{"id":"W3146187752","doi":"10.1186/s12859-021-04018-6","title":"Reliable genomic strategies for species classification of plant genetic resources","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Newfoundland and Labrador; Ministerie van Landbouw, Natuur en Voedselkwaliteit","keywords":"Naive Bayes classifier; Classifier (UML); Documentation; Computer science; Data mining; Random forest; Variety (cybernetics); Bayes' theorem; Machine learning; Artificial intelligence; Support vector machine; Bayesian probability","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01148708,0.001029417,0.001215498,0.006084551,0.001030761,0.003330581,0.002002695,0.001163696,0.002669359],"category_scores_gemma":[0.03912258,0.0005145945,0.001213617,0.005095125,0.00109689,0.003948029,0.001921375,0.001775473,0.002612292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001408789,"about_ca_system_score_gemma":0.002032845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002454394,"about_ca_topic_score_gemma":0.004414554,"domain_scores_codex":[0.9940609,0.002291509,0.0006116622,0.001513038,0.001250607,0.0002721777],"domain_scores_gemma":[0.9700118,0.01336624,0.004098036,0.005474126,0.006263093,0.0007866462],"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":[0.0008741331,0.0004986016,0.0974934,0.002448448,0.00046979,0.0005232252,0.002403063,0.03074413,0.08848181,0.01772994,0.01168901,0.7466444],"study_design_scores_gemma":[0.0002174763,0.0006457947,0.1623114,0.001415226,0.0006786389,0.001366642,0.003361125,0.5322748,0.09531514,0.1328314,0.06919388,0.0003883137],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1384938,0.001866372,0.8368928,0.001070646,0.0001457579,0.0004939979,0.01106874,0.005783788,0.004184106],"genre_scores_gemma":[0.2311714,0.0003300467,0.7541202,0.0001608406,0.00006159557,0.0002548587,0.01294576,0.0004917283,0.0004636509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01148708,"threshold_uncertainty_score":0.06075025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02844512426101886,"score_gpt":0.2325085918689675,"score_spread":0.2040634676079486,"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."}}