{"id":"W2951013216","doi":"10.1038/s41598-018-22505-4","title":"Automated high throughput animal CO1 metabarcode classification","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":177,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Ontario Forest Research Institute; Natural Resources Canada","funders":"Government of Canada","keywords":"Classifier (UML); Barcode; DNA barcoding; Biological classification; Biodiversity; Computer science; Taxonomic rank; Biota; Biology; Artificial intelligence; Machine learning; Data mining; Ecology; Evolutionary biology","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":[],"consensus_categories":[],"category_scores_codex":[0.001678227,0.001057553,0.000887416,0.003857948,0.001186755,0.002008038,0.001728287,0.00110918,0.003281838],"category_scores_gemma":[0.005978326,0.0006947725,0.0007684851,0.002331343,0.0004447817,0.001110178,0.001103508,0.001221198,0.004311881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000728654,"about_ca_system_score_gemma":0.001104854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004704033,"about_ca_topic_score_gemma":0.01030094,"domain_scores_codex":[0.9981793,0.0002432322,0.00009709048,0.0005964639,0.0007579844,0.0001259112],"domain_scores_gemma":[0.9959676,0.001026355,0.0005315832,0.0007029055,0.001605187,0.000166326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004380131,0.0001845607,0.03267697,0.0008542526,0.0002191823,0.0003253888,0.0004555232,0.005411458,0.4445134,0.002423971,0.02561552,0.4868818],"study_design_scores_gemma":[0.00007832656,0.0003186332,0.0726252,0.0001977934,0.0001587012,0.001630934,0.0003668039,0.2635928,0.5363889,0.009417905,0.1149317,0.0002922607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09689768,0.00154983,0.8533777,0.0007663636,0.0002798101,0.0004700661,0.01564936,0.02530828,0.005700861],"genre_scores_gemma":[0.07505745,0.0003506469,0.9029964,0.0001964385,0.00007530639,0.0003274722,0.01707127,0.0008404406,0.003084593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004704033,"threshold_uncertainty_score":0.01097882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316163589301985,"score_gpt":0.246137571206475,"score_spread":0.2229759353134552,"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."}}