{"id":"W2121628067","doi":"10.1093/bioinformatics/btt064","title":"Phylogenomic clustering for selecting non-redundant genomes for comparative genomics","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genomics; Comparative genomics; Cluster analysis; Genome; Computational biology; Computer science; Biology; Evolutionary biology; Genetics; Artificial intelligence; Gene","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":[0.004343572,0.002068006,0.001742112,0.007500781,0.002192369,0.002046049,0.002648287,0.001182223,0.005299388],"category_scores_gemma":[0.01287791,0.0008904397,0.001960575,0.006710153,0.0007264381,0.002005932,0.001822462,0.001714522,0.003332139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279827,"about_ca_system_score_gemma":0.00164955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002136358,"about_ca_topic_score_gemma":0.003322582,"domain_scores_codex":[0.997535,0.0008236415,0.0002062272,0.0006782382,0.0005766996,0.0001801997],"domain_scores_gemma":[0.9956992,0.001659261,0.0005089603,0.0008170179,0.001022806,0.0002928504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003725082,0.001511064,0.05645644,0.00548043,0.001914182,0.0009472065,0.00308268,0.04816973,0.2754182,0.01947559,0.05514403,0.5286754],"study_design_scores_gemma":[0.000517373,0.000546187,0.05363431,0.0004634832,0.000622743,0.001567704,0.00187481,0.7286621,0.1280319,0.04389874,0.03981381,0.0003668426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08396255,0.0007132234,0.8778645,0.0005440511,0.0001245246,0.0008171736,0.009827832,0.02370386,0.002442265],"genre_scores_gemma":[0.08362333,0.0001564127,0.9009396,0.0000901431,0.00003143611,0.0005315855,0.01190532,0.00230759,0.0004145456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007500781,"threshold_uncertainty_score":0.02297127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02680222815174952,"score_gpt":0.2642351388127584,"score_spread":0.2374329106610089,"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."}}