{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003433173,0.0001610495,0.0002198812,0.00001350835,0.0002423135,0.00002822997,0.0008247671,0.00003275171,0.0001225704],"category_scores_gemma":[0.00006567087,0.0001093048,0.00003479165,0.0001264951,0.0005268875,0.0002079002,0.001568791,0.0001099248,0.00005713462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000399801,"about_ca_system_score_gemma":0.000002969871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005531102,"about_ca_topic_score_gemma":0.00002791688,"domain_scores_codex":[0.9988104,0.00008246623,0.0001765236,0.0004405769,0.0002950629,0.0001949609],"domain_scores_gemma":[0.9988955,0.00008557009,0.0001427447,0.0007750763,0.000003130865,0.00009801697],"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":[0.0001332567,0.000122554,0.2317082,0.0000623279,0.000411737,0.00001231011,0.005075162,0.0002973134,0.7289252,0.0006151452,0.02095894,0.01167784],"study_design_scores_gemma":[0.002307701,0.000370206,0.6720562,0.00002241585,0.001314898,0.00001409425,0.008916781,0.003873847,0.08644065,0.000196532,0.2236179,0.0008687309],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903768,0.0004497513,0.002019554,0.004628082,0.00003634429,0.0002781137,0.0002408027,0.0000268765,0.001943618],"genre_scores_gemma":[0.9853969,0.0006118395,0.01316854,0.0006031044,0.00002854505,0.000005062544,0.00003988122,0.00001319594,0.0001328849],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6424845,"threshold_uncertainty_score":0.4457321,"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."}}