{"id":"W3037979840","doi":"10.1101/2020.06.29.177634","title":"Alignment-free identification of COI DNA barcode data with the Python package Alfie","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Ontario Ministry of Economic Development, Job Creation and Trade; Ministero dello Sviluppo Economico; Ontario Genomics; Compute Canada; Genome Canada","keywords":"Barcode; Python (programming language); DNA barcoding; Classifier (UML); Computer science; Artificial intelligence; DNA sequencing; Machine learning; Replicate; Data mining; Biology; DNA; Genetics; Ecology; Mathematics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002565749,0.002747129,0.001411562,0.001782712,0.001086267,0.001780178,0.00307922,0.0008881824,0.03497915],"category_scores_gemma":[0.007435365,0.00144819,0.002246543,0.00121817,0.00138488,0.002570778,0.004042477,0.003155679,0.03690339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108884,"about_ca_system_score_gemma":0.002579303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002930515,"about_ca_topic_score_gemma":0.003304591,"domain_scores_codex":[0.9983901,0.0001828849,0.0001291227,0.0005025781,0.0005498728,0.0002454799],"domain_scores_gemma":[0.9979787,0.0006733266,0.0003062663,0.0004357815,0.0004387159,0.0001672435],"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":[0.001907215,0.0004763208,0.01318808,0.003294723,0.0007280656,0.0008365284,0.001095593,0.01370519,0.04465287,0.01313284,0.6757577,0.2312249],"study_design_scores_gemma":[0.0005026331,0.0003527563,0.02020115,0.0006604222,0.0002243167,0.001044946,0.0002211464,0.3254471,0.1380362,0.04452737,0.468149,0.0006329064],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.01186281,0.0002325009,0.1913588,0.0003548166,0.0002259222,0.0004080818,0.03297018,0.755209,0.007377877],"genre_scores_gemma":[0.1262073,0.0005914852,0.5200841,0.002413396,0.0002316263,0.003811766,0.1096856,0.2141188,0.02285604],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.03497915,"threshold_uncertainty_score":0.1170169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0222956779577698,"score_gpt":0.2091936758708788,"score_spread":0.186897997913109,"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."}}