{"id":"W4416850537","doi":"10.1099/mgen.0.001739","title":"From classification to confirmation: verifying taxonomic classifications by mapping metagenomic reads to reference genomes","year":2025,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Metagenomics; Genome; Reference genome; False positive paradox; Precision and recall; Taxonomic rank; Environmental DNA; Identification (biology)","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":[0.0001713259,0.0002749243,0.0002835295,0.000144804,0.0003031227,0.0001191981,0.0005119901,0.0001780226,0.00002460115],"category_scores_gemma":[0.00004306415,0.0003266263,0.00009074061,0.0002110245,0.00005931362,0.000002582614,0.0003219904,0.0001091309,0.0001714469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001705261,"about_ca_system_score_gemma":0.0002319792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001545429,"about_ca_topic_score_gemma":0.0001152759,"domain_scores_codex":[0.9983076,0.00006006487,0.0004978937,0.0007287925,0.00005977985,0.0003458937],"domain_scores_gemma":[0.9989669,0.00002542893,0.0001302228,0.000600449,0.0001412372,0.0001357457],"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":[0.00005139543,0.00002979479,0.0002474033,0.000008464645,0.0001332085,1.634383e-7,0.0003111206,0.0002449793,0.9613102,0.000305032,0.03149265,0.005865571],"study_design_scores_gemma":[0.000294258,0.00004570535,0.007482623,0.00001202625,0.00004128881,9.832233e-7,0.0005017854,0.00005690692,0.1836965,0.00006751605,0.8074796,0.0003207615],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703036,0.001522142,0.02132467,0.00208971,0.0004214654,0.0007214763,0.0007175519,0.00001632574,0.002883065],"genre_scores_gemma":[0.9798669,0.000478227,0.01423183,0.002260441,0.0002906519,0.0001423185,0.0006314611,0.00003550135,0.002062714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7776137,"threshold_uncertainty_score":0.9999186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607685209852086,"score_gpt":0.2652680696827137,"score_spread":0.2291912175841928,"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."}}