{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005095747,0.0003997124,0.000427922,0.00007881156,0.0001733667,0.0001024344,0.0006487598,0.0001385403,0.0000338496],"category_scores_gemma":[0.0003698888,0.0003380529,0.000129726,0.0001253016,0.000134972,0.000005808493,0.001647158,0.0003006121,0.000007288733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007323625,"about_ca_system_score_gemma":0.0003169693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002607729,"about_ca_topic_score_gemma":0.00001148221,"domain_scores_codex":[0.997978,0.0001524124,0.0004972421,0.0008734707,0.0001794638,0.0003193858],"domain_scores_gemma":[0.9973992,0.0001428445,0.0003775381,0.001784503,0.0001434331,0.0001525206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00008098102,0.0000532009,0.01781697,0.00008804761,0.0003756816,9.017795e-7,0.00001317145,0.0003729985,0.9809012,0.00001997402,0.000257577,0.00001924826],"study_design_scores_gemma":[0.0004563942,0.000230105,0.6854655,0.00007903898,0.0003082724,2.875395e-8,0.00001996929,0.001231893,0.2961913,8.561254e-7,0.01534293,0.0006737852],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913555,0.001980952,0.0007244352,0.00009904966,0.000303,0.000843228,0.00468015,0.000009732154,0.000003938357],"genre_scores_gemma":[0.988597,0.001002106,0.009518705,0.0001821826,0.000280195,0.0003344447,0.00002129189,0.00006111458,0.000002984259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.68471,"threshold_uncertainty_score":0.9999071,"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."}}