{"id":"W2115504560","doi":"10.1186/gb-2008-9-2-r31","title":"Text-mining assisted regulatory annotation","year":2008,"lang":"en","type":"article","venue":"Genome biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Vlaamse regering; Fonds Wetenschappelijk Onderzoek; Genome British Columbia; Canadian Institutes of Health Research; Genome Canada; Michael Smith Health Research BC; National Evolutionary Synthesis Center; European Molecular Biology Organization; National Science Foundation","keywords":"Annotation; Regulatory sequence; Ranking (information retrieval); Computational biology; Computer science; Genome; Gene Annotation; Relevance (law); Genomics; Information retrieval; Gene; Data mining; Biology; Regulation of gene expression; Genetics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002975903,0.001375926,0.0009988334,0.008152766,0.0008575905,0.001735903,0.001783401,0.001062419,0.005919217],"category_scores_gemma":[0.01356152,0.0002464964,0.001224726,0.006322403,0.0005574896,0.002056848,0.001002696,0.001039871,0.002522241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009436408,"about_ca_system_score_gemma":0.002200536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0018576,"about_ca_topic_score_gemma":0.001990331,"domain_scores_codex":[0.9975169,0.0006729601,0.0004166451,0.000665165,0.0006350318,0.00009340823],"domain_scores_gemma":[0.9859937,0.008835962,0.001448559,0.0007745904,0.002744706,0.00020247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007865641,0.0006542987,0.01086637,0.007572058,0.0003597797,0.001540925,0.0009716527,0.01958794,0.08249043,0.01428594,0.04174977,0.8191342],"study_design_scores_gemma":[0.00038234,0.0004288409,0.01969313,0.001349882,0.0009294017,0.002894258,0.001278613,0.4782208,0.2131418,0.08328139,0.1981601,0.0002393677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08284151,0.00527589,0.820248,0.003587005,0.0005089206,0.001724979,0.05254592,0.02265679,0.01061104],"genre_scores_gemma":[0.1912042,0.002582276,0.7362236,0.0005152858,0.0003522349,0.001278109,0.06329605,0.0005758854,0.003972208],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008152766,"threshold_uncertainty_score":0.01980174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03047699018400425,"score_gpt":0.2702659858287964,"score_spread":0.2397889956447921,"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."}}