{"id":"W2064957473","doi":"10.1186/gm376","title":"Inferring novel gene-disease associations using Medical Subject Heading Over-representation Profiles","year":2012,"lang":"en","type":"article","venue":"Genome Medicine","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"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":"Disease; Similarity (geometry); MEDLINE; Computer science; Computational biology; Identification (biology); Health informatics; Informatics; Representation (politics); Subject (documents); Gene Annotation; Bioinformatics; Gene; Medicine; Artificial intelligence; Biology; Genetics; Genome; Pathology","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":[0.0007311639,0.0001531348,0.0002075572,0.00008487146,0.0001480513,0.000009540857,0.0001688643,0.0001815385,0.0001211065],"category_scores_gemma":[0.002264929,0.0001279083,0.00006034444,0.0001739658,0.0001928165,0.000007703784,0.0001278443,0.0001348698,0.00000676922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004939858,"about_ca_system_score_gemma":0.0001242775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001140944,"about_ca_topic_score_gemma":0.00001069845,"domain_scores_codex":[0.9985352,0.00007932168,0.0002860345,0.0002580995,0.0004313912,0.0004099729],"domain_scores_gemma":[0.999105,0.00006738014,0.0001132402,0.0002437247,0.00005825389,0.0004123544],"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":[0.00004551189,0.0001508406,0.1874938,0.00003923502,0.0001176914,0.000005494162,0.0004709017,0.00005422397,0.8038678,0.0001687455,0.0006831624,0.006902636],"study_design_scores_gemma":[0.005013744,0.0004607175,0.9016755,0.0002199498,0.0003268611,0.000125297,0.0008680358,0.003670663,0.02908508,0.0001826515,0.05744975,0.0009217104],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9627994,0.003064363,0.03163793,0.0009890964,0.0007178253,0.0001547312,0.00002989992,0.00004813378,0.000558596],"genre_scores_gemma":[0.9936135,0.00009354115,0.00254367,0.0005659533,0.002560448,0.00001604832,0.0003822074,0.00002155685,0.0002030879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7747827,"threshold_uncertainty_score":0.5215948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06901671946663247,"score_gpt":0.3624902022854343,"score_spread":0.2934734828188018,"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."}}