{"id":"W2793383967","doi":"10.1101/253377","title":"Taxonomic identification from metagenomic and metabarcoding data using any genetic marker","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Food Inspection Agency","funders":"Vetenskapsrådet; Svenska Forskningsrådet Formas; Project Apis m.","keywords":"Metagenomics; Biology; Identification (biology); Amplicon; Computational biology; Taxonomic rank; Biodiversity; Genetic diversity; Biological classification; DNA sequencing; Genetic marker; Shotgun sequencing; Evolutionary biology; Genetics; Ecology; DNA; Gene; 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":[0.008194762,0.00226947,0.001529398,0.006536122,0.001619697,0.005212131,0.00204627,0.001369937,0.007150716],"category_scores_gemma":[0.01867292,0.001986249,0.001962304,0.004703229,0.0007599635,0.003392525,0.00279403,0.003158725,0.009550487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005763916,"about_ca_system_score_gemma":0.001843026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00106987,"about_ca_topic_score_gemma":0.002227097,"domain_scores_codex":[0.9956264,0.0006186676,0.0006858336,0.000975358,0.001885703,0.0002080496],"domain_scores_gemma":[0.9924152,0.001570566,0.00110056,0.003120523,0.001441479,0.0003516176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001279738,0.0003634808,0.03347246,0.004303746,0.001365002,0.001011324,0.002930705,0.001029158,0.4150337,0.008611787,0.1008484,0.4297505],"study_design_scores_gemma":[0.0001919434,0.0002572769,0.04631755,0.001007673,0.0007720627,0.002741842,0.0005938629,0.01338207,0.3608748,0.02309399,0.5501858,0.0005810332],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05414001,0.00536794,0.7202622,0.00287515,0.002264003,0.000566571,0.08490449,0.115812,0.01380768],"genre_scores_gemma":[0.04765361,0.003116613,0.8328815,0.0005508559,0.0004870546,0.0004228803,0.08608688,0.02250255,0.006298107],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008194762,"threshold_uncertainty_score":0.04333854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03960303071492557,"score_gpt":0.2214051871762717,"score_spread":0.1818021564613461,"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."}}