{"id":"W2005255873","doi":"10.1186/1471-2105-13-249","title":"Quantitative biomedical annotation using medical subject heading over-representation profiles (MeSHOPs)","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Child and Family Research Institute; University of British Columbia","funders":"National Institute of General Medical Sciences; Michael Smith Health Research BC; Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Computer science; Controlled vocabulary; Annotation; Information retrieval; Vocabulary; Ontology; Representation (politics); Subject (documents); Set (abstract data type); Unified Medical Language System; Open Biomedical Ontologies; Visualization; Data science; Natural language processing; Data mining; Artificial intelligence; World Wide Web; Ontology alignment","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":[0.0006883066,0.0001793685,0.0001982028,0.0001100477,0.0001345528,0.00003508464,0.0001916546,0.0003712155,0.00006111589],"category_scores_gemma":[0.001509311,0.0001491471,0.00009341598,0.000249175,0.0003098016,0.00003063264,0.0001307305,0.000148297,0.00003495126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003155021,"about_ca_system_score_gemma":0.0002114065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002478465,"about_ca_topic_score_gemma":0.00001069396,"domain_scores_codex":[0.9982975,0.0001009435,0.0004762973,0.0001593081,0.0005309663,0.0004349897],"domain_scores_gemma":[0.9991314,0.0001187318,0.0001873402,0.0002228602,0.00007080484,0.0002688412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001620525,0.00198928,0.3780482,0.002121148,0.0009114658,0.00002471148,0.01539511,0.0005529302,0.1874314,0.008582179,0.05602214,0.347301],"study_design_scores_gemma":[0.005074875,0.001766788,0.03210982,0.0004234763,0.000191612,0.0005312342,0.01570859,0.8344676,0.049892,0.0002616602,0.05788623,0.00168608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.612516,0.0006222161,0.385145,0.0001137677,0.0007025759,0.0002106817,0.00002862448,0.0000586448,0.0006025617],"genre_scores_gemma":[0.6326135,0.00009054197,0.3655863,0.0003322502,0.0006669262,0.00002460924,0.0005253236,0.00002849379,0.0001320337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8339147,"threshold_uncertainty_score":0.6082042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06687942214877576,"score_gpt":0.3695098940486,"score_spread":0.3026304718998242,"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."}}