{"id":"W2952043149","doi":"10.1371/journal.pone.0200177","title":"Over 2.5 million COI sequences in GenBank and growing","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Natural Resources Canada","funders":"","keywords":"GenBank; Barcode; Usability; Annotation; Popularity; Biology; Database; Geography; Computer science; Evolutionary biology; Information retrieval; Bioinformatics; 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":[0.007460146,0.0006952507,0.0009986992,0.007942265,0.001384334,0.002816178,0.001442188,0.001217767,0.008262669],"category_scores_gemma":[0.01887029,0.000467621,0.0006633979,0.01938733,0.0008623681,0.002524222,0.001851176,0.001736584,0.005572562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001395761,"about_ca_system_score_gemma":0.003124113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008906369,"about_ca_topic_score_gemma":0.01538097,"domain_scores_codex":[0.9945956,0.0008551329,0.0006493034,0.001289742,0.002351602,0.0002586502],"domain_scores_gemma":[0.983366,0.004066342,0.003996502,0.002264916,0.005175672,0.001130641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001097344,0.0001949135,0.1169686,0.007665824,0.0004077056,0.002250838,0.004717551,0.000994377,0.07875064,0.008098047,0.07646511,0.7023891],"study_design_scores_gemma":[0.00003082952,0.0002055116,0.1528637,0.00229897,0.0002758855,0.003635517,0.002261963,0.001193755,0.0139652,0.003162923,0.8199714,0.00013437],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4507536,0.1368004,0.08681415,0.02108502,0.006707838,0.0006378508,0.2194429,0.008318389,0.06943991],"genre_scores_gemma":[0.2860027,0.06754573,0.2162476,0.006304748,0.002435572,0.0005477195,0.394642,0.001648898,0.02462511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008906369,"threshold_uncertainty_score":0.03945351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03230627986650756,"score_gpt":0.2040242507341725,"score_spread":0.1717179708676649,"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."}}