{"id":"W2809066811","doi":"10.1093/bioinformatics/bty482","title":"Metaxa2 Database Builder: enabling taxonomic identification from metagenomic or metabarcoding data using any genetic marker","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Food Inspection Agency","funders":"Vetenskapsrådet; Svenska Forskningsrådet Formas; Project Apis m.","keywords":"Metagenomics; Identification (biology); Biology; Amplicon; Taxonomic rank; DNA barcoding; Software; Computational biology; Genetic marker; Computer science; Data mining; Evolutionary biology; Gene; Genetics; Ecology; Taxon; Polymerase chain reaction","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005579083,0.0002690498,0.0002708138,0.0000785751,0.0005661114,0.0001505625,0.001136879,0.00007025467,0.003039862],"category_scores_gemma":[0.000126522,0.0002366294,0.00005798817,0.0002225654,0.0005001726,0.001677168,0.002866058,0.0001156711,0.003243652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003257649,"about_ca_system_score_gemma":0.00001150975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006572314,"about_ca_topic_score_gemma":0.0001510641,"domain_scores_codex":[0.9980532,0.00005849213,0.0006139909,0.0004694092,0.0003994083,0.0004055162],"domain_scores_gemma":[0.9979612,0.00008811709,0.0003960073,0.00141884,0.000007967777,0.0001278889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003040318,0.0004609205,0.4844743,0.0002239394,0.001755171,0.00004857102,0.005236142,0.001927741,0.4044372,0.00002624198,0.05237234,0.04873337],"study_design_scores_gemma":[0.001527142,0.0001105264,0.376635,0.00008369984,0.001671978,0.00004067176,0.004692933,0.4787184,0.03911004,0.00006366617,0.09567601,0.001669909],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.960534,0.0002533696,0.03634512,0.00003553843,0.0004191578,0.0004823614,0.001205825,0.00006925623,0.0006553903],"genre_scores_gemma":[0.3303747,0.0003635037,0.6682131,0.0002560676,0.0001410205,0.0000065252,0.0003641053,0.00002440962,0.0002565943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.631868,"threshold_uncertainty_score":0.9978715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0907229681115546,"score_gpt":0.2702370529449247,"score_spread":0.1795140848333701,"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."}}