{"id":"W2769252189","doi":"10.1101/219675","title":"Automated high throughput animal DNA metabarcode classification","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Ontario Forest Research Institute; Natural Resources Canada","funders":"Government of Canada","keywords":"Barcode; DNA barcoding; Classifier (UML); Computer science; DNA sequencing; Biology; Throughput; Computational biology; Data mining; Artificial intelligence; DNA; Evolutionary biology; Genetics","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":[0.002674107,0.0008806683,0.0008949635,0.003579377,0.0009499454,0.00213134,0.001614985,0.001283917,0.003840843],"category_scores_gemma":[0.006219489,0.0005358735,0.0007806523,0.002277351,0.0004412273,0.001129611,0.001043145,0.001120995,0.005117998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007798519,"about_ca_system_score_gemma":0.001193756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003379727,"about_ca_topic_score_gemma":0.006850418,"domain_scores_codex":[0.9976548,0.0003776876,0.0001473946,0.0006907636,0.0009708395,0.0001585438],"domain_scores_gemma":[0.9965677,0.0008171861,0.0003724929,0.0005056488,0.001575719,0.0001611879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006301556,0.0002055339,0.04135742,0.001034844,0.0001880085,0.0004019399,0.0005748696,0.004100603,0.5416574,0.003685541,0.0296425,0.3765212],"study_design_scores_gemma":[0.0001082942,0.000304907,0.09026279,0.0002510624,0.0001625422,0.001447333,0.0004449209,0.180383,0.5842007,0.009806096,0.1323638,0.0002646303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2317614,0.002684677,0.6884389,0.001444449,0.0005133096,0.0006881037,0.03061157,0.03318395,0.01067365],"genre_scores_gemma":[0.1070337,0.0006409984,0.8594831,0.00043531,0.00007663202,0.0003381385,0.02552428,0.001183368,0.005284388],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003840843,"threshold_uncertainty_score":0.01414216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02487876028021978,"score_gpt":0.229219700511457,"score_spread":0.2043409402312373,"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."}}