{"id":"W4223896981","doi":"10.1101/2022.03.31.486647","title":"Decision Tree Ensembles Utilizing Multivariate Splits Are Effective at Investigating Beta-Diversity in Medically Relevant 16S Amplicon Sequencing Data","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"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; Computer science; Workflow; Decision tree; Tree (set theory); Artificial intelligence; Machine learning; Data mining; Computational biology; Biology; Mathematics","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":[0.01361421,0.001465564,0.00180643,0.002321741,0.0009519999,0.001672076,0.0009920511,0.001369027,0.0008196926],"category_scores_gemma":[0.02501157,0.0005915198,0.002200885,0.001218035,0.0007451384,0.001848853,0.001611677,0.002622945,0.0003185852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007346408,"about_ca_system_score_gemma":0.001007858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004706771,"about_ca_topic_score_gemma":0.005848707,"domain_scores_codex":[0.9961123,0.002659895,0.0001664998,0.0005038823,0.00037517,0.0001824111],"domain_scores_gemma":[0.9802346,0.01485488,0.00117306,0.001516529,0.001488987,0.0007319689],"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":[0.0006056328,0.0002724679,0.04513648,0.00009487459,0.0007605848,0.000136795,0.0002647618,0.8657211,0.005524503,0.001919672,0.001734457,0.07782867],"study_design_scores_gemma":[0.000006021355,0.00005430995,0.002100399,0.00001023133,0.00001664191,0.00001261151,0.00003895229,0.993857,0.0007392481,0.003013884,0.0001371478,0.00001354125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4973401,0.0008055983,0.49733,0.0008178932,0.0001500671,0.000133835,0.0006943979,0.001391808,0.001336241],"genre_scores_gemma":[0.8873142,0.0001627704,0.11031,0.0002335762,0.00009003628,0.00008799162,0.001262577,0.0001385849,0.0004002042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01361421,"threshold_uncertainty_score":0.07199967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04918409149629214,"score_gpt":0.2810083305703946,"score_spread":0.2318242390741025,"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."}}