{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006571073,0.0002912498,0.0003201817,0.0001132159,0.00008883905,0.000133836,0.0003617944,0.0004547859,0.00001517248],"category_scores_gemma":[0.0005848679,0.0003399639,0.00008319198,0.0001623925,0.0001507355,0.00001218893,0.0003987633,0.0002317844,0.00002353325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004966808,"about_ca_system_score_gemma":0.000330076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006264119,"about_ca_topic_score_gemma":0.000007840761,"domain_scores_codex":[0.9980057,0.00014273,0.0005462631,0.0009256433,0.0001225595,0.0002570981],"domain_scores_gemma":[0.9978055,0.00003239702,0.0005475412,0.001129947,0.0003552664,0.0001293396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002311601,0.00003586148,0.004569566,0.0002073023,0.00005768119,0.000001380533,0.000003388295,0.000008158064,0.9946907,0.0001899874,0.0002020884,0.0000108066],"study_design_scores_gemma":[0.0002607812,0.00004595915,0.5120418,0.0001326866,0.00004773759,2.108736e-8,0.000004933214,0.0005253333,0.4850538,0.000004145164,0.00148301,0.0003997577],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967293,0.0002892769,0.001260102,0.0001474329,0.0006782001,0.0004711026,0.000319681,0.00009809952,0.000006762873],"genre_scores_gemma":[0.9970379,0.0004819449,0.002004152,0.00004610987,0.0002437126,0.00009986115,0.000006981619,0.00006476673,0.00001458363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5096368,"threshold_uncertainty_score":0.9999052,"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."}}