{"id":"W4416373688","doi":"10.1016/j.isci.2025.114029","title":"Run-length compressed metagenomic read classification with SMEM-finding and tagging","year":2025,"lang":"en","type":"article","venue":"iScience","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":"National Human Genome Research Institute; Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek; National Institutes of Health; National Science Foundation","keywords":"Metagenomics; Identifier; Task (project management); Class (philosophy); Identification (biology); Pattern recognition (psychology)","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":[0.0007342275,0.0009341189,0.0008495888,0.002008048,0.0005468146,0.00136272,0.001250693,0.001041387,0.003551125],"category_scores_gemma":[0.003713151,0.0003352462,0.0009224645,0.002400786,0.0003986392,0.001279863,0.001135317,0.0008479996,0.003026674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005264467,"about_ca_system_score_gemma":0.001258438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002364387,"about_ca_topic_score_gemma":0.005239249,"domain_scores_codex":[0.9993031,0.00006296133,0.00007921542,0.0002577965,0.0002331137,0.00006373898],"domain_scores_gemma":[0.9982374,0.0004425506,0.0002204411,0.0005756293,0.0004304805,0.00009354579],"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":[0.001842751,0.0003935935,0.02054225,0.0006997688,0.0002295305,0.0003984029,0.0005256135,0.0140554,0.2527776,0.002515694,0.01199192,0.6940274],"study_design_scores_gemma":[0.0001877214,0.0006365587,0.02463348,0.0001305574,0.0001868505,0.001265952,0.0007621396,0.6158687,0.3132529,0.01207024,0.03084173,0.0001631182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2000412,0.0008802415,0.7473632,0.0003660675,0.0002488622,0.0003123,0.007827773,0.03971203,0.003248419],"genre_scores_gemma":[0.2660967,0.0002064811,0.7091708,0.000254697,0.00008530948,0.0003303589,0.01689122,0.001194975,0.005769442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003551125,"threshold_uncertainty_score":0.01187968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076258872854633,"score_gpt":0.2647410485507156,"score_spread":0.2439784598221692,"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."}}