{"id":"W4391463569","doi":"10.1093/bioadv/vbae016","title":"HiTaxon: a hierarchical ensemble framework for taxonomic classification of short reads","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ministry of Agriculture, Food and Rural Affairs; University of Toronto; Compute Canada; Canada Foundation for Innovation; Ontario Ministry of Agriculture, Food and Rural Affairs; Government of Ontario","keywords":"Metagenomics; Biological classification; Computer science; Taxonomy (biology); Taxonomic rank; Microbiome; Key (lock); Artificial intelligence; Taxon; Data mining; Machine learning; Biology; Bioinformatics; Evolutionary biology; Ecology; Genetics","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":[0.003612215,0.001224294,0.001227741,0.002175285,0.001077015,0.001822117,0.002465397,0.001047555,0.003507971],"category_scores_gemma":[0.007924109,0.0005922991,0.001433382,0.001900719,0.0003980615,0.002353329,0.002306624,0.00189313,0.001940784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008909837,"about_ca_system_score_gemma":0.001650782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01090243,"about_ca_topic_score_gemma":0.0199101,"domain_scores_codex":[0.9984371,0.0004212247,0.00009281177,0.0004062571,0.0005151764,0.0001274317],"domain_scores_gemma":[0.9980583,0.0007331216,0.0001325484,0.0003204748,0.0005935733,0.0001620536],"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":[0.0007987773,0.0002925016,0.01267719,0.0005466886,0.0009962793,0.0003022982,0.0006801671,0.2315353,0.01369596,0.01354803,0.03747499,0.6874518],"study_design_scores_gemma":[0.00002643437,0.0001122389,0.001807992,0.00005399456,0.00008946095,0.00008038287,0.00007174172,0.9624233,0.003188485,0.02303291,0.009069691,0.00004336641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009856259,0.0005440034,0.97297,0.0001711872,0.00009950044,0.000148397,0.002736465,0.01243416,0.001039973],"genre_scores_gemma":[0.1361879,0.0005438092,0.8359277,0.0003918887,0.0002008779,0.0006111762,0.02162432,0.001468991,0.003043415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01090243,"threshold_uncertainty_score":0.02167797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02636127204626749,"score_gpt":0.2936164668138977,"score_spread":0.2672551947676303,"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."}}