{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001546139,0.0002353195,0.0002758387,0.00004827207,0.0002823402,0.00008419198,0.0002262483,0.0001091694,0.00000389769],"category_scores_gemma":[0.00002856476,0.0002232583,0.0001583821,0.00004558848,0.00006046971,0.000003550531,0.000144682,0.00004523887,0.00001842801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004011163,"about_ca_system_score_gemma":0.00008988813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001095905,"about_ca_topic_score_gemma":0.00002643934,"domain_scores_codex":[0.9988639,0.000007568832,0.0004326075,0.0002116826,0.00005747955,0.0004266968],"domain_scores_gemma":[0.9992052,0.00004887165,0.0002016831,0.0002499553,0.0002100874,0.00008421561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007846057,0.0000400172,0.000449792,0.0002359133,0.0003306719,4.411025e-8,0.002442943,0.002555234,0.9795234,0.00005651126,0.005031199,0.009255841],"study_design_scores_gemma":[0.004494088,0.002322809,0.004587456,0.00004143447,0.0001862074,0.00003392061,0.007435216,0.3080737,0.3516439,0.0008882427,0.3185115,0.001781518],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9005025,0.0007195142,0.09514625,0.00007385595,0.0003389643,0.002109783,0.0001563593,0.000009098308,0.0009436866],"genre_scores_gemma":[0.8296285,0.0001638728,0.1685893,0.0002859045,0.0003962352,0.0004602988,0.0001374155,0.00003494888,0.0003035707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6278794,"threshold_uncertainty_score":0.9104211,"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."}}