{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005547666,0.00005339955,0.00007877322,0.00003883924,0.00004714082,0.000006915035,0.00007096327,0.00005375531,0.000002871499],"category_scores_gemma":[0.000155079,0.00004918847,0.00001107361,0.00006000049,0.0002137754,0.00001042652,0.00006959524,0.00003911865,7.026962e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001652188,"about_ca_system_score_gemma":0.00001826184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001174968,"about_ca_topic_score_gemma":0.00001133471,"domain_scores_codex":[0.9993778,0.0001129256,0.000248868,0.0001436469,0.00004303036,0.00007373984],"domain_scores_gemma":[0.9996368,0.00002757337,0.0001588009,0.0001255107,0.00003331359,0.00001800534],"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":[0.00001989733,0.0000124688,0.04729605,0.00002567103,0.000006204742,6.935029e-8,0.000197318,0.0006055804,0.9512939,0.0001809772,0.000007584501,0.0003542808],"study_design_scores_gemma":[0.0001668081,0.00007446257,0.7550299,0.000006325334,0.000007117146,0.00001398078,0.0004619631,0.01353113,0.2304921,0.00005872624,0.0001069731,0.00005061315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856048,0.0001958968,0.0139115,0.00007434468,0.00005972958,0.0001000823,0.000008802585,0.000002637376,0.00004221994],"genre_scores_gemma":[0.9964157,0.00007289949,0.003400211,0.00001374136,0.00001114738,0.00001174846,0.00003972617,0.000003566616,0.00003127523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7208018,"threshold_uncertainty_score":0.2005847,"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."}}