{"id":"W2014139771","doi":"10.1016/j.jbi.2014.05.013","title":"Automatic construction of a large-scale and accurate drug-side-effect association knowledge base from biomedical literature","year":2014,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Intertek (Canada)","funders":"National Center for Research Resources; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute","keywords":"Computer science; Drug; MEDLINE; Artificial intelligence; Parsing; Machine learning; Support vector machine; Natural language processing; Ranking (information retrieval); Set (abstract data type); Knowledge base; Information retrieval; Medicine; Pharmacology; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004377466,0.0001675514,0.0005125505,0.0004478274,0.00007429055,0.0001795079,0.0004600312,0.0001881487,0.00001644141],"category_scores_gemma":[0.002019377,0.0001237184,0.0001453307,0.0007804703,0.0001477627,0.001158121,0.0002294474,0.0004350231,0.000009102702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001335674,"about_ca_system_score_gemma":0.0002540662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002642723,"about_ca_topic_score_gemma":0.000001090169,"domain_scores_codex":[0.9967729,0.0005225264,0.001375549,0.0001027707,0.0009704966,0.0002556848],"domain_scores_gemma":[0.9949186,0.002737155,0.001433778,0.0002063467,0.0003744752,0.0003296661],"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":[0.00008869448,0.0009266679,0.003354502,0.001597931,0.0005759204,0.00002736451,0.04247585,0.000237559,0.001097671,0.006832703,0.01760184,0.9251833],"study_design_scores_gemma":[0.001663095,0.0003449469,0.003297369,0.0005717929,0.00005922171,0.0001338357,0.0002210621,0.981566,0.0005999078,0.006261867,0.005134801,0.000146072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4408156,0.0001358532,0.5571105,0.0007915588,0.0009121135,0.00007938685,0.00003181883,0.00002341318,0.00009967802],"genre_scores_gemma":[0.4672983,0.00005840251,0.5318071,0.0003136521,0.0004472268,0.000002866628,0.0000459384,0.00001026613,0.00001623129],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9813285,"threshold_uncertainty_score":0.504509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006573931731527429,"score_gpt":0.2843456287834984,"score_spread":0.277771697051971,"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."}}