{"id":"W4323036397","doi":"10.1099/mgen.0.000949","title":"From defaults to databases: parameter and database choice dramatically impact the performance of metagenomic taxonomic classification tools","year":2023,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Dalhousie Medical Research Foundation","keywords":"Metagenomics; Taxonomic rank; Database; Computer science; Biological classification; Reference database; Range (aeronautics); Precision and recall; Data mining; Information retrieval; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002827154,0.0002075743,0.0002373129,0.00005574894,0.0001368655,0.00005639597,0.0003413467,0.00006514673,0.00001027362],"category_scores_gemma":[0.0001532594,0.0001641876,0.00008987093,0.0001212755,0.0001261699,0.000004276008,0.0004876563,0.00007962911,0.00004951084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002874369,"about_ca_system_score_gemma":0.0001107298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002702969,"about_ca_topic_score_gemma":0.0001314753,"domain_scores_codex":[0.9988199,0.00005506559,0.0003523805,0.0004284648,0.00006178295,0.0002823445],"domain_scores_gemma":[0.9989164,0.0001225834,0.0001307533,0.0006831886,0.00005916674,0.00008791042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001043174,0.00001889443,0.002844051,0.00001624183,0.0001439327,3.187627e-7,0.0001779435,0.0005392533,0.9897394,0.00001003555,0.001949991,0.004455579],"study_design_scores_gemma":[0.001365053,0.0005159232,0.298953,0.00004195714,0.0002621291,0.00001368964,0.0004776772,0.004320367,0.5739187,0.00003789927,0.1192882,0.0008053645],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964009,0.0003644715,0.0004285251,0.0001790321,0.0001463962,0.0004610543,0.001981071,0.000006039046,0.00003251071],"genre_scores_gemma":[0.9931829,0.0007914315,0.004578357,0.0002511836,0.0002479625,0.00003482325,0.000799364,0.00003083282,0.0000831561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4158207,"threshold_uncertainty_score":0.6695376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04488845870774653,"score_gpt":0.2863626560169507,"score_spread":0.2414741973092041,"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."}}