{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001434188,0.0001303515,0.0001587691,0.00005690592,0.0001412539,0.000004250701,0.0001755359,0.0003156636,0.00004373342],"category_scores_gemma":[0.0001146205,0.0001149406,0.00006677974,0.00009546912,0.0003781544,0.000001337304,0.00008824328,0.00007219041,0.00004109253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001336489,"about_ca_system_score_gemma":0.00007393281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006001358,"about_ca_topic_score_gemma":0.000005069112,"domain_scores_codex":[0.9990292,0.00008318386,0.0001958957,0.0003521292,0.0000589134,0.0002806972],"domain_scores_gemma":[0.9994915,0.0000213023,0.00007841575,0.00027916,0.00005273868,0.00007694981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00006647527,0.00002950251,0.01712926,0.000006474938,0.00005470053,0.00001154035,0.0001418952,0.000003378722,0.9526998,0.00008115522,0.002762799,0.02701297],"study_design_scores_gemma":[0.0007400291,0.000714646,0.5829695,0.000004990711,0.00001275949,0.0002554167,0.0001340999,0.00001391579,0.01522912,0.0001050838,0.3994847,0.0003356764],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940289,0.001892363,0.001792872,0.0001918701,0.0002458216,0.0000658281,0.00001486727,0.00005133695,0.001716097],"genre_scores_gemma":[0.9932929,0.0001552679,0.004337328,0.0004215614,0.0003484927,0.00001581041,0.0002885852,0.00001409376,0.001125955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9374707,"threshold_uncertainty_score":0.468714,"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."}}