{"id":"W2125070329","doi":"10.1093/molbev/mss208","title":"Impact of Missing Data on Phylogenies Inferred from Empirical Phylogenomic Data Sets","year":2012,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":362,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Université de Montréal; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Missing data; Inference; Supermatrix; Phylogenetic tree; Phylogenomics; Biology; Set (abstract data type); Maximum parsimony; Sequence (biology); Bayesian probability; Phylogenetic network; Data set; Prior probability; Bayesian inference; Evolutionary biology; Interpretation (philosophy); Phylogenetics; Probabilistic logic; Computer science; Artificial intelligence; Machine learning; Mathematics; Genetics; 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":[0.0002570653,0.0002002053,0.0002387212,0.00004781265,0.00009474452,0.000008269944,0.0004491375,0.0002253441,0.000006298805],"category_scores_gemma":[0.0001456557,0.0001713509,0.00006140397,0.00005589409,0.0002099964,0.000003627208,0.0009153713,0.00008427652,0.000004716627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001791734,"about_ca_system_score_gemma":0.00006888837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001826611,"about_ca_topic_score_gemma":0.00001731068,"domain_scores_codex":[0.9987394,0.0001490346,0.0002240609,0.000517133,0.00005564864,0.0003147177],"domain_scores_gemma":[0.9985301,0.000031207,0.0001133173,0.001195265,0.00003680694,0.00009322564],"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":[0.0001014276,0.00007594091,0.3026214,0.00000377817,0.0002541416,5.642535e-7,0.00003401318,0.00001694468,0.6939037,0.00004666251,0.0004393981,0.002502025],"study_design_scores_gemma":[0.0006000976,0.0005156268,0.9734058,0.000009837975,0.0001068821,0.00001684476,0.00003090894,0.0004723123,0.02157315,0.0012512,0.00172295,0.0002943214],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810491,0.01303939,0.004196065,0.00007440028,0.0001591945,0.0001166638,0.001247837,0.000003806025,0.000113539],"genre_scores_gemma":[0.9951031,0.0002307988,0.00155679,0.00009307535,0.0001980177,0.000003358685,0.002794594,0.00001662246,0.000003697775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6723306,"threshold_uncertainty_score":0.6987489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05466960448727309,"score_gpt":0.3648530757839112,"score_spread":0.3101834712966381,"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."}}