{"id":"W4386767901","doi":"10.1101/2023.09.11.557224","title":"HiTaxon: A hierarchical ensemble framework for taxonomic classification of short reads","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Ministry of Agriculture, Food and Rural Affairs; University of Toronto; Ontario Ministry of Agriculture, Food and Rural Affairs; Government of Ontario; Compute Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Key (lock); Biological classification; Metagenomics; Data mining; Pattern recognition (psychology); Biology","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":[0.003713939,0.001033767,0.001451741,0.00212935,0.0008181974,0.001720079,0.00230443,0.001076066,0.002090358],"category_scores_gemma":[0.00656471,0.0005229127,0.00148941,0.001723642,0.0003675973,0.001883415,0.002103168,0.001821699,0.001071456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009103188,"about_ca_system_score_gemma":0.001321173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009677612,"about_ca_topic_score_gemma":0.01407999,"domain_scores_codex":[0.9984052,0.0005260103,0.00009254948,0.0003644208,0.0004731243,0.0001387587],"domain_scores_gemma":[0.9977469,0.0009572126,0.000159122,0.000316982,0.0006566105,0.0001631741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005149613,0.000277112,0.008950614,0.0002559785,0.0008861497,0.0001930273,0.0003410874,0.4633463,0.01109894,0.009776862,0.01123748,0.4931214],"study_design_scores_gemma":[0.000007802852,0.0000393572,0.0005579668,0.00001248992,0.00002972518,0.0000182016,0.00002297374,0.9899113,0.001089346,0.006946656,0.00135021,0.00001409415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01269855,0.0004144697,0.9818081,0.0001133322,0.00006918734,0.00008357979,0.0007410132,0.003570534,0.0005012239],"genre_scores_gemma":[0.2384225,0.0004951518,0.7494736,0.0003252352,0.0002450023,0.0004605254,0.007409446,0.0006999061,0.002468632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009677612,"threshold_uncertainty_score":0.0196414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04011541657399193,"score_gpt":0.2616897570556034,"score_spread":0.2215743404816115,"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."}}