{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000141891,0.0001242131,0.0001522579,0.00004757779,0.00005508945,0.00002707189,0.0001415405,0.0001044293,0.000002376307],"category_scores_gemma":[0.00007976643,0.0001078905,0.0001079185,0.00006891059,0.00009176358,0.000003574525,0.00005674118,0.00005690727,0.000004324332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001067723,"about_ca_system_score_gemma":0.00006375611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.281279e-7,"about_ca_topic_score_gemma":0.000005240627,"domain_scores_codex":[0.9992472,0.000008119995,0.000333352,0.0001633005,0.00007733761,0.0001707037],"domain_scores_gemma":[0.9995387,0.00006656922,0.00006165339,0.0002326113,0.00005860135,0.00004186824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002390494,0.0000966485,0.001605428,0.001454266,0.0003822776,8.189533e-7,0.000592218,0.00042852,0.4664538,0.1269068,0.004733155,0.397107],"study_design_scores_gemma":[0.0002704901,0.0008388154,0.002025433,0.0001590762,0.00008050205,0.00001359548,0.0007021984,0.01542618,0.1160631,0.01944632,0.8444918,0.0004824614],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4018608,0.01861231,0.5706702,0.0003444573,0.0009782679,0.0007820462,0.0002599808,0.0000217673,0.006470184],"genre_scores_gemma":[0.8432097,0.001762905,0.1545554,0.00004662148,0.0001970273,0.00008471179,0.00005746886,0.00001344935,0.00007271062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8397587,"threshold_uncertainty_score":0.4399648,"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."}}