{"id":"W2149205772","doi":"10.1186/1471-2105-12-328","title":"Classifying short genomic fragments from novel lineages using composition and homology","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic; Killam Trusts; Canada Research Chairs; Government of Canada; Genome Canada; Ontario Genomics; Ontario Genomics Institute","keywords":"Metagenomics; Taxonomic rank; Classifier (UML); Naive Bayes classifier; Artificial intelligence; Biology; Computer science; Rank (graph theory); Genome; Computational biology; Homology (biology); Bayes' theorem; Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Genetics; Support vector machine; Bayesian probability; Gene; Ecology","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":[0.001592802,0.0007657384,0.0007041473,0.002851912,0.0005239597,0.001319159,0.0007859449,0.00123902,0.001857849],"category_scores_gemma":[0.003964499,0.0002373002,0.0007652423,0.001574484,0.0007061804,0.001462013,0.0009203,0.0007726232,0.001588412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006068575,"about_ca_system_score_gemma":0.0006743261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001500775,"about_ca_topic_score_gemma":0.001766731,"domain_scores_codex":[0.9990037,0.0001527235,0.00008381662,0.0003339505,0.0003382129,0.0000876191],"domain_scores_gemma":[0.9968629,0.001330559,0.0007073607,0.0002252691,0.0006798975,0.0001941417],"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":[0.001290537,0.0003690463,0.08362349,0.001120767,0.0002759662,0.0004376268,0.000547438,0.04124871,0.2860985,0.002288844,0.001987254,0.5807118],"study_design_scores_gemma":[0.00005513921,0.0005054857,0.04621802,0.0001924862,0.0002160981,0.0009380316,0.0006661552,0.7915341,0.1441479,0.01035547,0.005061857,0.0001092472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4329837,0.001532789,0.5575454,0.0002643466,0.00006162454,0.0002688841,0.001273316,0.002489196,0.003580616],"genre_scores_gemma":[0.6324356,0.0004537212,0.3626714,0.0001891268,0.00005405407,0.0001409101,0.002500914,0.0001481332,0.00140618],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002851912,"threshold_uncertainty_score":0.008423626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06827311741666486,"score_gpt":0.2566565656054769,"score_spread":0.1883834481888121,"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."}}