{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005655911,0.001834725,0.001647796,0.001836416,0.001036186,0.00182476,0.003101227,0.001659009,0.004222439],"category_scores_gemma":[0.01659887,0.0008594077,0.001299443,0.00138938,0.0005537188,0.001754986,0.001553578,0.002908155,0.002590547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001557608,"about_ca_system_score_gemma":0.00419855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01494081,"about_ca_topic_score_gemma":0.01964018,"domain_scores_codex":[0.9968623,0.0008809976,0.0002543351,0.0006926358,0.001133638,0.0001761404],"domain_scores_gemma":[0.9957796,0.001849911,0.0002653376,0.0004798517,0.001420799,0.000204486],"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":[0.00121638,0.0005116121,0.0163924,0.001103388,0.0005843376,0.0002375782,0.0003430751,0.2001857,0.02998409,0.00741464,0.06972952,0.6722973],"study_design_scores_gemma":[0.00009313922,0.00009002748,0.0007517915,0.00004775331,0.00004160918,0.00005220199,0.00002917532,0.9793618,0.007384581,0.005572252,0.006538125,0.00003748264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02688105,0.001418576,0.9275458,0.0007907262,0.0003364011,0.0005001798,0.003316924,0.0372513,0.001959116],"genre_scores_gemma":[0.1108616,0.0002966096,0.8754284,0.0006595201,0.0001579624,0.0006162139,0.008070659,0.001798402,0.002110743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01494081,"threshold_uncertainty_score":0.0299117,"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."}}