{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01116526,0.001100106,0.0009589567,0.00220024,0.0009383475,0.003197601,0.001880193,0.00167362,0.00297155],"category_scores_gemma":[0.04563977,0.0006049348,0.001493742,0.001703969,0.0008110753,0.002101112,0.002116152,0.001574732,0.003289313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009553955,"about_ca_system_score_gemma":0.001746153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004210287,"about_ca_topic_score_gemma":0.00628462,"domain_scores_codex":[0.9921239,0.002377378,0.0007534572,0.002131274,0.00213826,0.000475721],"domain_scores_gemma":[0.9660934,0.01453435,0.003886318,0.007697961,0.007164157,0.0006237409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003413933,0.000397483,0.3546245,0.003121089,0.00139297,0.0008270406,0.001598308,0.04080325,0.1637642,0.005816536,0.01905825,0.4051824],"study_design_scores_gemma":[0.0002549017,0.00104584,0.143206,0.001483048,0.000605569,0.001264303,0.001644483,0.4981292,0.2880524,0.02247011,0.04151108,0.0003330511],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4803323,0.003417954,0.4843095,0.001737006,0.001309413,0.0003931402,0.008875065,0.01175002,0.007875648],"genre_scores_gemma":[0.7182139,0.0004031941,0.268975,0.001029707,0.0001283677,0.0001644901,0.009219883,0.0008686741,0.0009967631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01116526,"threshold_uncertainty_score":0.05904824,"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."}}