{"id":"W4225081585","doi":"10.1101/2022.04.27.489753","title":"From defaults to databases: parameter and database choice dramatically impact the performance of metagenomic taxonomic classification tools","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metagenomics; Taxonomic rank; Database; Biological classification; Computer science; Range (aeronautics); Precision and recall; Reference database; Data mining; Machine learning; Biology; Taxon; Ecology; Gene; Evolutionary biology; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03693083,0.002594739,0.002524472,0.002839377,0.002014979,0.006494293,0.006365214,0.003429995,0.003470354],"category_scores_gemma":[0.1153222,0.001740239,0.001759148,0.004070356,0.001080032,0.01029565,0.004530664,0.004373283,0.003907896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001164692,"about_ca_system_score_gemma":0.001495964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003533379,"about_ca_topic_score_gemma":0.003371039,"domain_scores_codex":[0.9760419,0.008326101,0.003994059,0.005902697,0.004617081,0.001118061],"domain_scores_gemma":[0.9144351,0.06035598,0.002230608,0.01492215,0.006307829,0.001748297],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01704294,0.003811663,0.1667567,0.007126845,0.003875351,0.002052884,0.003055554,0.04856957,0.117748,0.007717357,0.07910699,0.5431362],"study_design_scores_gemma":[0.002889074,0.003349571,0.07093889,0.003008045,0.002224134,0.00461667,0.00361766,0.4115269,0.3336141,0.03386796,0.1278052,0.002541829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8098509,0.01533357,0.09139091,0.003208835,0.001385055,0.0007509249,0.01077481,0.05945943,0.007845597],"genre_scores_gemma":[0.7688615,0.002251557,0.1916276,0.002972689,0.000144652,0.0008569357,0.02139173,0.01039311,0.001500147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9630691,"threshold_uncertainty_score":0.1953112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03446878568646268,"score_gpt":0.2643991852553324,"score_spread":0.2299303995688697,"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."}}