,"about_ca_system_score_gemma":0.0009090863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002307067,"about_ca_topic_score_gemma":0.003746035,"domain_scores_codex":[0.9964315,0.002377449,0.0002055563,0.0004797612,0.0003612724,0.000144478],"domain_scores_gemma":[0.9852668,0.01167254,0.0007997494,0.001043617,0.0008196133,0.0003976607],"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":[0.000891946,0.0004542315,0.05088769,0.0001900857,0.001128357,0.0002031017,0.0003125957,0.7048497,0.006219926,0.002993686,0.003583897,0.2282847],"study_design_scores_gemma":[0.00002141725,0.0001156681,0.003458845,0.00003360574,0.00005855884,0.00003797396,0.00008590927,0.9855355,0.0009587711,0.009133935,0.0005365099,0.00002336427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3651173,0.001819215,0.6268353,0.000796503,0.0002291467,0.000181634,0.001197844,0.001728337,0.002094613],"genre_scores_gemma":[0.8335009,0.0004849107,0.1616517,0.0003776895,0.000191232,0.0001357687,0.002890882,0.0001823751,0.000584503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01166251,"threshold_uncertainty_score":0.06167799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04057412790836721,"score_gpt":0.277597295951193,"score_spread":0.2370231680428258,"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."}}