{"id":"W3136292736","doi":"10.1101/2021.03.16.434153","title":"BugSeq 16S: NanoCLUST with Improved Consensus Sequence Classification","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Classifier (UML); Nanopore sequencing; Artificial intelligence; Computer science; Pattern recognition (psychology); Data mining; DNA sequencing; Biology; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":false,"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":[0.007549921,0.001645559,0.001787706,0.002546215,0.00104686,0.001701912,0.002041781,0.001344558,0.007110883],"category_scores_gemma":[0.01506569,0.001164804,0.001461627,0.001715437,0.0007163822,0.00191652,0.001627717,0.001856446,0.007239327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023623,"about_ca_system_score_gemma":0.001970397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003472421,"about_ca_topic_score_gemma":0.005665359,"domain_scores_codex":[0.9946668,0.0009228559,0.0007132877,0.001938746,0.001446079,0.0003121126],"domain_scores_gemma":[0.9938515,0.002266202,0.0008264276,0.001097197,0.001599878,0.0003587731],"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":[0.006345043,0.0003964553,0.05641669,0.00405256,0.001159594,0.0008633222,0.001694013,0.01303277,0.5270681,0.007764374,0.1618607,0.2193463],"study_design_scores_gemma":[0.0006687901,0.0009711509,0.02107853,0.0005863437,0.0003342705,0.001576642,0.0005650488,0.243136,0.5038686,0.01024738,0.2162686,0.0006987253],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2264381,0.001807015,0.5071309,0.001670806,0.00175102,0.0007042194,0.1181172,0.1361382,0.006242538],"genre_scores_gemma":[0.1617044,0.0002198731,0.7518142,0.001007439,0.0001375571,0.0007489148,0.06911727,0.01187837,0.003371999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007549921,"threshold_uncertainty_score":0.03992832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01994633365981285,"score_gpt":0.2242410848445036,"score_spread":0.2042947511846908,"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."}}