{"id":"W3086141885","doi":"10.3897/mbmg.4.55815","title":"Alignment-free classification of COI DNA barcode data with the Python package Alfie","year":2020,"lang":"en","type":"article","venue":"Metabarcoding and Metagenomics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Barcode; Python (programming language); Classifier (UML); DNA barcoding; Computer science; Artificial intelligence; DNA sequencing; R package; Machine learning; Biology; Data mining; DNA; Genetics; Ecology; Programming language","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":[0.001901104,0.00277452,0.001371724,0.001720316,0.001089692,0.001654156,0.002817001,0.000871286,0.02863211],"category_scores_gemma":[0.00589524,0.001189438,0.002319369,0.001345746,0.001199795,0.002370253,0.003214262,0.003377834,0.0301761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001186357,"about_ca_system_score_gemma":0.002517418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003835348,"about_ca_topic_score_gemma":0.005004964,"domain_scores_codex":[0.9986432,0.000135631,0.0001099827,0.0004673354,0.0004324784,0.0002113365],"domain_scores_gemma":[0.9984307,0.000540435,0.0002121048,0.0003211866,0.0003662693,0.0001293674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001541577,0.0005008712,0.0123496,0.002882902,0.0006886595,0.0006381386,0.001006658,0.01399069,0.04405389,0.01062365,0.6382736,0.2734498],"study_design_scores_gemma":[0.0004174843,0.0003614677,0.02076244,0.0004706956,0.0002080459,0.0009008954,0.0002201444,0.3966775,0.1229132,0.04134351,0.415194,0.0005306329],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.01578497,0.0002724978,0.2596991,0.0004122593,0.0002710394,0.0005401511,0.03943768,0.6745053,0.009076961],"genre_scores_gemma":[0.1015489,0.0005989692,0.6000522,0.002292724,0.0002115223,0.004118151,0.1196406,0.147252,0.02428496],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.02863211,"threshold_uncertainty_score":0.09578395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06206540775624807,"score_gpt":0.230077760631354,"score_spread":0.1680123528751059,"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."}}