{"id":"W2123708619","doi":"10.1186/1687-4153-2012-12","title":"Identification of CpG islands in DNA sequences using statistically optimal null filters","year":2012,"lang":"en","type":"article","venue":"EURASIP Journal on Bioinformatics and Systems Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CpG site; Identification (biology); Computational biology; Gene; Computer science; DNA sequencing; Genetics; Null (SQL); Biology; Algorithm; Data mining; DNA methylation; Gene expression","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":[0.001114232,0.0001306464,0.0002311761,0.0001228588,0.00007051231,0.00004140934,0.0001280519,0.0001533003,0.000008393375],"category_scores_gemma":[0.0001427209,0.0000981877,0.00004573892,0.00005969761,0.0000766962,0.00001938292,0.0000323249,0.00009653063,0.000003785522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001735349,"about_ca_system_score_gemma":0.00004273692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006475074,"about_ca_topic_score_gemma":7.945913e-7,"domain_scores_codex":[0.9986617,0.0001604623,0.0007240559,0.00009250395,0.0001036493,0.0002576059],"domain_scores_gemma":[0.9991994,0.00004774592,0.0004515268,0.0001334865,0.00006838135,0.00009948078],"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":[0.0001297593,0.00005406108,0.01008486,0.0001075622,0.00006201195,0.000002343628,0.0004968817,0.0002375905,0.9826808,0.003640414,0.00009912321,0.002404624],"study_design_scores_gemma":[0.004774065,0.006445379,0.02526363,0.001070299,0.0001848188,0.004246659,0.008812038,0.06765716,0.863566,0.00159841,0.01419626,0.002185264],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9490694,0.0006282622,0.04936428,0.00002784465,0.0004864477,0.0001443195,0.00004920341,0.000002563394,0.0002276928],"genre_scores_gemma":[0.9968582,0.0002686985,0.002605669,0.000046751,0.0001557308,0.00000569452,0.00001851107,0.000008119992,0.00003257827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1191148,"threshold_uncertainty_score":0.4003978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02522515860316512,"score_gpt":0.284707655133603,"score_spread":0.2594824965304379,"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."}}