{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005260649,0.0002491535,0.0003093464,0.0001322809,0.0003367749,0.00001880975,0.0006303961,0.0002892054,0.00001758743],"category_scores_gemma":[0.0004808484,0.0002311272,0.00008296633,0.0002091441,0.0001850565,0.000007924053,0.003679312,0.0001896524,0.00005878307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000129984,"about_ca_system_score_gemma":0.00009594962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000302163,"about_ca_topic_score_gemma":0.005320445,"domain_scores_codex":[0.997972,0.0001733741,0.0003123711,0.0009336567,0.00006834038,0.0005402489],"domain_scores_gemma":[0.9988074,0.0001559509,0.0001663568,0.0007077679,0.00003168632,0.0001308644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000129846,0.00002631149,0.04436531,0.00002147769,0.00006860296,0.0001180533,0.0001929783,0.00009530938,0.9517784,0.00001907384,0.001160462,0.002024184],"study_design_scores_gemma":[0.004004656,0.0004694879,0.50853,0.0004293478,0.0001351242,0.0002706131,0.001828239,0.001921175,0.4725509,0.001596151,0.006977068,0.001287256],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976123,0.000719922,0.0001358982,0.0003701848,0.0002761825,0.0003240875,0.0004314534,0.00004369244,0.00008628582],"genre_scores_gemma":[0.9965903,0.000257736,0.0005452757,0.0003530908,0.0001154646,0.000009324188,0.002041878,0.00002682709,0.00006013319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4792275,"threshold_uncertainty_score":0.9425094,"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."}}