{"id":"W2950884444","doi":"10.1371/journal.pbio.2005849","title":"EukRef: Phylogenetic curation of ribosomal RNA to enhance understanding of eukaryotic diversity and distribution","year":2018,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Protist diversity and phylogeny","field":"Biochemistry, Genetics and Molecular Biology","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of British Columbia","funders":"H2020 Marie Skłodowska-Curie Actions; European Regional Development Fund; Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche; Akademie Věd České Republiky; Tula Foundation; Gordon and Betty Moore Foundation; FP7 People: Marie-Curie Actions; National Science Foundation","keywords":"GenBank; Biology; Phylogenetic tree; Taxonomic rank; Annotation; Phylogenetics; Microbial ecology; Computational biology; Metagenomics; Phylogenomics; Evolutionary biology; DNA sequencing; Environmental DNA; Sequence database; Ecology; Bioinformatics; Biodiversity; Genetics; Taxon; Clade; DNA; Gene","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":[],"consensus_categories":[],"category_scores_codex":[0.00008570046,0.00007884781,0.0001299681,0.00002874496,0.0001645321,0.000001956662,0.0001236392,0.0001161651,0.00001235048],"category_scores_gemma":[0.00007577782,0.00008023139,0.00003000487,0.00007577714,0.0002820308,0.000003608363,0.0004608038,0.00003252034,0.000003012363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000176703,"about_ca_system_score_gemma":0.00001790241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003617615,"about_ca_topic_score_gemma":0.00003544373,"domain_scores_codex":[0.9994084,0.00005929437,0.000133781,0.0002161743,0.00004929119,0.00013306],"domain_scores_gemma":[0.9996192,0.00001351448,0.00009353313,0.0001386168,0.00008736969,0.0000477321],"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":[0.0001502026,0.00004371547,0.1600475,0.00002342328,0.0000479569,2.728142e-7,0.000148391,0.00000162272,0.8380712,0.001162125,0.00005349602,0.0002500144],"study_design_scores_gemma":[0.0002063125,0.001135483,0.08859815,0.00001452978,0.00003235575,0.000001944964,0.00005183766,0.00002974894,0.9084655,0.001295327,0.0000671547,0.0001016547],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9792625,0.0001211906,0.02000631,0.00005498716,0.00006722298,0.0001391181,0.0001814876,0.000003735577,0.0001634074],"genre_scores_gemma":[0.9994305,0.00004922738,0.0002561545,0.00004676557,0.00007335913,0.000001500176,0.0001239616,0.000003194611,0.00001529793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0714494,"threshold_uncertainty_score":0.3271741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03029750492932147,"score_gpt":0.261456548257557,"score_spread":0.2311590433282355,"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."}}