{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04221859,0.003396906,0.003422302,0.00359035,0.00222787,0.008914732,0.007838952,0.00447213,0.005345659],"category_scores_gemma":[0.1258174,0.00233531,0.002323765,0.005414647,0.001215793,0.01433072,0.005750519,0.006181227,0.007704781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001389489,"about_ca_system_score_gemma":0.00177911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003548632,"about_ca_topic_score_gemma":0.003581851,"domain_scores_codex":[0.9714776,0.008842502,0.005211268,0.007473907,0.005595429,0.001399272],"domain_scores_gemma":[0.9185194,0.05181401,0.002220048,0.01791797,0.007555183,0.001973317],"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":[0.01560176,0.003328122,0.1286256,0.008006623,0.003714421,0.001980956,0.003447536,0.03015378,0.09179898,0.009647227,0.1300642,0.5736309],"study_design_scores_gemma":[0.00374024,0.002879248,0.06473453,0.003693962,0.002525633,0.006981132,0.004151117,0.2629194,0.3097245,0.0595209,0.2757154,0.00341394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6155828,0.02690761,0.1744964,0.005665245,0.002758537,0.001295018,0.02790233,0.1293517,0.01604049],"genre_scores_gemma":[0.5905423,0.004166467,0.3186477,0.006353294,0.0002796133,0.001768882,0.05244755,0.02307257,0.002721624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04221859,"threshold_uncertainty_score":0.223276,"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."}}