{"id":"W1615242748","doi":"10.1186/1471-2105-6-236","title":"SIMPROT: Using an empirically determined indel distribution in simulations of protein evolution","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Indel; Alignment-free sequence analysis; Multiple sequence alignment; Sequence (biology); Phylogenetic tree; INDEL Mutation; Sequence alignment; Sequence analysis; Computational biology; Biology; Genetics; Molecular evolution; Protein family; Computer science; Algorithm; Peptide sequence; 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":[0.0001218231,0.00009985407,0.0001129138,0.00004211715,0.00004977288,0.00001006851,0.00009439897,0.0001081246,0.000002378825],"category_scores_gemma":[0.0000748822,0.00009737675,0.00004010778,0.0001022459,0.00004677289,0.000005273271,0.00006409513,0.00004180534,0.000001213383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004032513,"about_ca_system_score_gemma":0.0001050904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002135459,"about_ca_topic_score_gemma":0.0002938146,"domain_scores_codex":[0.999256,0.00002330633,0.0003841957,0.00009711643,0.0000863775,0.0001530704],"domain_scores_gemma":[0.999516,0.000006818916,0.0001423041,0.0002057968,0.00009037532,0.00003869407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001405601,0.0003900378,0.05234143,0.0001713204,0.0000365768,2.065897e-7,0.0006164506,0.3050091,0.6328023,0.0002802502,0.00003109139,0.008180704],"study_design_scores_gemma":[0.0007200064,0.0002330843,0.026111,0.00002023237,0.00001407425,0.000002951837,0.0001627186,0.9420767,0.02937494,0.0001416997,0.0009482864,0.0001943324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8906315,0.00008032551,0.1087906,0.0000110269,0.00001761644,0.0003116101,0.0001033701,0.00000242028,0.00005151222],"genre_scores_gemma":[0.9432324,0.000004410106,0.05650434,0.00001958291,0.00005849821,0.000008551495,0.000153496,0.000006554525,0.00001221536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6370676,"threshold_uncertainty_score":0.3970909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02861468696996599,"score_gpt":0.2802764922088181,"score_spread":0.2516618052388521,"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."}}