{"id":"W4375955770","doi":"10.1093/bioinformatics/btad309","title":"Genome mining for anti-CRISPR operons using machine learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; National Institute of General Medical Sciences; National Institute of Allergy and Infectious Diseases; University of Nebraska-Lincoln; University of Toronto; U.S. Department of Agriculture","keywords":"CRISPR; Genome; Operon; Computational biology; Context (archaeology); Computer science; Python (programming language); Gene; Biology; Genetics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001884217,0.0001312027,0.0001248736,0.00007998582,0.0001409314,0.0000354687,0.0001286112,0.00008916124,0.00000613254],"category_scores_gemma":[0.00009421749,0.0001311516,0.00007872621,0.0001392035,0.00002105867,0.000005500395,0.0001135904,0.00005644648,0.00001817771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009587713,"about_ca_system_score_gemma":0.0000323587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004365931,"about_ca_topic_score_gemma":0.000003915827,"domain_scores_codex":[0.9992543,0.000007116564,0.0002357476,0.0001176019,0.00008260038,0.000302608],"domain_scores_gemma":[0.9996468,0.00001427646,0.00005432447,0.000178249,0.00004100834,0.00006534268],"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":[0.00001921406,0.00001658627,0.003042002,0.0002708118,0.00009497427,0.000002111288,0.0008583393,0.1097334,0.8821453,0.00002480983,0.0006440766,0.003148278],"study_design_scores_gemma":[0.0007383929,0.000210023,0.001889864,0.00002739237,0.00004090752,0.00002708554,0.000996263,0.784853,0.09368828,0.000005868796,0.1170972,0.0004257335],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.834343,0.0003665039,0.1643734,0.0000341462,0.0002080516,0.0002299039,0.00004837901,0.00007513972,0.0003215464],"genre_scores_gemma":[0.937066,0.0002742701,0.06079191,0.00008545339,0.0002700724,0.00001919075,0.000674068,0.00005092976,0.0007680882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7884571,"threshold_uncertainty_score":0.5348206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02191280019472707,"score_gpt":0.3098302355894656,"score_spread":0.2879174353947385,"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."}}