{"id":"W2338899252","doi":"10.1139/gen-2015-0184","title":"The effects of parameter choice on defining molecular operational taxonomic units and resulting ecological analyses of metabarcoding data","year":2016,"lang":"en","type":"article","venue":"Genome","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Biology; Cluster analysis; Ecology; Taxonomic rank; Biodiversity; DNA barcoding; Simple (philosophy); Evolutionary biology; Computer science; Taxon; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0002304511,0.00007493931,0.0001144948,0.00001483483,0.0001544597,0.000007793967,0.0002718075,0.00002278604,0.00004161064],"category_scores_gemma":[0.0006986229,0.00004227398,0.00001720361,0.000064927,0.000362056,0.00008831553,0.0008406276,0.00003709444,0.00002820469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004758599,"about_ca_system_score_gemma":0.000001667829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004777979,"about_ca_topic_score_gemma":0.00000711533,"domain_scores_codex":[0.9992996,0.00007270964,0.0001386402,0.000221353,0.0001459432,0.000121754],"domain_scores_gemma":[0.9983562,0.001276352,0.00008845289,0.0002499898,0.000002973691,0.00002607849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001475974,0.0000276473,0.1385761,0.000008474713,0.0000766931,0.000002166916,0.00008299873,0.0002016704,0.858301,0.0000735187,0.00006059117,0.002574377],"study_design_scores_gemma":[0.0003199273,0.000123891,0.9538588,0.00001679381,0.00004742343,6.548893e-7,0.0000724288,0.00004811019,0.04449103,0.0000306677,0.0009047384,0.0000855517],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990088,0.0002768835,0.0000655999,0.00009335145,0.00002429006,0.0001087121,0.00005515229,0.000003663296,0.0003635617],"genre_scores_gemma":[0.9963889,0.000157328,0.003339668,0.00006274792,0.000004811716,0.000003506165,0.000006081109,0.000002786849,0.00003418422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8152826,"threshold_uncertainty_score":0.1723883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06556737303967468,"score_gpt":0.271968952736585,"score_spread":0.2064015796969103,"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."}}