{"id":"W4318454197","doi":"10.1101/2023.01.29.526108","title":"Rapid and accurate taxonomic classification of cpn60 amplicon sequence variants","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bacterial Identification and Susceptibility Testing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Amplicon; Biology; Computational biology; Classifier (UML); Barcode; Microbiome; Multilocus sequence typing; Bayesian probability; Metagenomics; Identification (biology); Naive Bayes classifier; Genetics; Artificial intelligence; Gene; Computer science; Polymerase chain reaction; Genotype; Support vector machine; Ecology","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":[0.002448608,0.0005253101,0.0007009175,0.002080998,0.0004719628,0.001227403,0.000536039,0.0007781675,0.001382362],"category_scores_gemma":[0.006727468,0.0002951152,0.0004337313,0.0009298428,0.0002758316,0.0007847179,0.0008830135,0.0006299153,0.002121919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003844568,"about_ca_system_score_gemma":0.0003947158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002022726,"about_ca_topic_score_gemma":0.002688563,"domain_scores_codex":[0.9979221,0.0003797401,0.0001373337,0.0007543346,0.0006308366,0.0001757468],"domain_scores_gemma":[0.9978141,0.0006203951,0.0002556238,0.0002002278,0.000984791,0.0001248761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006561803,0.0002290575,0.08253714,0.0003526992,0.00008840744,0.0001545646,0.0003325742,0.002887871,0.7200134,0.0007507585,0.003225382,0.188772],"study_design_scores_gemma":[0.00005467161,0.0003722131,0.254347,0.0001951231,0.0001214751,0.001221951,0.0005436509,0.2442989,0.4796823,0.003020094,0.01597118,0.0001715155],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.692902,0.001754482,0.289193,0.0003759194,0.0001979712,0.0003962096,0.008872016,0.002727531,0.003580901],"genre_scores_gemma":[0.6322699,0.0003820078,0.3523258,0.0001856964,0.00005122391,0.0001649743,0.0121641,0.0003368183,0.002119486],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.002448608,"threshold_uncertainty_score":0.01294959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0642893172600156,"score_gpt":0.26784354476923,"score_spread":0.2035542275092144,"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."}}