{"id":"W2022692405","doi":"10.1186/1755-8794-6-s2-s3","title":"Compensating for literature annotation bias when predicting novel drug-disease relationships through Medical Subject Heading Over-representation Profile (MeSHOP) similarity","year":2013,"lang":"en","type":"article","venue":"BMC Medical Genomics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"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":"Leverage (statistics); Disease; Annotation; MEDLINE; Computer science; Precision medicine; Subject (documents); Representation (politics); Medicine; Information retrieval; Bioinformatics; Artificial intelligence; Biology; Pathology; World Wide Web","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00136563,0.000245477,0.0002789549,0.00005587132,0.0003558605,0.0001088154,0.0003559638,0.0005837526,0.0001678913],"category_scores_gemma":[0.01708028,0.0002194502,0.0001669179,0.0001605995,0.000251414,0.00002700757,0.000194351,0.0004850642,0.00001486741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005420517,"about_ca_system_score_gemma":0.0007384968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008662783,"about_ca_topic_score_gemma":0.0001873065,"domain_scores_codex":[0.9973635,0.0002805093,0.000619277,0.0006101083,0.000684517,0.000442062],"domain_scores_gemma":[0.9976546,0.00104837,0.0002331943,0.0003500811,0.0002067648,0.0005070285],"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":[0.001867157,0.001776079,0.6344776,0.003087577,0.0007171251,0.00005675594,0.01404747,0.0008383689,0.06353174,0.004531712,0.137751,0.1373175],"study_design_scores_gemma":[0.01635161,0.0008236613,0.1777708,0.002322763,0.0003687767,0.0001815017,0.006244431,0.6985674,0.01712311,0.01203299,0.0655649,0.002648109],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8370058,0.0008364042,0.1577311,0.00257091,0.0004849281,0.0008486535,0.0001279546,0.00009495213,0.0002993063],"genre_scores_gemma":[0.9104027,0.0001251572,0.08310968,0.001439877,0.001621798,0.0002924437,0.002473237,0.0000522567,0.0004828192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.697729,"threshold_uncertainty_score":0.9911993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08568723756780985,"score_gpt":0.3262356611169133,"score_spread":0.2405484235491034,"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."}}