{"id":"W4403299283","doi":"10.1093/bioinformatics/btae601","title":"MNBC: a multithreaded Minimizer-based Naïve Bayes Classifier for improved metagenomic sequence classification","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada; University of Manitoba; Agriculture and Agri-Food Canada; Canadian Food Inspection Agency","funders":"Public Health Agency; Public Health Agency of Canada; Agriculture and Agri-Food Canada; Canadian Food Inspection Agency; University of Lethbridge","keywords":"Metagenomics; Naive Bayes classifier; Classifier (UML); Computer science; Bayes' theorem; Artificial intelligence; Bayes classifier; Pattern recognition (psychology); Sequence (biology); Machine learning; Computational biology; Bayesian probability; Biology; Support vector machine; Genetics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002042552,0.0002169864,0.0001867599,0.00007061778,0.0001142725,0.0001032235,0.0001989825,0.0001643685,0.000007077058],"category_scores_gemma":[0.00008366531,0.0001875473,0.0001797529,0.00008813557,0.0000979172,0.000003655999,0.00005645135,0.00006674754,0.00002566088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003581529,"about_ca_system_score_gemma":0.0002080354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005059543,"about_ca_topic_score_gemma":0.00001774937,"domain_scores_codex":[0.9989656,0.0000159482,0.000394371,0.0002652828,0.00007710482,0.0002816607],"domain_scores_gemma":[0.9993104,0.00005574178,0.0001026224,0.0003510251,0.0001065673,0.00007361078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008413778,0.00003316912,0.00006009879,0.0002715259,0.0002091457,4.602289e-7,0.0002693267,0.00009873966,0.9706784,0.0005022152,0.005148844,0.02264397],"study_design_scores_gemma":[0.001258389,0.0004982543,0.0007543616,0.00005211767,0.0001815561,0.000009311759,0.000588608,0.4996117,0.1733179,0.0003213458,0.3227791,0.0006272803],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6323965,0.007983851,0.3436674,0.002598112,0.002769643,0.003698177,0.002210152,0.0001459312,0.004530198],"genre_scores_gemma":[0.9047497,0.0002800593,0.09274755,0.000504222,0.0002633593,0.0002313277,0.0004305115,0.00004348296,0.0007497887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7973605,"threshold_uncertainty_score":0.7647958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05319947061359019,"score_gpt":0.2939683203582025,"score_spread":0.2407688497446123,"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."}}