{"id":"W6912372020","doi":"10.5281/zenodo.15678063","title":"Comparative performance of reference-based metagenomic tools to identify species-level taxa among families of bacteria: benchmarking Mycobacteriaceae and Neisseriaceae","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Metagenomics; RefSeq; Scripting language; Benchmarking; Python (programming language); Genome","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004160793,0.001685054,0.001120708,0.002722098,0.0007388978,0.001454443,0.002040855,0.000770047,0.01182878],"category_scores_gemma":[0.00670286,0.000581365,0.001566575,0.002636157,0.0003459568,0.001389158,0.001616134,0.0007618538,0.00812167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007273548,"about_ca_system_score_gemma":0.0009134097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00484973,"about_ca_topic_score_gemma":0.005032457,"domain_scores_codex":[0.9974983,0.0004969987,0.000236212,0.0008824934,0.0006621968,0.0002238307],"domain_scores_gemma":[0.9971325,0.001031285,0.0001685739,0.0007012335,0.0007682093,0.0001980866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.009721466,0.001652752,0.1487446,0.00701195,0.002625175,0.0005806683,0.001930659,0.06736479,0.1379738,0.007777974,0.3469875,0.2676287],"study_design_scores_gemma":[0.0008825432,0.00202539,0.2369042,0.0008982735,0.001091535,0.001156514,0.001719785,0.2383341,0.2942364,0.01239032,0.2097338,0.000627279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.3607062,0.002469905,0.06792618,0.0004332403,0.000427735,0.000325468,0.4769445,0.06850334,0.02226345],"genre_scores_gemma":[0.314769,0.0007354568,0.136076,0.0002827357,0.00005169837,0.0005930949,0.5271105,0.01607627,0.004305105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01182878,"threshold_uncertainty_score":0.03957123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05378883104348853,"score_gpt":0.2680120512050861,"score_spread":0.2142232201615976,"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."}}