{"id":"W4392190584","doi":"10.1186/s12859-024-05693-x","title":"GPAD: a natural language processing-based application to extract the gene-disease association discovery information from OMIM","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Computational biology; Disease; DNA microarray; Association (psychology); Gene; Natural (archaeology); Computer science; Biology; Data science; Bioinformatics; Genetics; Medicine; Gene expression; Psychology; 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":[0.0002573444,0.0001336579,0.00009093276,0.00005512611,0.0000991264,0.0003214734,0.0002138186,0.0001370728,0.00000394376],"category_scores_gemma":[0.0003898451,0.00008954011,0.00008200722,0.0001731976,0.00003731723,0.00005041894,0.00006217775,0.0001263053,0.0001041551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006159592,"about_ca_system_score_gemma":0.0002410316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002328177,"about_ca_topic_score_gemma":0.00003308382,"domain_scores_codex":[0.9991087,0.00002622082,0.0002957468,0.0001228678,0.0002557937,0.0001906791],"domain_scores_gemma":[0.9994135,0.00006670631,0.000119188,0.0002650028,0.00005708868,0.00007846172],"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":[0.000301645,0.00007480371,0.002811654,0.0006342694,0.000105204,0.00000224609,0.003103132,0.00202392,0.01043845,0.00006292678,0.0299182,0.9505236],"study_design_scores_gemma":[0.0004113088,0.0000823073,0.007493023,0.0001018984,0.000077779,0.000002266885,0.001143713,0.8265734,0.008339094,0.00006040595,0.1553745,0.0003403107],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09988863,0.003182592,0.8938463,0.00144684,0.0004171465,0.0004880175,0.0003096212,0.0001549687,0.00026585],"genre_scores_gemma":[0.9608902,0.0000221365,0.03417245,0.002177933,0.0003488074,0.000112475,0.00196074,0.00001397582,0.0003013003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9501832,"threshold_uncertainty_score":0.365134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006096063725336593,"score_gpt":0.2559648101059047,"score_spread":0.2498687463805681,"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."}}