{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007107451,0.0001438155,0.0001462023,0.00003510783,0.000113467,0.00001921166,0.0001070635,0.0001297639,0.000005779951],"category_scores_gemma":[0.000008313782,0.0001385823,0.00004412158,0.00002719695,0.00009234789,0.000002315734,0.0002023733,0.00005376101,0.000004191617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001127438,"about_ca_system_score_gemma":0.00003127518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003948663,"about_ca_topic_score_gemma":0.00001729501,"domain_scores_codex":[0.9993372,0.00001201824,0.0002671917,0.0001489594,0.00005413108,0.0001805215],"domain_scores_gemma":[0.9996181,0.00001032978,0.00008088483,0.0001974941,0.0000366419,0.00005655129],"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":[0.00006013586,0.00007093243,0.1034162,0.00004825017,0.0001556016,8.182577e-7,0.0009172566,0.0002047313,0.8932415,0.00007190226,0.00004758828,0.001765166],"study_design_scores_gemma":[0.002563752,0.0006324041,0.6400582,0.00007757086,0.0003435406,0.0001433599,0.002325994,0.1470478,0.2014248,0.0003498202,0.003659735,0.001372928],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9319423,0.0005723845,0.06645057,0.000003157938,0.0001524039,0.0001259086,0.00007236974,0.000004522461,0.0006763816],"genre_scores_gemma":[0.7523073,0.0001848455,0.2471997,0.0001265133,0.00008913083,0.000004151194,0.00006657157,0.00001179591,0.000009983369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6918167,"threshold_uncertainty_score":0.5651222,"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."}}