{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001605163,0.0007567973,0.0008397411,0.001344503,0.000376507,0.0007177271,0.001105107,0.0009277535,0.0008465125],"category_scores_gemma":[0.004807477,0.0003212224,0.0009858734,0.000801661,0.001024876,0.0009655774,0.001074913,0.0006954475,0.0005152303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006112022,"about_ca_system_score_gemma":0.001457674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002183095,"about_ca_topic_score_gemma":0.002422353,"domain_scores_codex":[0.9988475,0.0002306816,0.00008864314,0.0002887949,0.0004299942,0.0001144646],"domain_scores_gemma":[0.9979844,0.001037412,0.0002702051,0.0002320084,0.0003963403,0.00007969321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001103876,0.0002540898,0.008756096,0.0004603225,0.0002122495,0.0003598198,0.0002491947,0.1664104,0.3121086,0.02654908,0.001190873,0.4823454],"study_design_scores_gemma":[0.00004424358,0.000190498,0.00338702,0.00001541522,0.00004209386,0.000193942,0.00004492266,0.895594,0.08813263,0.01058049,0.001722675,0.00005217972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01876642,0.00008374391,0.9804954,0.00003953241,0.00001364053,0.00002658483,0.00006075458,0.000291433,0.0002224507],"genre_scores_gemma":[0.2261323,0.0001717551,0.7712364,0.0000869083,0.00003570331,0.0001620969,0.0006222692,0.00008366878,0.001468922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002183095,"threshold_uncertainty_score":0.008489013,"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."}}