{"id":"W2897089549","doi":"10.1101/441576","title":"Nomenclature Errors in Public 16S rRNA Gene Reference Databases","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Calgary","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Nomenclature; Biology; 16S ribosomal RNA; Taxonomic rank; Reference database; Taxon; Taxonomy (biology); Database; Information retrieval; Computational biology; Gene; Computer science; Genetics; Zoology; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09327026,0.001191841,0.001928371,0.01492596,0.002818565,0.00886328,0.003899747,0.002057344,0.003125019],"category_scores_gemma":[0.2641466,0.001146602,0.0009408318,0.02299785,0.002516137,0.004724132,0.004210421,0.002837038,0.004172912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004389449,"about_ca_system_score_gemma":0.005852252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003653137,"about_ca_topic_score_gemma":0.003188103,"domain_scores_codex":[0.8004026,0.07046238,0.05204804,0.0142543,0.06019938,0.002633162],"domain_scores_gemma":[0.597262,0.1768011,0.0621454,0.09033944,0.07150457,0.001947513],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002548537,0.0007071335,0.08754557,0.01418609,0.001194506,0.00379788,0.01799632,0.007685036,0.05892157,0.07617272,0.1503865,0.578858],"study_design_scores_gemma":[0.0001130345,0.0002093771,0.04181258,0.00940338,0.0005595447,0.003040618,0.006183813,0.009995003,0.06578418,0.05092378,0.8116192,0.0003554995],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2776882,0.04222246,0.5021867,0.02417349,0.02093319,0.002131947,0.06682128,0.0191493,0.04469358],"genre_scores_gemma":[0.3921762,0.01256205,0.4828838,0.01148202,0.00163048,0.002110112,0.08467495,0.005217082,0.007263303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9067298,"threshold_uncertainty_score":0.4932662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0358299808408631,"score_gpt":0.2231527791561833,"score_spread":0.1873227983153202,"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."}}