{"id":"W1569930069","doi":"10.1002/ece3.1497","title":"Toward accurate molecular identification of species in complex environmental samples: testing the performance of sequence filtering and clustering methods","year":2015,"lang":"en","type":"article","venue":"Ecology and Evolution","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":161,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministerio de Economía y Competitividad; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Cluster analysis; Computer science; Sequence (biology); Computational biology; Biological system; Artificial intelligence; Biology; Ecology; 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":[0.02009928,0.001527894,0.000971267,0.002302598,0.001387249,0.001479222,0.001403085,0.002470332,0.0005102638],"category_scores_gemma":[0.03507367,0.0005315079,0.001561308,0.002430158,0.001432683,0.001998413,0.002100075,0.001140991,0.0006212033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005699082,"about_ca_system_score_gemma":0.0007940579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00519521,"about_ca_topic_score_gemma":0.005711973,"domain_scores_codex":[0.9848802,0.005391821,0.001867168,0.003850451,0.003420262,0.0005900664],"domain_scores_gemma":[0.9651901,0.02395562,0.002895614,0.003001412,0.004247547,0.0007098041],"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":[0.003444227,0.00298458,0.2013417,0.00177045,0.001433245,0.0002204748,0.002668075,0.05941281,0.5869964,0.001013118,0.0004683396,0.1382466],"study_design_scores_gemma":[0.0001964731,0.01185563,0.2229045,0.0002449944,0.0006905217,0.0005590107,0.001240108,0.3014025,0.4564674,0.00138493,0.002717289,0.0003366712],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.953242,0.0006518837,0.04468829,0.0001122748,0.00005137776,0.0002387689,0.0003991297,0.0001433578,0.000472938],"genre_scores_gemma":[0.7128469,0.000823782,0.2825831,0.0002280379,0.00003980308,0.0005087179,0.002187883,0.0001918613,0.0005899045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02009928,"threshold_uncertainty_score":0.1062964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1299259790590974,"score_gpt":0.325367197772037,"score_spread":0.1954412187129396,"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."}}