{"id":"W2167193190","doi":"10.1093/molbev/msh182","title":"Phylogenomics of Eukaryotes: Impact of Missing Data on Large Alignments","year":2004,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":406,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; Biotechnology and Biological Sciences Research Council","keywords":"Phylogenomics; Biology; Evolutionary biology; Missing data; Computational biology; Phylogenetics; Genetics; Machine learning; Computer science; Gene; Clade","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01716887,0.001422609,0.002907097,0.004963611,0.00238441,0.004518776,0.001758397,0.00163406,0.002096019],"category_scores_gemma":[0.08490071,0.001398612,0.001928806,0.006679566,0.001853214,0.004683792,0.002919665,0.004385082,0.0013184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008704492,"about_ca_system_score_gemma":0.0009290534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006437206,"about_ca_topic_score_gemma":0.001015127,"domain_scores_codex":[0.9819557,0.009680857,0.001728669,0.003665613,0.002480925,0.0004881987],"domain_scores_gemma":[0.9215014,0.06051977,0.004447661,0.009420612,0.002521208,0.001589349],"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":[0.007697251,0.00116951,0.2804458,0.006191597,0.006062328,0.008361497,0.004707035,0.1709142,0.2502784,0.02298377,0.01166061,0.229528],"study_design_scores_gemma":[0.0004921031,0.0007578658,0.210437,0.001295551,0.002492239,0.004481306,0.001960183,0.6000822,0.04949597,0.1001517,0.02796623,0.0003877199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6732723,0.00695681,0.2974335,0.002141774,0.0004285254,0.0001709683,0.01373663,0.003448876,0.002410686],"genre_scores_gemma":[0.8275197,0.002485946,0.1410559,0.000656576,0.0002079622,0.0003386064,0.02598292,0.001382239,0.0003702112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01716887,"threshold_uncertainty_score":0.09079874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01428097211628965,"score_gpt":0.2993191622130749,"score_spread":0.2850381900967852,"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."}}