{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009385317,0.00287222,0.00147839,0.003711055,0.001444186,0.004360156,0.005012067,0.001609705,0.01554041],"category_scores_gemma":[0.01988643,0.002703178,0.00220155,0.003019163,0.0008522657,0.00435156,0.00494776,0.003148461,0.01434885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008024953,"about_ca_system_score_gemma":0.00234588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002129833,"about_ca_topic_score_gemma":0.002253784,"domain_scores_codex":[0.9966806,0.0005786876,0.0005257471,0.0009361709,0.00104549,0.0002334139],"domain_scores_gemma":[0.9921494,0.002679525,0.001347501,0.00186312,0.001331621,0.0006288979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00703665,0.0007142279,0.04082838,0.007555497,0.002077037,0.00163016,0.003149735,0.008615921,0.1671483,0.01555818,0.4231728,0.3225132],"study_design_scores_gemma":[0.001109841,0.0007508185,0.02954764,0.001651571,0.0008571175,0.002344316,0.0006991361,0.06898145,0.2357867,0.02215435,0.6351811,0.0009359632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.02417719,0.001707423,0.4469693,0.0009370147,0.0006399465,0.0008153201,0.07366619,0.4448375,0.006250083],"genre_scores_gemma":[0.07555152,0.001642793,0.6814625,0.001066064,0.0002992524,0.002543352,0.1706299,0.06045841,0.006346115],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01554041,"threshold_uncertainty_score":0.05198789,"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."}}