{"id":"W2964354311","doi":"10.1038/s41467-019-11026-x","title":"A machine-compiled database of genome-wide association studies","year":2019,"lang":"en","type":"article","venue":"Nature Communications","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Office of Naval Research; Ant Financial Services Group; National Institutes of Health; National Science Foundation; VMware; Stanford Bio-X; Accenture; Gordon and Betty Moore Foundation; Okawa Foundation for Information and Telecommunications","keywords":"Computer science; Precision and recall; Information extraction; Information retrieval; Association (psychology); Genetic programming; Genome-wide association study; Knowledge base; Data science; Artificial intelligence; Genotype; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957016,0.00007570645,0.0001445807,0.00003473057,0.00006172598,0.000005061047,0.0005707614,0.0002424315,0.0000110659],"category_scores_gemma":[0.001833331,0.00006502468,0.00005852119,0.0001094888,0.00008571662,0.000002275314,0.0004261753,0.0003027925,0.00001664367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002405798,"about_ca_system_score_gemma":0.00003824294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006038484,"about_ca_topic_score_gemma":0.00009241486,"domain_scores_codex":[0.9993715,0.0001064624,0.0001660437,0.0001386303,0.0001108674,0.0001065032],"domain_scores_gemma":[0.9981707,0.0003631634,0.0001399126,0.001130145,0.0001702825,0.00002576895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001006412,0.0004792805,0.7353802,0.0001432253,0.001059217,7.128201e-7,0.0005862352,0.00002463074,0.1887417,0.002393385,0.06654026,0.004550456],"study_design_scores_gemma":[0.0008563969,0.0001939139,0.07007613,0.00005430392,0.0000700133,0.000002044147,0.0005271814,0.0001781958,0.008010766,0.0002085978,0.9195784,0.0002440975],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7476986,0.2245488,0.0004170389,0.01554152,0.0006114094,0.0005528979,0.0004038882,0.00008157013,0.01014435],"genre_scores_gemma":[0.985873,0.004749996,0.007085259,0.0008162658,0.00002902896,0.0000139617,0.0005853103,0.000007608284,0.0008394968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8530381,"threshold_uncertainty_score":0.265163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02464967991211376,"score_gpt":0.3318762768121205,"score_spread":0.3072265969000067,"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."}}