{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001663012,0.0001249812,0.0001782059,0.00004285579,0.0000527327,0.000002340327,0.0001709456,0.0001389067,0.000001567541],"category_scores_gemma":[0.00005246362,0.0001103191,0.00006958982,0.00004781128,0.0001334347,8.368692e-7,0.0002179166,0.00004091503,7.933667e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000191125,"about_ca_system_score_gemma":0.00006942583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007711568,"about_ca_topic_score_gemma":0.00000862977,"domain_scores_codex":[0.9992493,0.0000457734,0.0001913605,0.0002945313,0.00004093893,0.0001780354],"domain_scores_gemma":[0.9993814,0.000006863417,0.0001166805,0.0004142115,0.00004294167,0.00003793824],"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":[0.00009319295,0.0000910994,0.02959467,0.00001133711,0.0001783295,9.227237e-7,0.00002652073,0.0003656422,0.9674816,0.001586396,0.00002022273,0.0005500709],"study_design_scores_gemma":[0.002837962,0.003134944,0.3369657,0.00005396577,0.000119257,0.0000304162,0.00008179297,0.0001970005,0.6374673,0.01821578,0.0004761021,0.0004197886],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795769,0.003380441,0.01644246,0.00003792976,0.00005437186,0.0001004756,0.0002634903,0.000001394078,0.0001425597],"genre_scores_gemma":[0.9981601,0.000235402,0.001286721,0.00004472252,0.00003394348,0.000002036911,0.0002238893,0.000009822576,0.000003356916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3300143,"threshold_uncertainty_score":0.4498684,"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."}}