{"id":"W2063216803","doi":"10.1186/1471-2148-8-331","title":"A class frequency mixture model that adjusts for site-specific amino acid frequencies and improves inference of protein phylogeny","year":2008,"lang":"en","type":"article","venue":"BMC Evolutionary Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Tula Foundation; Alfred P. Sloan Foundation","keywords":"Phylogenetic tree; Substitution (logic); Biology; Phylogenetics; Inference; Set (abstract data type); Empirical distribution function; Amino acid; Distribution (mathematics); Mathematics; Evolutionary biology; Statistics; Computer science; Artificial intelligence; Genetics","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":[0.00008835857,0.0002333017,0.0002777338,0.00005600132,0.0001736095,0.000003640798,0.0001907257,0.0002976424,0.000003781872],"category_scores_gemma":[0.00009037929,0.0002080917,0.0001154501,0.00005332516,0.0005727709,0.000002146823,0.0001585864,0.00007526053,0.000001484015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001791205,"about_ca_system_score_gemma":0.0001804249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002773182,"about_ca_topic_score_gemma":0.00006417016,"domain_scores_codex":[0.9988048,0.00005588183,0.0002660746,0.0004943263,0.00006336402,0.0003155603],"domain_scores_gemma":[0.9992446,0.0000405468,0.0001523849,0.000315058,0.0001840776,0.00006327427],"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":[0.0001002195,0.00004696884,0.04467992,0.00004806095,0.00004173668,4.939419e-7,0.00009462141,0.00005533472,0.951859,0.002492537,0.0003566434,0.0002244493],"study_design_scores_gemma":[0.002682053,0.00287647,0.4093193,0.00004507634,0.00007325295,0.0001293682,0.0002577996,0.00248393,0.5403368,0.02866853,0.01187694,0.001250488],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9636767,0.02684343,0.008124332,0.00005869272,0.00008795159,0.0005345301,0.0004624327,0.000006768009,0.0002051694],"genre_scores_gemma":[0.9687394,0.001567309,0.02887562,0.00006389014,0.0001420331,0.0001939498,0.0001823159,0.00001791495,0.0002176041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4115222,"threshold_uncertainty_score":0.8485731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03429746117771788,"score_gpt":0.2446286035272504,"score_spread":0.2103311423495325,"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."}}