{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1935198,0.00151934,0.002180814,0.003445616,0.003761452,0.004177602,0.003780519,0.003532229,0.001671736],"category_scores_gemma":[0.5360148,0.00197139,0.004123115,0.004530343,0.008780349,0.007146577,0.004511028,0.00866512,0.0003569843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002607028,"about_ca_system_score_gemma":0.001669826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004636507,"about_ca_topic_score_gemma":0.004707973,"domain_scores_codex":[0.8277408,0.1338164,0.009320265,0.01531067,0.01131299,0.002498856],"domain_scores_gemma":[0.1999259,0.7361429,0.0226543,0.03408452,0.004964751,0.002227676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005997918,0.0007679919,0.5716681,0.002631919,0.008342228,0.004048162,0.006345761,0.2789126,0.01008881,0.02432358,0.004026925,0.08284602],"study_design_scores_gemma":[0.0004950729,0.001219409,0.2696693,0.001611164,0.003544372,0.004191917,0.003825946,0.5438425,0.02090233,0.1435877,0.00648394,0.0006264033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.837346,0.00262347,0.1489882,0.005721702,0.0002599485,0.0001811551,0.00248641,0.0007152939,0.001677852],"genre_scores_gemma":[0.9635862,0.0004721765,0.03275827,0.001215638,0.00009028309,0.0001175675,0.001422504,0.0001789683,0.000158404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1935198,"threshold_uncertainty_score":0.9945336,"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."}}