{"id":"W3202525117","doi":"10.1101/2021.10.07.463580","title":"Pseudofinder: detection of pseudogenes in prokaryotic genomes","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation; National Aeronautics and Space Administration; National Science Foundation","keywords":"Pseudogene; Genome; Biology; Gene; ENCODE; Genetics; Computational biology; Identification (biology); Selection (genetic algorithm); Negative selection; Phylogenetic tree; Bacterial genome size; Evolutionary biology; Computer science; Ecology; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003024772,0.000412396,0.0005152329,0.0001696877,0.0000626099,0.0000498262,0.0003522178,0.0005124148,0.000006103146],"category_scores_gemma":[0.00009540896,0.0004692225,0.0001927037,0.0002412585,0.0001088362,0.000001721877,0.0006616432,0.0002653664,0.000002720474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006035173,"about_ca_system_score_gemma":0.0004344829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005749016,"about_ca_topic_score_gemma":0.00004330419,"domain_scores_codex":[0.9979227,0.000113318,0.000529711,0.0008677518,0.0001841264,0.0003823627],"domain_scores_gemma":[0.998276,0.00001426305,0.0003141276,0.0009522199,0.000348031,0.00009534149],"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":[0.00002823837,0.0001060232,0.03536709,0.0002704404,0.0001844989,0.00001172503,0.00001170564,0.0003228579,0.9636671,0.0000116998,0.000008250415,0.00001037575],"study_design_scores_gemma":[0.0003070566,0.00007966254,0.2044874,0.00008530781,0.00005265502,3.585109e-8,0.000009986169,0.00005947045,0.7940265,0.000001264446,0.0005046909,0.00038598],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.980611,0.01775445,0.0004067292,0.00003370743,0.0006556262,0.0004504556,0.00006819631,0.00001218521,0.000007614595],"genre_scores_gemma":[0.9942019,0.003365129,0.001861274,0.00005108887,0.0002949918,0.0001409571,7.591883e-7,0.00007969435,0.000004177862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1696406,"threshold_uncertainty_score":0.9997759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01097006265036804,"score_gpt":0.2066996351157698,"score_spread":0.1957295724654018,"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."}}